A method, device, medium and equipment for optimizing consistency of multiple segment tasks

Abstract

This application provides a method, apparatus, medium, and device for optimizing the consistency of multiple segment tasks, belonging to the field of map production technology. This application mainly includes a coordinate acquisition process, a new segment task acquisition process, and a pose adjustment process. The beneficial effect of this application is that by optimizing by creating new segment tasks adjacent to the original segment tasks and matching the same features obtained from multiple acquisition tasks, lateral and elevation errors between multiple segment tasks are avoided, ensuring consistency between multiple segment tasks.

Description

Technical Field

[0001] This application relates to the field of map production technology, and in particular to a method, apparatus, medium and device for optimizing the consistency of multiple segment tasks. Background Technology

[0002] A complete map is created using multiple segment tasks, each of which is produced separately. These unrelated segment tasks are then stitched together. Inevitably, stitching errors will occur during this process, so consistency optimization is needed to eliminate these errors between segment tasks. Summary of the Invention

[0003] To address the problems existing in the prior art, this application mainly provides a method, apparatus, medium, and device for optimizing the consistency of multiple segment tasks. By creating new segment tasks adjacent to the original segment tasks for optimization and matching identical elements obtained from multiple data acquisition tasks, it avoids lateral and elevation errors between multiple segment tasks, thus ensuring consistency among them.

[0004] To achieve the above objectives, one technical solution adopted in this application is: providing a method for optimizing consistency across multiple segment tasks, comprising:

[0005] The coordinate acquisition process involves extracting the absolute position coordinates of each trajectory point in each original segment task from multiple original segment tasks obtained by performing multiple acquisition tasks in a predetermined area for each acquisition task, and constructing optimized trajectory point coordinates for each trajectory point. The new segment task acquisition process involves obtaining multiple new segment tasks based on the absolute position coordinates of adjacent trajectory points between adjacent original segment tasks in each original segment task. The pose adjustment process involves adjusting the pose of segment task elements within the corresponding new segment task based on the optimized trajectory point coordinates, the absolute position coordinates of the trajectory points, the coordinates of adjacent optimized trajectory points of each trajectory point, the absolute position coordinates of adjacent trajectory points between adjacent original segment tasks within each new segment task, and the segment task elements representing the same object in the multiple original segment tasks.

[0006] Another technical solution adopted in this application is: providing a multi-segment task consistency optimization device, which includes:

[0007] The coordinate acquisition module is used to extract the absolute position coordinates of each trajectory point in each original segment task obtained from multiple acquisition tasks in a predetermined area where multiple original segment tasks can be obtained from each acquisition task, and to construct the optimized trajectory point coordinates for each trajectory point. The new segment task acquisition module is used to obtain multiple new segment tasks based on the absolute position coordinates of adjacent trajectory points between adjacent original segment tasks in each original segment task. The pose adjustment module is used to adjust the pose of the segment task elements within the corresponding new segment task based on the optimized trajectory point coordinates, the absolute position coordinates of the trajectory points, the coordinates of the adjacent optimized trajectory points of each trajectory point, the absolute position coordinates of adjacent trajectory points between adjacent original segment tasks within each new segment task, and the segment task elements representing the same object in the multiple original segment tasks.

[0008] Another technical solution adopted in this application is: providing a map production system, which includes multiple segment task consistency optimization devices, which are used for the multiple segment task consistency optimization method in the above solution.

[0009] Another technical solution adopted in this application is to provide a computer-readable storage medium storing computer instructions that are operated to execute the multi-segment task consistency optimization method in the above solution.

[0010] Another technical solution adopted in this application is: providing a computer device, which includes a processor and a memory, the memory storing computer instructions, which are operated to execute the multi-segment task consistency optimization method in the above solution.

[0011] The beneficial effects that the technical solution of this application can achieve are: providing a method, device, medium and equipment for optimizing the consistency of multiple segment tasks, optimizing by creating new segment tasks adjacent to the original segment tasks and matching the same elements obtained from multiple collection tasks, avoiding lateral and elevation errors between multiple segment tasks, and ensuring the consistency between multiple segment tasks. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a diagram illustrating the discontinuity between multiple task segments;

[0014] Figure 2 This is a flowchart illustrating a specific implementation of a multi-segment task consistency optimization method according to this application;

[0015] Figure 3 This is a flowchart illustrating a specific embodiment of a multi-segment task consistency optimization method according to this application;

[0016] Figure 4 This is a flowchart illustrating a specific implementation of a multi-segment task consistency optimization device according to this application;

[0017] Figure 5 This is a flowchart illustrating a specific embodiment of a multi-segment task consistency optimization device according to this application;

[0018] The accompanying drawings have illustrated specific embodiments of this disclosure, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concepts of this disclosure to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0019] The preferred embodiments of this application will now be described in detail with reference to the accompanying drawings, so that the advantages and features of this application can be more easily understood by those skilled in the art, thereby providing a clearer and more definite definition of the scope of protection of this application.

[0020] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0021] A complete map is created using multiple segment tasks, each of which is created separately. For example, a large area is divided into small grids. When building a map, we create these small grids one by one; each small grid is a segment task. When a data collection vehicle goes out to collect data, it creates a new grid every 3 kilometers. Then, the segment tasks that are not connected to each other are stitched together. Because GPS signals can be unstable during data collection, discontinuities can occur at the boundaries of these stitched grids. Figure 1As shown, the lateral and elevation errors can reach 75cm, with a maximum of 5m. Therefore, consistency optimization is needed for multiple segment tasks to eliminate errors between segment tasks.

[0022] When optimizing multiple segment tasks, existing technologies require the use of data such as images from the segment task data. When faced with segment task optimization tasks that collect data over a large area, such as an entire city, the memory required is enormous.

[0023] This application provides a method, apparatus, medium, and device for optimizing consistency among multiple segment tasks. By creating new segment tasks between segment tasks and using multi-path correlation of multiple acquisition tasks, the accuracy can be controlled within 20cm, ensuring consistency among multiple segment tasks. This application can optimize and further adjust the consistency of multiple segment tasks based only on point data. Compared with the existing technology that requires consistency optimization and adjustment based on image data, it can greatly save computation, save memory space, and improve optimization efficiency.

[0024] The technical solutions of this application will now be described in detail with reference to specific embodiments and accompanying drawings. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0025] Figure 2 This paper illustrates a specific implementation of a multi-segment task consistency optimization method according to this application.

[0026] exist Figure 2 In the specific embodiment shown, the method for optimizing the consistency of multiple segment tasks in this application includes: a coordinate acquisition process S201, in which the absolute position coordinates of each trajectory point in each original segment task obtained from multiple original segment tasks obtained by performing multiple acquisition tasks in a predetermined area where multiple original segment tasks can be obtained in each acquisition task are extracted, and the optimized trajectory point coordinates of each trajectory point are constructed; a new segment task acquisition process S202, in which multiple new segment tasks are obtained based on the absolute position coordinates of adjacent trajectory points between adjacent original segment tasks in each original segment task; and a pose adjustment process S203, in which the pose of the segment task elements within the corresponding new segment task is adjusted based on the optimized trajectory point coordinates, the absolute position coordinates of the trajectory points, the adjacent optimized trajectory point coordinates of the trajectory points adjacent to each trajectory point, the absolute position coordinates of adjacent trajectory points between adjacent original segment tasks within each new segment task, and the segment task elements representing the same object in the multiple original segment tasks.

[0027] This application optimizes the process by creating new segment tasks adjacent to the original segment tasks and matching the same elements obtained from multiple data collection tasks, thereby avoiding lateral and elevation errors between multiple segment tasks and ensuring consistency among them.

[0028] The coordinate acquisition process S201 represents the process of extracting the absolute position coordinates of each trajectory point in each of the multiple original segment tasks obtained from multiple acquisition tasks, which can be obtained from a predetermined area of ​​multiple original segment tasks in each acquisition task, and constructing the optimized trajectory point coordinates for each trajectory point. This facilitates the adjustment and optimization of the trajectory point coordinates based on the absolute position coordinates, achieving the goal of consistent optimization across multiple segment tasks.

[0029] Specifically, because GPS signals may be unstable, the actual coordinates of the track points may differ from the absolute coordinates obtained from GPS. Therefore, it is necessary to construct new track points to adjust the absolute positions so that the adjusted positions of the track points are closer to the actual positions.

[0030] In an optional embodiment of this application, multiple data collection vehicles are used to perform one data collection task on each of the predetermined areas to obtain multiple segment tasks for the predetermined areas. Because multiple data collection vehicles can work simultaneously, time for field data collection can be saved.

[0031] Optionally, a data collection task can be performed on a predetermined area by manually walking to obtain multiple segments of the predetermined area.

[0032] In optional embodiments of this application, the aforementioned multiple raw segment tasks include segment task elements such as GPS positioning information, image information, and data point cloud information. Optionally, the aforementioned GPS positioning information, image information, and data point cloud information are acquired using an inertial navigation system, camera, and radar configured on the data acquisition vehicle, respectively.

[0033] In an optional embodiment of this application, when using a data collection vehicle to perform a data collection task, the data acquired within each 20-minute interval is considered as a segment task.

[0034] In an optional specific embodiment of this application, the coordinates of a trajectory point in a segment task are constructed, and then the coordinates of other trajectory points in this segment task are obtained through trajectory extrapolation.

[0035] The process of obtaining new segment tasks, S202, represents the process of obtaining multiple new segment tasks based on the absolute position coordinates of adjacent trajectory points between adjacent original segment tasks in each original segment task. This facilitates the optimization of two adjacent original segment tasks by performing consistency optimization within the new segment tasks that include the boundaries of two adjacent original segment tasks.

[0036] In an optional specific embodiment of this application, the process of obtaining multiple new segment tasks based on the absolute position coordinates of adjacent trajectory points between adjacent original segment tasks in each original segment task includes creating the new segment task based on the absolute position coordinates of two adjacent trajectory points between two adjacent original segment tasks in each original segment task using segment task data within a predetermined range at the boundary of these two original segment tasks.

[0037] In an optional specific example of this application, the two adjacent original segment tasks each include 3 kilometers of segment task data. Using the segment task data of 500 meters at the boundary of these two original segment tasks, a new segment task including 1 kilometer of segment task data is created. In this way, as long as consistency optimization is performed on the new 1-kilometer segment task, consistency optimization of the two adjacent 3-kilometer segment tasks can be achieved.

[0038] Specifically, a continuous signal of a trajectory is extracted from multiple segment tasks obtained from a single collection task by the collection vehicle. Based on the relative positions between frames, the relative position coordinates of the trajectory points of two consecutive frames at the boundary of two adjacent segment tasks are obtained. A new segment task is then created using the relative positions of the trajectory points of these two consecutive frames within a predetermined range of segment tasks.

[0039] The pose adjustment process S203 represents the process of adjusting the pose of segment task elements within a newly created segment task based on the coordinates of optimized trajectory points, the absolute position coordinates of trajectory points, the coordinates of adjacent optimized trajectory points of each adjacent trajectory point, the absolute position coordinates of adjacent trajectory points between adjacent original segment tasks within each newly created segment task, and the segment task elements representing the same object in multiple original segment tasks. By adjusting the pose of segment task elements obtained from multiple acquisition tasks and adjusting their poses within the newly created segment task, consistency optimization between adjacent segment tasks of multiple original segment tasks obtained from a single acquisition task can be achieved. Specifically, if the information acquired in a single acquisition task is incomplete or inaccurate due to unstable GPS signals or obstructions, the information obtained from multiple acquisition tasks can be used to supplement each other, improving the accuracy of consistency optimization.

[0040] Specifically, the segment task elements representing the same object mentioned above can be information such as images or point clouds.

[0041] In an optional specific embodiment of this application, the consistency within each segment task in each original segment task meets the requirements. Therefore, it is only necessary to execute the pose adjustment S203 process, i.e., the pose adjustment process for the new segment task, and perform consistency optimization within the new segment task to ensure that the consistency between multiple segment tasks in the same path meets the requirements.

[0042] In an optional specific embodiment of this application, the pose adjustment process, in addition to the newly created segment task pose adjustment process described above, further includes the original segment task pose adjustment process, such as... Figure 3 As shown in process S303, the pose of the segment task elements within the corresponding original segment task is adjusted based on the coordinates of the optimized trajectory points, the absolute position coordinates of the trajectory points, the coordinates of the adjacent optimized trajectory points of each trajectory point, and the segment task elements representing the same object in the multiple original segment tasks. Specifically, performing consistency optimization within the original segment task after creating a new segment task, including the boundary between adjacent original segment tasks, or after optimization, can achieve better optimization results.

[0043] In an optional specific embodiment of this application, when the consistency within each segment task in each of the above-mentioned original segment tasks does not meet the requirements, the above-mentioned original segment task pose adjustment process needs to be performed before the new segment task pose adjustment process described in execution process S203, such as... Figure 3 As shown, the pose adjustment of the segment task elements in the corresponding original segment task is performed based on the coordinates of the optimized trajectory point, the absolute position coordinates of the trajectory point, the coordinates of the adjacent optimized trajectory point of each trajectory point, and the segment task elements representing the same object in the multiple original segment tasks, which makes the optimization efficiency higher and the optimization effect better.

[0044] In an optional embodiment of this application, the above-mentioned pose adjustment process further includes,

[0045] The distance calculation process involves calculating the first distance based on the coordinates of each optimized trajectory point and the corresponding absolute position coordinates of the trajectory point; calculating the second distance based on the coordinates of the optimized trajectory point and the corresponding adjacent optimized trajectory point coordinates; calculating the third distance based on the absolute position coordinates of the adjacent trajectory points between adjacent original segment tasks within each newly created segment task; and calculating the fourth distance based on the coordinate information of the segment task elements representing the same object in multiple newly created segment tasks of multiple collection tasks.

[0046] The distance optimization calculation process involves adjusting the first, second, third, and fourth distances based on preset thresholds for the first, second, third, and fourth distances, respectively, to minimize their values, thus obtaining the optimized first, second, third, and fourth distance values. Furthermore, the optimization adjustment process utilizes these optimized first, second, third, and fourth distance values ​​to adjust the pose of the segment task elements within the corresponding newly created segment task.

[0047] Specifically, since the first distance optimization value is essentially the distance between the optimized trajectory point and the absolute position point, and the second distance optimization value is essentially the distance between adjacent optimized trajectory points, and the coordinates of the absolute position point are fixed, once the first and second distance optimization values ​​are determined, the optimized trajectory can be obtained by trajectory deduction. Based on the relative positional relationship between the trajectory points and the segment task elements, the pose of these segment task elements can be adjusted according to the optimized trajectory.

[0048] In an optional specific embodiment of this application, the above-mentioned distance optimization value calculation process further includes: using the first point distance, the threshold of the first point distance, the second point distance, the threshold of the second point distance, the third point distance, the threshold of the third point distance, the fourth distance, and the threshold of the fourth distance to obtain a least squares optimization equation; and iteratively calculating a first optimization parameter, a second optimization parameter, a third optimization parameter, and a fourth optimization parameter based on the least squares optimization equation; and using the first optimization parameter, the second optimization parameter, the third optimization parameter, and the fourth optimization parameter to optimize the first point distance, the second point distance, the third point distance, and the fourth distance respectively to obtain the first point distance optimization value, the second point distance optimization value, the third point distance optimization value, and the fourth distance optimization value.

[0049] Specifically, the expression for the above least squares optimization equation is as follows:

[0050] Objective function: F(x) = ∑E i (x)

[0051] Convert to least squares form: F(x)=∑e i (x) T Te i (x), where e i (x) is the error function, and T is the information matrix (transformation matrix).

[0052] Error function: Where f(x) is the state function and z is the observed value.

[0053] In an optional embodiment of this application, the aforementioned segment task elements are data point clouds. The process of obtaining the fourth distance based on the coordinate information of segment task elements representing the same object in multiple newly created segment tasks from multiple data acquisition tasks includes: extracting point cloud clusters representing different objects from the data point clouds of each original segment task; and calculating the distance between point cloud clusters representing the same object in multiple original segment tasks based on the absolute position coordinates of the points in the point cloud clusters to obtain the fourth distance. In this embodiment, the optimization process for multiple segment tasks in this application only performs consistency optimization and further adjustments based on point data. Compared with the prior art, which requires consistency optimization and adjustments based on data such as images, this can greatly save computational load, save required memory space, and improve optimization efficiency.

[0054] In optional embodiments of this application, the point cloud clusters of the different objects mentioned above include ground point clouds, aerial point clouds, and vertical pole point clouds.

[0055] Optionally, the process of extracting point cloud clusters representing different objects from the data point cloud of each original task segment includes: first, clustering the data point cloud within a predetermined range near the trajectory point, such as within 50m; then, extracting the point cloud clusters of vertical poles based on the direction of the data points; next, extracting the point cloud clusters with all normals pointing vertically upwards at a predetermined distance downwards from the radar installation location on the vehicle using the RANSAC algorithm as the ground point cloud, for example, if the radar installation height is 2m, selecting point clouds below 1.8m; and finally, extracting the planar point cloud with essentially zero curvature within the predetermined range to obtain the aerial point cloud. Specifically, the aforementioned vertical pole point cloud represents pole-shaped objects such as streetlights passed by the data acquisition vehicle in each task segment, the aforementioned ground point cloud represents the ground surface of the road segment where each task segment is located, and the aforementioned aerial point cloud represents aerial objects such as signs passed by the data acquisition vehicle in each task segment.

[0056] In an optional specific embodiment of this application, the process of calculating the distance between point cloud clusters representing the same object in a multi-path original segment task based on the absolute position coordinates of points in the point cloud cluster includes,

[0057] Calculate the first point-plane distance from a point in the ground point cloud of one original segment task representing the same road segment to the plane containing the ground point cloud of another original segment task; calculate the second point-plane distance from a point in the aerial point cloud of one original segment task representing the same object to the plane containing the aerial point cloud of another original segment task; and calculate the point-line distance from a point in the vertical pole point cloud of one original segment task representing the same object to the line containing the vertical pole point cloud of another original segment task.

[0058] In real-world data collection scenarios, different data collection runs can result in different ground point clouds, aerial point clouds, and vertical pole point clouds acquired due to obstructions from nearby vehicles. Therefore, calculating point-to-line distances and point-to-area distances can accurately determine the true distances between point cloud clusters representing the same object obtained from two data collection runs.

[0059] Figure 4 This paper illustrates a specific embodiment of a multi-segment task consistency optimization apparatus according to the present application.

[0060] exist Figure 4 In the specific implementation shown, the multi-segment task consistency optimization device of this application includes: a coordinate acquisition module 401, used to extract the absolute position coordinates of each trajectory point in each original segment task obtained from multiple original segment tasks obtained by performing multiple acquisition tasks in a predetermined area where multiple original segment tasks can be obtained in each acquisition task, and construct the optimized trajectory point coordinates of each trajectory point; a new segment task acquisition module 402, used to obtain multiple new segment tasks based on the absolute position coordinates of adjacent trajectory points between adjacent original segment tasks in each original segment task; and a pose adjustment module 403, used to adjust the pose of segment task elements within the corresponding new segment task based on the optimized trajectory point coordinates, the absolute position coordinates of trajectory points, the adjacent optimized trajectory point coordinates of trajectory points adjacent to each trajectory point, the absolute position coordinates of adjacent trajectory points between adjacent original segment tasks within each new segment task, and the segment task elements representing the same object in the multiple original segment tasks.

[0061] The device described in this application can optimize by creating new segment tasks adjacent to the original segment tasks and matching the same elements obtained from multiple acquisition tasks, thereby avoiding lateral and elevation errors between multiple segment tasks and ensuring consistency between multiple segment tasks.

[0062] The coordinate acquisition module 401 represents a module used to extract the absolute position coordinates of each trajectory point in each original segment task obtained from multiple acquisition tasks performed on a predetermined area where multiple original segment tasks can be obtained from each acquisition task, and to construct optimized trajectory point coordinates for each trajectory point. This facilitates the adjustment and optimization of trajectory point coordinates based on absolute position coordinates, achieving the goal of consistent optimization across multiple segment tasks. Specifically, because GPS signals may be unstable, causing the actual coordinate information of the trajectory point to differ from the absolute position coordinates obtained from GPS, it is necessary to construct new trajectory points to adjust the absolute positions, so that the adjusted positions of the trajectory points are closer to their actual positions.

[0063] The new segment task acquisition module 402 represents a module used to obtain multiple new segment tasks based on the absolute position coordinates of adjacent trajectory points between adjacent original segment tasks in each original segment task. It can facilitate the optimization of two adjacent original segment tasks by performing consistency optimization within the new segment tasks that include the boundaries of two adjacent original segment tasks.

[0064] The pose adjustment module 403 represents a module used to adjust the pose of segment task elements within a newly created segment task based on the coordinates of optimized trajectory points, the absolute position coordinates of trajectory points, the coordinates of adjacent optimized trajectory points of each adjacent trajectory point, the absolute position coordinates of adjacent trajectory points between adjacent original segment tasks within each newly created segment task, and segment task elements representing the same object in multiple original segment tasks. By adjusting the pose of segment task elements obtained from multiple acquisition tasks within the newly created segment task, consistency optimization can be achieved between adjacent segment tasks of multiple original segment tasks obtained from a single acquisition task. Specifically, if the information acquired in a single acquisition task is incomplete or inaccurate due to unstable GPS signals or obstructions, information obtained from multiple acquisition tasks can be used to supplement each other, improving the accuracy of consistency optimization.

[0065] In optional specific embodiments of this application, such as Figure 5 As shown in module 503, the pose adjustment module includes a new segment task pose adjustment module and an original segment task pose adjustment submodule. The new segment task pose adjustment module performs the aforementioned process of adjusting the pose of segment task elements within the corresponding new segment task. The original segment task pose adjustment submodule adjusts the pose of segment task elements within the corresponding original segment task based on the optimized trajectory point coordinates, the absolute position coordinates of the trajectory points, the coordinates of adjacent optimized trajectory points of each trajectory point, and the segment task elements representing the same object in multiple original segment tasks. Specifically, performing further consistency optimization within the original segment task after creating or optimizing a new segment task, including those at the boundary of adjacent original segment tasks, can achieve better optimization results.

[0066] The extended multi-segment task consistency optimization apparatus provided in this application can be used to execute the extended multi-segment task consistency optimization method described in any of the above embodiments. Its implementation principle and technical effect are similar, and will not be repeated here.

[0067] In one specific embodiment of this application, each functional module in the multi-segment task consistency optimization device of this application can be directly in hardware, in a software module executed by a processor, or in a combination of both.

[0068] Software modules may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in this art. An exemplary storage medium is coupled to the processor, enabling the processor to read information from and write information to the storage medium.

[0069] 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, discrete hardware components, or any combination thereof. A general-purpose processor can be a microprocessor, but alternatively, it can be any conventional processor, controller, microcontroller, or state machine. The processor can also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors incorporating a DSP core, or any other such configuration. Alternatively, the storage medium can be integrated with the processor. The processor and storage medium can reside in an ASIC. The ASIC can reside in the user terminal. Alternatively, the processor and storage medium can reside as discrete components in the user terminal.

[0070] In another specific embodiment of this application, a computer-readable storage medium stores computer instructions that are operated to perform the extended multi-segment task consistency optimization method described above.

[0071] In another specific embodiment of this application, a computer device includes a processor and a memory, the memory storing computer instructions that are operated to execute the multi-segment task consistency optimization method in the above scheme.

[0072] Another technical solution adopted in this application is: providing a map production system, which includes multiple segment task consistency optimization devices, which are used for the multiple segment task consistency optimization method in the above solution.

[0073] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0074] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0075] The above are merely embodiments of this application and do not limit the scope of this patent application. Any equivalent structural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of this application.

Claims

1. A method for optimizing consistency across multiple task segments, characterized in that, include, The coordinate acquisition process involves extracting the absolute position coordinates of each trajectory point in each original segment task obtained from multiple original segment tasks obtained by executing multiple collection tasks in a predetermined area of ​​each collection task, and constructing the optimized trajectory point coordinates for each trajectory point. The process of obtaining new segment tasks involves obtaining multiple new segment tasks based on the absolute position coordinates of the trajectory points adjacent to each original segment task in each original segment task. In the pose adjustment process, the pose of the segment task elements within the corresponding new segment task is adjusted based on the coordinates of the optimized trajectory points, the absolute position coordinates of the trajectory points, the coordinates of the adjacent optimized trajectory points of each trajectory point, the absolute position coordinates of the trajectory points between adjacent original segment tasks within each new segment task, and the segment task elements representing the same object in the multiple original segment tasks.

2. The method for optimizing consistency of multiple segment tasks according to claim 1, characterized in that, The pose adjustment process further includes... The pose adjustment process for the original segment task involves adjusting the pose of the segment task elements within the corresponding original segment task based on the coordinates of the optimized trajectory points, the absolute position coordinates of the trajectory points, the coordinates of the adjacent optimized trajectory points of each trajectory point, and the segment task elements representing the same object in the multiple original segment tasks.

3. The method for optimizing consistency of multiple segment tasks according to claim 1, characterized in that, The pose adjustment process further includes... The distance calculation process involves calculating the first point distance based on the coordinates of each optimized trajectory point and the corresponding absolute position coordinates of the trajectory point; calculating the second point distance based on the coordinates of the optimized trajectory point and the corresponding coordinates of adjacent optimized trajectory points; calculating the third point distance based on the absolute position coordinates of adjacent trajectory points between adjacent original segment tasks within each newly created segment task; and obtaining the fourth distance based on the coordinate information of the segment task elements representing the same object in the multiple newly created segment tasks of the multiple collection tasks. The distance optimization calculation process involves adjusting the distances to the first, second, third, and fourth points based on preset thresholds for the distances to the first, second, third, and fourth points, respectively, to minimize these values. This yields optimized distance values ​​for the first, second, third, and fourth points. The optimization and adjustment process uses the first point distance optimization value, the second point distance optimization value, the third point distance optimization value, and the fourth distance optimization value to adjust the pose of the segment task elements within the corresponding newly created segment task.

4. The method for optimizing consistency of multiple segment tasks according to claim 3, characterized in that, The distance optimization value calculation process includes, Using the first point distance, the threshold of the first point distance, the second point distance, the threshold of the second point distance, the third point distance, the threshold of the third point distance, the fourth distance, and the threshold of the fourth distance, a least squares optimization equation is obtained, and a first optimization parameter, a second optimization parameter, a third optimization parameter, and a fourth optimization parameter are obtained by iterative calculation based on the least squares optimization equation; as well as, Using the first optimization parameter, the second optimization parameter, the third optimization parameter, and the fourth optimization parameter, the distances to the first point, the second point, the third point, and the fourth point are optimized respectively to obtain the optimized values ​​of the first point distance, the second point distance, the third point distance, and the fourth distance.

5. The method for optimizing consistency of multiple segment tasks according to claim 3, characterized in that, The segment task elements include data point clouds. The process of obtaining the fourth distance based on the coordinate information of the segment task elements representing the same object in the multiple newly created segment tasks of the multiple data acquisition tasks includes... From the point cloud data of each original segment task, extract point cloud clusters representing different objects respectively; The fourth distance is obtained by calculating the distance between point cloud clusters representing the same object in the multi-path original segment task based on the absolute position coordinates of the points in the point cloud cluster.

6. The method for optimizing consistency of multiple segment tasks according to claim 5, characterized in that, The point cloud clusters of different objects include ground point clouds, aerial point clouds, and vertical pole point clouds; the process of calculating the distance between point cloud clusters representing the same object in the multi-path original segment task based on the absolute position coordinates of points in the point cloud clusters includes... Calculate the distance from a point in the ground point cloud of one original segment task representing the same road segment to the first point in the plane where the ground point cloud of another original segment task is located. Calculate the second point-plane distance from a point in the aerial point cloud representing the same object in one original segment task to the plane containing the aerial point cloud in another original segment task; and Calculate the point-to-line distance from a point in the vertical pole point cloud of one original segment task representing the same object to the line containing the vertical pole point cloud of another original segment task.

7. A multi-segment task consistency optimization device, characterized in that, include, The coordinate acquisition module is used to extract the absolute position coordinates of each trajectory point in each original segment task obtained by each acquisition task from the multiple original segment tasks obtained by executing multiple acquisition tasks in a predetermined area where multiple original segment tasks can be obtained in each acquisition task, and to construct the optimized trajectory point coordinates of each trajectory point. The newly created segment task acquisition module is used to obtain multiple newly created segment tasks based on the absolute position coordinates of the trajectory points between adjacent original segment tasks in each original segment task. The pose adjustment module is used to adjust the pose of segment task elements within the corresponding new segment task based on the coordinates of the optimized trajectory points, the absolute position coordinates of the trajectory points, the coordinates of the adjacent optimized trajectory points of each trajectory point, the absolute position coordinates of the trajectory points between adjacent original segment tasks within each new segment task, and the segment task elements representing the same object in the multiple original segment tasks.

8. A map production system, comprising multiple segment task consistency optimization devices, characterized in that, The multiple segment task consistency optimization device is used to execute the multiple segment task consistency optimization method according to any one of claims 1-6.

9. A computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are operated to perform the multi-segment task consistency optimization method according to any one of claims 1-6.

10. A computer device comprising a processor and a memory storing computer instructions, wherein the processor operates the computer instructions to perform the plurality of segment task consistency optimization method according to any one of claims 1-6.

Images