Motor vehicle road track splitting optimization method, device, computer readable storage medium and computer program product

Abstract

The embodiment of the present application provides a kind of motor vehicle road track splitting optimization method, device, computer readable storage medium and computer program product, the method comprises: the driving data information of motor vehicle is acquired in real time and the track feature information of each frame output by vehicle-mounted millimeter wave radar;Judge whether motor vehicle is in the predetermined road scene needing to implement optimization to track splitting;When determining that motor vehicle is in predetermined road scene, determine whether the actual number of moving target in each frame track feature information increases;When determining that the actual number of moving target increases, new generation track is acquired, and the predetermined area range around the position center of new generation track is demarcated as secondary clustering area;All track points in secondary clustering area are secondary clustered based on improved k-means clustering algorithm model to output clustering result;And the track points in secondary clustering area are merged with mature track around secondary clustering area to generate target optimization track.This embodiment can reduce track splitting, avoid misjudgment.

Description

Technical Field

[0001] This invention relates to the field of motor vehicle driving assistance technology, and in particular to a method, apparatus, computer-readable storage medium, and computer program product for optimizing motor vehicle road trajectory splitting. Background Technology

[0002] The vehicle navigation system installed in a motor vehicle is based on the vehicle-mounted millimeter-wave radar to detect objects around the vehicle and generate radar data information to generate a navigation track for the driver's reference. It is an important part of realizing intelligent assisted driving.

[0003] In congested urban scenarios with high traffic volume and vehicle density, vehicle-mounted millimeter-wave radar often exhibits track splitting when detecting large vehicles. This typically manifests as one or more discontinuous sub-tracks splitting off near the vehicle's established trajectory during the starting and stopping phases of large vehicles, particularly in urban traffic light and congestion scenarios. This phenomenon can easily cause misjudgments by vehicle collision avoidance systems, affecting the vehicle's assisted driving capabilities.

[0004] To minimize track splitting, existing optimization methods typically set broader association rules in radar tracking algorithms. However, the inventors discovered in practice that overly broad association rules can cause the tracks of two or more vehicles traveling in close proximity to merge into one track, compromising navigation safety. Summary of the Invention

[0005] The technical problem to be solved by the embodiments of the present invention is to provide a method for optimizing motor vehicle road track splitting, which can effectively reduce track splitting and avoid misjudgment.

[0006] A further technical problem to be solved by the embodiments of the present invention is to provide a motor vehicle road track splitting optimization device, which can effectively reduce track splitting and avoid misjudgment.

[0007] A further technical problem to be solved by the embodiments of the present invention is to provide a computer-readable storage medium for storing a computer program that can effectively reduce track splitting and avoid misjudgment.

[0008] A further technical problem to be solved by the embodiments of the present invention is to provide a computer program product that can effectively reduce track splitting and avoid misjudgment.

[0009] To address the aforementioned technical problems, this invention first provides the following technical solution: a method for optimizing motor vehicle road trajectory splitting, comprising the following steps: Real-time acquisition of vehicle driving data and trajectory feature information output by the vehicle-mounted millimeter-wave radar for each frame; Based on the driving data information and the trajectory feature information, it is determined whether the motor vehicle is in a predetermined road scenario where trajectory splitting needs to be optimized; When it is determined that the motor vehicle is in the predetermined road scene, it is determined whether the actual number of moving targets in the trajectory feature information of each frame has increased based on the trajectory feature information. When it is determined that the actual number of moving targets increases, a new track is generated by tracking based on the track feature information output by the vehicle-mounted millimeter-wave radar, and a predetermined area around the location center of the new track is defined as a secondary clustering region. A secondary clustering algorithm model is used to perform secondary clustering on all track points within the secondary clustering region to output the clustering results; and Based on the clustering results, the track points within the secondary clustering region are merged with the mature tracks surrounding the secondary clustering region to generate the target optimized track.

[0010] Furthermore, the step of performing secondary clustering on all track points within the secondary clustering region based on the improved k-means clustering algorithm model to output the clustering results specifically includes: The optimal number of clusters is determined by combining the number of moving target tracks in the historical frames output by the vehicle-mounted millimeter-wave radar with the elbow rule. Based on the kernel density estimation algorithm model, high-density regions of track points in the secondary clustering region are selected, and the center point of the high-density region is used as the initial cluster centroid. A spatiotemporal similarity function is obtained based on the track feature information in the historical frames output by the vehicle-mounted millimeter-wave radar; Iteratively update the positions of the cluster centroids to minimize the spatiotemporal similarity function; and Clustering is performed based on the location of the cluster centroid when the spatiotemporal similarity function is minimized, and the clustering results are output.

[0011] Furthermore, the spatiotemporal similarity function is expressed as: , in, This represents the Euclidean distance between the waypoint and the cluster centroid. This represents an exponential decay function based on the inter-frame timestamps of waypoints. The radial velocity component represents the path point, where α, β, and γ are preset weighting indices. It represents spatiotemporal similarity.

[0012] Furthermore, dividing the predetermined area around the location center of the newly generated track into a secondary clustering region specifically means dividing the secondary clustering region with the location center of the newly generated track as the center and a predetermined multiple of the association threshold as the radius.

[0013] Furthermore, the predetermined road scenario is either a vehicle starting and stopping at traffic lights or a vehicle slow-speed congestion scenario.

[0014] Furthermore, the step of determining whether a motor vehicle is in a predetermined road scenario requiring optimization of trajectory splitting based on the driving data information and the trajectory feature information specifically includes: Based on the driving data information, determine the vehicle speed range corresponding to the trajectory feature information of a predetermined number of consecutive frames; If the vehicle speed corresponding to the trajectory feature information of a consecutive predetermined number of frames is zero, then it is further determined whether the number of mature stationary trajectories within a predetermined range around the installation location of the vehicle-mounted millimeter-wave radar is greater than a first predetermined number. If so, it is determined to be a traffic light stop scenario; and If the vehicle speed corresponding to the trajectory feature information of a consecutive predetermined number of frames is not zero but is less than a predetermined speed threshold, then it is further determined whether the number of mature low-speed trajectories within a predetermined range around the vehicle-mounted millimeter-wave radar is less than a second predetermined number. If yes, it is determined to be a vehicle traffic light start-stop scenario; if no, it is determined to be a vehicle low-speed congestion scenario.

[0015] On the other hand, in order to solve the above-mentioned further technical problems, the present invention provides the following technical solution: a motor vehicle road track splitting optimization device, connected to an on-board millimeter-wave radar, the device including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements the motor vehicle road track splitting optimization method as described in any of the above claims.

[0016] Furthermore, in order to solve the aforementioned technical problems, the present invention provides the following technical solution: a computer-readable storage medium, including a stored computer program, wherein, when the computer program is running, it controls the device where the computer-readable storage medium is located to execute the motor vehicle road trajectory splitting optimization method as described above.

[0017] Furthermore, in order to solve the aforementioned technical problems, the present invention provides the following technical solution: a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, it implements the steps of the motor vehicle road trajectory splitting optimization method as described in any of the above claims.

[0018] After adopting the above technical solution, the embodiments of the present invention have at least the following beneficial effects: The embodiments of the present invention first determine whether the motor vehicle is in a predetermined road scene that requires optimization of track splitting based on the driving data information of the motor vehicle and the track feature information output by the vehicle-mounted millimeter-wave radar. When it is determined that the motor vehicle is in the predetermined road scene, it then determines whether the actual number of moving targets in the track feature information of each frame has increased. The increase in the actual number of moving targets will lead to the splitting and generation of a new track. Therefore, it further defines a predetermined area around the location center of the newly generated track as a secondary clustering area, and performs secondary clustering on all track points in the secondary clustering area based on the improved k-means clustering algorithm model to output the clustering result. Finally, based on the clustering result, it merges the track points in the secondary clustering area with the mature tracks around the secondary clustering area to generate the target optimized track, thereby realizing the re-merging of the split track into the mature track and reducing misjudgment. Attached Figure Description

[0019] Figure 1 This is a flowchart illustrating the steps of an optional embodiment of the motor vehicle road trajectory splitting optimization method of the present invention.

[0020] Figure 2 The flowchart below shows a specific step S5 of an optional embodiment of the motor vehicle road trajectory splitting optimization method of the present invention.

[0021] Figure 3 The flowchart below shows a specific step S2 of an optional embodiment of the motor vehicle road trajectory splitting optimization method of the present invention.

[0022] Figure 4 This is a schematic diagram of an optional embodiment of the motor vehicle road trajectory splitting optimization device of the present invention.

[0023] Figure 5 This is a functional block diagram of an optional embodiment of the motor vehicle road trajectory splitting optimization device of the present invention. Detailed Implementation

[0024] The present application will now be described in further detail with reference to the accompanying drawings and specific embodiments. It should be understood that the following illustrative embodiments and descriptions are only used to explain the present invention and are not intended to limit the present invention. Moreover, the embodiments and features in the embodiments of the present application can be combined with each other unless otherwise specified.

[0025] like Figure 1 As shown, an optional embodiment of the present invention provides a method for optimizing motor vehicle road trajectory splitting, comprising the following steps: S1: Real-time acquisition of vehicle driving data and track feature information output by vehicle-mounted millimeter-wave radar 1 for each frame; S2: Based on the driving data information and the trajectory feature information, determine whether the motor vehicle is in a predetermined road scenario where trajectory splitting needs to be optimized; S3: When it is determined that the motor vehicle is in the predetermined road scene, it is determined whether the actual number of moving targets in the trajectory feature information of each frame has increased based on the trajectory feature information; S4: When it is determined that the actual number of moving targets increases, a new generated track is further obtained based on the track feature information output by the vehicle-mounted millimeter-wave radar 1, and the predetermined area around the position center of the new generated track is defined as a secondary clustering region. S5: Based on the improved k-means clustering algorithm model, perform secondary clustering on all track points within the secondary clustering region to output the clustering results; and S6: Based on the clustering results, the track points in the secondary clustering region are merged with the mature tracks around the secondary clustering region to generate the target optimized track.

[0026] This invention first determines whether a vehicle is in a predetermined road scenario requiring optimization of track splitting based on its driving data and track feature information output by the vehicle-mounted millimeter-wave radar 1. When the vehicle is determined to be in the predetermined road scenario, the invention then determines whether the actual number of moving targets in each frame of track feature information has increased. An increase in the actual number of moving targets will lead to the generation of a new track. Therefore, a predetermined area around the location center of the newly generated track is defined as a secondary clustering region. Based on an improved k-means clustering algorithm model, all track points within the secondary clustering region are further clustered to output clustering results. Finally, based on the clustering results, the track points within the secondary clustering region are merged with mature tracks around the secondary clustering region to generate a target-optimized track. This achieves the re-merging of split tracks into mature tracks, reducing misjudgments.

[0027] In an optional embodiment of the present invention, such as Figure 2 As shown, step S5 specifically includes: S51: Determine the optimal number of clusters by combining the number of moving target tracks in the historical frames output by the vehicle-mounted millimeter-wave radar 1 with the elbow method; S52: Based on the kernel density estimation (KDE) algorithm model, high-density regions of track points in the secondary clustering region are selected, and the center point of the high-density region is used as the initial cluster centroid; S53: Obtain a spatiotemporal similarity function based on the track feature information in the historical frames output by the vehicle-mounted millimeter-wave radar 1; S54: Iteratively update the position of the cluster centroid to minimize the spatiotemporal similarity function; and S55: Clustering is performed based on the position of the cluster centroid when the spatiotemporal similarity function is minimized, and the clustering results are output.

[0028] This embodiment determines the optimal number of clusters by combining the number of moving target tracks in the historical frames output by the vehicle-mounted millimeter-wave radar 1 with the elbow rule, thereby selecting the optimal number of clusters (K value) for moving target tracks in the historical frames. Then, to avoid local optima caused by random initialization, a kernel density estimation (KDE) algorithm model is used to filter high-density regions of track points in the secondary clustering region, and the center point of the high-density region is selected as the initial cluster centroid. Further, a spatiotemporal similarity function is obtained based on the track feature information in the historical frames. By iteratively updating the position of the cluster centroid, the spatiotemporal similarity function is minimized to obtain the final cluster centroid. The clustering result (cluster label and cluster centroid of each track) can be output by clustering based on the position of the cluster centroid.

[0029] In an optional embodiment of the present invention, the spatiotemporal similarity function is expressed as: , in, This represents the Euclidean distance between the waypoint and the cluster centroid. This represents an exponential decay function based on the inter-frame timestamps of waypoints. The radial velocity component represents the path point, where α, β, and γ are preset weighting indices. It represents spatiotemporal similarity.

[0030] In this embodiment, the spatiotemporal similarity function captures the geometric distribution, temporal continuity, and motion consistency of the target simultaneously through a linear combination of Euclidean distance (space), exponentially decaying time difference (time), and radial velocity difference (motion). This results in high computational accuracy and improved clustering accuracy.

[0031] In an optional embodiment of the present invention, dividing the predetermined area around the location center of the newly generated track into a secondary clustering region specifically means: using the location center of the newly generated track as the center and a predetermined multiple (e.g., 3-5 times) of the association threshold as the radius to divide the secondary clustering region. In this embodiment, the secondary clustering region is divided with a predetermined multiple of the association threshold as the radius. By automatically adjusting the processing granularity through the association threshold, the computational load is significantly reduced while ensuring the clustering quality of the core region.

[0032] In an optional embodiment of the present invention, the predetermined road scenario is a vehicle traffic light start-stop scenario or a vehicle low-speed congestion scenario. In this embodiment, when a motor vehicle is in either of these two scenarios, the vehicle will experience continuous start-stop processes, during which track splitting is likely to occur, requiring corresponding track splitting optimization.

[0033] In an optional embodiment of the present invention, such as Figure 3 As shown, step S2 specifically includes: S21: Based on the driving data information, determine the vehicle speed interval corresponding to the trajectory feature information of a consecutive predetermined number of frames; S22: If the vehicle speed corresponding to the track feature information of a consecutive predetermined number of frames is zero, then it is further determined whether the number of mature stationary tracks within a predetermined range around the installation location of the vehicle-mounted millimeter-wave radar 1 (e.g., a 10-meter radius range centered on the vehicle-mounted millimeter-wave radar 1) is greater than the first predetermined number. If so, it is determined to be a vehicle stopped at a traffic light scenario; and S23: If the vehicle speed corresponding to the track feature information of a consecutive predetermined number of frames is not zero but is less than a predetermined speed threshold, then it is further determined whether the number of mature low-speed tracks within a predetermined range around the vehicle-mounted millimeter-wave radar 1 is less than a second predetermined number. If yes, it is determined to be a vehicle traffic light start-stop scenario; if no, it is determined to be a vehicle low-speed congestion scenario.

[0034] In this embodiment, since both the traffic light start-stop scenario and the low-speed traffic jam scenario involve brief alternating start-stop processes of motor vehicles, further determination can be made by combining the range of the vehicle speed and the number of mature stationary tracks and mature low-speed tracks within a predetermined range around the installation location of the vehicle millimeter-wave radar 1. This allows for accurate determination of whether the vehicle is currently in a traffic light stop scenario or a low-speed traffic jam scenario.

[0035] In practice, the complete process for determining road type is as follows: The first step is to determine whether the vehicle speed in multiple frames is greater than 50 km / h, whether the number of moving tracks in the ROI area of ​​the vehicle millimeter-wave radar 1 is greater than k1, and whether the vehicle acceleration information is stable in multiple frames based on the vehicle speed information in the vehicle status data. If the above conditions are met, it is determined that the vehicle is currently on a highway or expressway; otherwise, proceed to the second step below. The second step is to determine whether the vehicle speed in multiple frames is greater than 10km / h and whether the vehicle acceleration in multiple frames is stable. If the above conditions are met, it is determined to be an urban expressway; otherwise, proceed to the third step below. The third step is to determine whether the vehicle speed is equal to 0 km / h for multiple frames. If the vehicle speed is equal to 0 km / h for multiple frames, then it is further determined whether the number of mature stationary tracks within a 10-meter radius of the radar installation location is greater than k2. If the number of mature stationary tracks is greater than k2, it is determined to be a traffic light stop scenario. If the number of mature stationary tracks is less than or equal to k2, it is determined to be a normal stop scenario. If the vehicle speed is not equal to 0 km / h for multiple frames, then proceed to the following fourth step. The fourth step is to determine whether the number of mature low-speed tracks within a 10-meter radius of the radar installation location is less than k3. If the number of mature low-speed tracks is less than k3, it is determined to be a traffic light start-stop scenario. If the number of mature low-speed tracks is greater than or equal to k3, it is determined to be a low-speed traffic jam scenario.

[0036] On the other hand, such as Figure 4 As shown, an optional embodiment of the present invention provides a motor vehicle road track splitting optimization device 3, which is connected to an on-board millimeter-wave radar 1. It includes a processor 30, a memory 32, and a computer program stored in the memory 32 and configured to be executed by the processor 30. When the processor 30 executes the computer program, it implements the motor vehicle road track splitting optimization method as described in any of the above embodiments.

[0037] For example, the computer program can be divided into one or more modules / units, which are stored in the memory 32 and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the motor vehicle road trajectory splitting optimization device 3. For example, the computer program can be divided into... Figure 5 The functional modules in the motor vehicle road trajectory splitting optimization device 3 include the trajectory information acquisition module 41, the road scene judgment module 42, the moving target number judgment module 43, the clustering region delineation module 44, the secondary clustering module 45, and the target trajectory output module 46, which respectively perform the above steps S1-S6.

[0038] The vehicle road track splitting optimization device 3 can be a computing device such as a desktop computer, laptop, handheld computer, or cloud server. The vehicle road track splitting optimization device 3 may include, but is not limited to, a processor 30 and a memory 32. Those skilled in the art will understand that the schematic diagram is merely an example of the vehicle road track splitting optimization device 3 and does not constitute a limitation on the device. It may include more or fewer components than shown, or combine certain components, or use different components. For example, the vehicle road track splitting optimization device 3 may also include input / output devices, network access devices, buses, etc.

[0039] The processor 30 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. The general-purpose processor can be a microprocessor or any conventional processor. The processor 30 is the control center of the vehicle road trajectory splitting optimization device 3, connecting all parts of the device via various interfaces and lines.

[0040] The memory 32 can be used to store the computer program and / or modules. The processor 30 implements various functions of the motor vehicle road trajectory splitting optimization device 3 by running or executing the computer program and / or modules stored in the memory 32 and calling the data stored in the memory 32. The memory 32 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as image recognition function, image overlay function, etc.), etc.; the data storage area may store data created according to the use of the control device (such as image data, etc.). In addition, the memory 32 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0041] If the functions described in the embodiments of the present invention are implemented in the form of software functional modules or units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the embodiments of the present invention can implement all or part of the processes in the methods described above, or they can be accomplished by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by the processor 30, 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 the 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 included 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, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0042] In another aspect, an optional embodiment of the present invention provides a computer-readable storage medium comprising a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the motor vehicle road trajectory splitting optimization method as described in any of the above embodiments.

[0043] In another aspect, an optional embodiment of the present invention provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the motor vehicle road trajectory splitting optimization method as described in any of the above embodiments.

[0044] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0045] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the scope of protection of the present invention.

Claims

1. A method for optimizing motor vehicle road trajectory splitting, characterized in that, The method includes the following steps: Real-time acquisition of vehicle driving data and trajectory feature information output by the vehicle-mounted millimeter-wave radar for each frame; Based on the driving data information and the trajectory feature information, it is determined whether the vehicle is in a predetermined road scenario that requires optimization of trajectory splitting. The predetermined road scenario is a vehicle traffic light start-stop scenario or a vehicle low-speed congestion scenario, specifically including: Based on the driving data information, determine the vehicle speed range corresponding to the trajectory feature information of a predetermined number of consecutive frames; If the vehicle speed corresponding to the trajectory feature information of a consecutive predetermined number of frames is zero, then it is further determined whether the number of mature stationary trajectories within a predetermined range around the installation location of the vehicle-mounted millimeter-wave radar is greater than a first predetermined number. If so, it is determined to be a traffic light stop scenario; and If the vehicle speed corresponding to the trajectory feature information of a consecutive predetermined number of frames is not zero but is less than a predetermined speed threshold, then it is further determined whether the number of mature low-speed trajectories within a predetermined range around the vehicle-mounted millimeter-wave radar is less than a second predetermined number. If yes, it is determined to be a vehicle traffic light start-stop scenario; if no, it is determined to be a vehicle low-speed congestion scenario. When it is determined that the motor vehicle is in the predetermined road scene, it is determined whether the actual number of moving targets in the trajectory feature information of each frame has increased based on the trajectory feature information. When it is determined that the actual number of moving targets increases, a new track is generated by tracking based on the track feature information output by the vehicle-mounted millimeter-wave radar, and a predetermined area around the location center of the new track is defined as a secondary clustering region. A secondary clustering algorithm model is used to perform secondary clustering on all track points within the secondary clustering region to output the clustering results; and Based on the clustering results, the track points within the secondary clustering region are merged with the mature tracks surrounding the secondary clustering region to generate the target optimized track.

2. The method for optimizing motor vehicle road trajectory splitting as described in claim 1, characterized in that, The improved k-means clustering algorithm model performs secondary clustering on all track points within the secondary clustering region to output the clustering results, specifically including: The optimal number of clusters is determined by combining the number of moving target tracks in the historical frames output by the vehicle-mounted millimeter-wave radar with the elbow rule. Based on the kernel density estimation algorithm model, high-density regions of track points in the secondary clustering region are selected, and the center point of the high-density region is used as the initial cluster centroid. A spatiotemporal similarity function is obtained based on the track feature information in the historical frames output by the vehicle-mounted millimeter-wave radar; Iteratively update the positions of the cluster centroids to minimize the spatiotemporal similarity function; and Clustering is performed based on the location of the cluster centroid when the spatiotemporal similarity function is minimized, and the clustering results are output.

3. The method for optimizing motor vehicle road trajectory splitting as described in claim 2, characterized in that, The spatiotemporal similarity function is expressed as: ， in, This represents the Euclidean distance between the waypoint and the cluster centroid. This represents an exponential decay function based on the inter-frame timestamps of waypoints. The radial velocity component represents the path point, where α, β, and γ are preset weighting indices. It represents spatiotemporal similarity.

4. The method for optimizing motor vehicle road trajectory splitting as described in claim 1, characterized in that, The step of dividing the predetermined area around the location center of the newly generated track into a secondary clustering region specifically means dividing the secondary clustering region with the location center of the newly generated track as the center and a predetermined multiple of the association threshold as the radius.

5. A vehicle road trajectory splitting optimization device, connected to an onboard millimeter-wave radar, characterized in that, The device includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the motor vehicle road track splitting optimization method as described in any one of claims 1 to 4.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device on which the computer-readable storage medium is located to perform the motor vehicle road trajectory splitting optimization method as described in any one of claims 1 to 4.

7. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the motor vehicle road trajectory splitting optimization method as described in any one of claims 1-4.

Images