Method, device and equipment for optimizing multiple driving tracks in mapping process, medium and product

Abstract

The embodiment of the invention provides a multi-driving track optimization method and device in a mapping process, equipment, a medium and a product, and the method comprises the steps: obtaining a current driving track of a vehicle in the mapping process; judging whether the current driving track is overlapped with the historical global driving track or not; if overlapping exists, replacing a historical overlapping driving track in the historical global driving track with a current overlapping driving track in the current driving track, and updating the factor graph to obtain an optimized global driving track; the current overlapped driving track is a driving track overlapped with the historical global driving track in the current driving track, and the historical overlapped driving track is a driving track overlapped with the current driving track in the historical global driving track. By utilizing the method, the factor graph is established for a plurality of driving tracks in the mapping process, that is, new values are adopted to replace original tracks for the tracks which are close to each other and are in the same lane range, so that storage resources can be saved, and the tracks can be simplified.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of map technology, and in particular to a multi-travel trajectory optimization method, device, equipment, medium and product in a mapping process. BACKGROUND

[0002] At present, intelligent driving tends to be integrated with driving. Based on mainstream intelligent parking technology, mapping and positioning cruise are usually composed of two parts. Mapping refers to establishing a parking map and a travel trajectory. Positioning cruise refers to assisting cruise based on an existing map and trajectory to facilitate automatic parking or automatic garage. Memory parking (Home zone Parking Assist, HPA) mapping is in a map module. Data output by the map is usually consistent with driving, which is lane level, i.e., the current vehicle is in a certain distance on a certain lane. The content of HPA in mapping includes parking spaces, columns, lane lines on the ground, etc. If there are multiple paths in mapping, i.e., part of the travel trajectory belongs to the same lane, multiple path trajectories of the same lane in the same parking lot will be stored, and there is no upper limit, which is easy to cause waste of storage resources. SUMMARY

[0003] Embodiments of the present application provide a multi-travel trajectory optimization method, device, equipment, medium and product in a mapping process, which realizes that a new value is used to replace an original trajectory for trajectories close to each other and in the same lane range, so as to save storage resources and simplify the trajectory.

[0004] In a first aspect, the embodiments provide a multi-travel trajectory optimization method in a mapping process, which includes:

[0005] In the mapping process, a current travel trajectory of a vehicle is acquired.

[0006] It is judged whether the current travel trajectory and a historical global travel trajectory overlap. The historical global travel trajectory is represented in the form of a factor graph. The factor graph includes each trajectory point in the historical global travel trajectory and a factor relationship of the trajectory point.

[0007] If there is overlap, a current overlapping travel trajectory in the current travel trajectory is used to replace a historical overlapping travel trajectory in the historical global travel trajectory, and the factor graph is updated to obtain an optimized global travel trajectory.

[0008] The current overlapping travel trajectory is a travel trajectory in the current travel trajectory that overlaps the historical global travel trajectory. The historical overlapping travel trajectory is a travel trajectory in the historical global travel trajectory that overlaps the current travel trajectory.

[0009] In a second aspect, the embodiments provide a multi-travel trajectory optimization device in a mapping process, which includes:

[0010] an obtaining module, configured to obtain a current driving trajectory of a vehicle in a mapping process;

[0011] a determining module, configured to determine whether the current driving trajectory overlaps with a historical global driving trajectory, the historical global driving trajectory being represented in a form of a factor graph, and the factor graph including each trajectory point in the historical global driving trajectory and a factor relationship of the trajectory point;

[0012] a first optimizing module, configured to replace a historical overlapping driving trajectory in the historical global driving trajectory with a current overlapping driving trajectory in the current driving trajectory, and update the factor graph to obtain an optimized global driving trajectory, if there is an overlap.

[0013] The current overlapping driving trajectory is a driving trajectory in the current driving trajectory that overlaps with the historical global driving trajectory, and the historical overlapping driving trajectory is a driving trajectory in the historical global driving trajectory that overlaps with the current driving trajectory.

[0014] In a third aspect, an electronic device is provided, and the electronic device comprises:

[0015] at least one processor; and

[0016] a memory connected with the at least one processor; wherein

[0017] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the mapping process multi-driving trajectory optimization method according to any one of the embodiments of the present application.

[0018] In a fourth aspect, a computer readable storage medium is provided, and the computer readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the mapping process multi-driving trajectory optimization method according to any one of the embodiments of the present application when executed by the processor.

[0019] In a fifth aspect, a computer program product is provided, and the computer program product comprises a computer program, and the computer program is used to implement the mapping process multi-driving trajectory optimization method according to any one of the embodiments of the present application when executed by a processor.

[0020] The embodiment of the application provides a kind of multi-drive trajectory optimization method, device, equipment, medium and product in mapping process, which comprises: first in mapping process, the current drive trajectory of vehicle is acquired;Then it is judged whether the current drive trajectory and historical global drive trajectory exist overlap, the historical global drive trajectory is expressed in the form of factor graph, and the factor graph includes each trajectory point in the historical global drive trajectory and the factor relationship of the trajectory point;Finally, if there is overlap, then the current overlapping drive trajectory in the current drive trajectory is used to replace the historical overlapping drive trajectory in the historical global drive trajectory, and the factor graph is updated, to obtain the global drive trajectory after optimization;The current overlapping drive trajectory is the drive trajectory in the current drive trajectory that overlaps with the historical global drive trajectory, and the historical overlapping drive trajectory is the drive trajectory in the historical global drive trajectory that overlaps with the current drive trajectory.The above technical solution, for the multiple drive trajectories in mapping process, establishes a factor graph, expresses the historical global drive trajectory in the form of factor graph, and the factor graph not only includes each trajectory point but also includes the factor relationship of each trajectory point, after generating the current drive trajectory, it is judged whether the current drive trajectory and the historical global drive trajectory exist overlap, if the two exist overlap, then for overlapping part, the current overlapping drive trajectory is used to replace the historical overlapping drive trajectory, i.e. for trajectory close and in the same lane range, new value is used to replace original trajectory, which can save storage resources and simplify trajectory.

[0021] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the application, nor is it intended to limit the scope of the application. Other features of the application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiments description. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0023] Figure 1 A flowchart of a multi-drive trajectory optimization method in mapping process provided by the first embodiment of the application;

[0024] Figure 2 An example diagram of a drive trajectory in a multi-drive trajectory optimization method in mapping process provided by the first embodiment of the application;

[0025] Figure 3 A flowchart of another multi-drive trajectory optimization method in mapping process provided by the second embodiment of the application;

[0026] Figure 4 Another example diagram of a driving track in a mapping process multi-driving track optimization method provided for the second embodiment of the present application;

[0027] Figure 5 Another example diagram of a driving track in a mapping process multi-driving track optimization method provided for the second embodiment of the present application;

[0028] Figure 6 A structural schematic diagram of a mapping process multi-driving track optimization device provided for the third embodiment of the present application;

[0029] Figure 7 A structural schematic diagram of an electronic device provided for the fourth embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to make the personnel in the technical field better understand the present application scheme, the technical scheme in the embodiments of the present application will be described clearly and completely below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by the person skilled in the art without creative labor should belong to the scope of protection of the present application.

[0031] It should be noted that the terms "first", "second" and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0032] Embodiment one

[0033] Figure 1 A flowchart of a mapping process multi-driving track optimization method provided for the first embodiment of the present application, which can be applicable to the case of optimizing multiple driving tracks in the mapping process, and the method can be executed by a mapping process multi-driving track optimization device, which can be realized in the form of hardware and / or software and generally integrated in an electronic device.

[0034] As Figure 1As shown, the multi-driving trajectory optimization method provided in this embodiment during the mapping process can specifically include the following steps.

[0035] S101, in the mapping process, the current driving trajectory of the vehicle is obtained.

[0036] It can be understood that, taking parking lot mapping as an example, the mapping content of HPA during mapping includes parking spaces, columns, lane lines on the ground, etc. To achieve complete mapping of the parking lot, the vehicle may need to travel in different directions to form multiple driving trajectories. If there are multiple driving trajectories during mapping, and part of the driving trajectories belong to the same track, it will cause multiple driving trajectories to be stored in the same lane of the same parking lot without an upper limit, which is easy to cause waste of storage resources. To solve the above problem, this embodiment provides a multi-driving trajectory optimization method during the mapping process. In the mapping process, the method provided in this embodiment is constantly executed. This step is used to obtain the driving trajectory of the vehicle at the current time during the mapping process, which is recorded as the current driving trajectory.

[0037] S102, determining whether the current driving trajectory overlaps with the historical global driving trajectory.

[0038] The historical global driving trajectory is represented in the form of a factor graph, and the factor graph includes each trajectory point in the historical global driving trajectory and the factor relationship of the trajectory point.

[0039] To solve the problem of storing multiple driving trajectories in the same lane of the same parking lot, in this embodiment, for trajectories that are close to each other and in the same lane range, the original trajectory is replaced with a new value, so that only one driving trajectory is saved in the same parking lot, thereby saving storage resources and simplifying the trajectory. Based on the above description, after obtaining the current driving trajectory of the vehicle, it is necessary to overlap the current driving trajectory with the historical trajectory. In this embodiment, the driving trajectory stored at the historical time is recorded as the historical global driving trajectory. For example, if only one driving trajectory is formed in the history, the driving trajectory formed in the history is recorded as the historical global driving trajectory. If two driving trajectories are formed in the history and part of the two driving trajectories overlap, the new driving trajectory formed in the history replaces the overlapping part of the original driving trajectory, and the non-overlapping part of the two driving trajectories is retained.

[0040] In the embodiment, the historical global driving trajectory is represented in the form of a factor graph, which contains not only the trajectory points in the historical global driving trajectory, but also the factor relationship of the trajectory points. The factor relationship of the trajectory points can include the factor relationship between a trajectory point and the next trajectory point in the same driving trajectory, and can also include the factor relationship between a trajectory point at the separation of a driving trajectory and a trajectory point at the separation of another driving trajectory. The content contained in the factor relationship is not specifically limited here, for example, it can be the position relationship between two trajectory points, or the attitude relationship between two trajectory points.

[0041] In the embodiment, the HPA can involve multiple paths in mapping the same parking lot, pass through the same scene, and although the paths are different, the lanes are consistent and can be shared after optimization. Therefore, it is necessary to determine whether the current driving trajectory overlaps with the historical global driving trajectory, that is, whether the current driving trajectory and the historical global driving trajectory have the same lane. The way to determine whether the current driving trajectory overlaps with the historical global driving trajectory can be to determine whether the distance between the trajectory points of the two trajectories is less than a set distance threshold based on the position information of the trajectory points in the current driving trajectory and the position information of the trajectory points in the historical global driving trajectory. If there is a case where the distance is less than the set distance threshold, it is determined that the current driving trajectory overlaps with the historical global driving trajectory, otherwise, it is determined that the current driving trajectory does not overlap with the historical global driving trajectory.

[0042] S103, if there is an overlap, replacing the historical overlapping driving trajectory in the historical global driving trajectory with the current overlapping driving trajectory in the current driving trajectory, and updating the factor graph to obtain an optimized global driving trajectory.

[0043] The current overlapping driving trajectory is the driving trajectory in the current driving trajectory that overlaps with the historical global driving trajectory, and the historical overlapping driving trajectory is the driving trajectory in the historical global driving trajectory that overlaps with the current driving trajectory.

[0044] For example, the trajectories of multiple mapping of the same scene are obtained, and a factor graph is established based on 2 driving trajectories. Figure 2 An example of a driving trajectory in a mapping process multi-driving trajectory optimization method provided by the embodiment of the present application is shown in FIG. 1. Figure 2 As shown in FIG. 1, the purple color represents the driving trajectory of the first mapping, the green color represents the driving trajectory of the second mapping, and the 'o' represents the trajectory point. In the blue box, the driving trajectories of the two mappings overlap, so the factor graph of the green segment will replace the corresponding purple point. The green box represents the separation of the two driving trajectories.

[0045] In the embodiment, if the current driving track and the historical global driving track have an overlapping part, the overlapping part is recorded as a current overlapping driving track and a historical overlapping driving track respectively. Since the current overlapping driving track and the historical overlapping driving track overlap, it can be considered that the current overlapping driving track and the historical overlapping driving track represent the same lane, and the current overlapping driving track is used to replace the historical overlapping driving track, that is, for the tracks close to each other and in the same lane range, the new value is used to replace the original track, so that the storage resource can be saved and the track can be simplified.

[0046] In the embodiment, the factor graph needs to be updated to obtain the optimized global driving track. Specifically, the factor relationship of each adjacent track point in the current overlapping driving track is used to replace the factor relationship of the corresponding each adjacent track point in the historical overlapping driving track in the factor graph; for each two adjacent track points in the current non-overlapping driving track in the current driving track, the factor relationship of each two adjacent track points is determined; the constraint relationship between the track points at the separation position of the current driving track and the historical overlapping driving track is determined; and each factor relationship associated with the current driving track is updated to the factor graph, so that the latest global track points and the factor relationship of each track point are included in the factor graph, and the optimized global driving track is obtained. The method provided in the embodiment is also applicable in the asynchronous state of the mapping module and the positioning module, and the path optimization is updated asynchronously.

[0047] The above technical solution is used for a plurality of driving tracks in the mapping process, a factor graph is established, the historical global driving track is represented in the form of the factor graph, the factor graph includes not only each track point but also the factor relationship of each track point, after the current driving track is generated, whether the current driving track and the historical global driving track overlap is determined, if the two overlap, the current overlapping driving track is used to replace the historical overlapping driving track, that is, for the tracks close to each other and in the same lane range, the new value is used to replace the original track, so that the storage resource can be saved and the track can be simplified.

[0048] As an optional embodiment of the embodiment, the method can be optimized on the basis of the above embodiment, and the method further includes:

[0049] If the current driving track and the historical global driving track do not overlap, the first factor relationship of each track point in the current driving track is updated to the factor graph to obtain the optimized global driving track.

[0050] In the embodiment, if the current driving trajectory and the historical global driving trajectory do not overlap, it indicates that the current driving trajectory and the global driving trajectory do not represent the same part of the lane, and the current driving trajectory needs to be added to the global driving trajectory, that is, the factor relationship of each trajectory point of the current driving trajectory is updated to the factor graph. In this case, the factor relationship of each trajectory point inside the current driving trajectory is involved, and the factor relationship of the trajectory points inside the driving trajectory is recorded as the first factor relationship, and the factor relationship of each trajectory point in the current driving trajectory is updated to the factor graph. Specifically, for each two adjacent trajectory points in the current driving trajectory, they are recorded as a first trajectory point and a second trajectory point respectively. The first position information and the first attitude information of the first trajectory point, and the second position information and the second attitude information of the second trajectory point are obtained. According to the first position information, the second position information and the first attitude information, the position relationship between the first trajectory point and the second trajectory point is determined. According to the first attitude information and the second attitude information, the attitude relationship between the first trajectory point and the second trajectory point is determined. The position relationship and the attitude relationship are taken as the first factor relationship of the first trajectory point. Each first factor relationship associated with the current driving trajectory is updated to the factor graph.

[0051] The above technical solution increases the case that the current driving trajectory and the historical global driving trajectory do not overlap, updates the first factor relationship of each trajectory point in the current driving trajectory to the factor graph, and ensures that there is only one driving trajectory in the entire mapping process by constructing the factor graph, thereby realizing trajectory optimization and saving memory resources.

[0052] As another optional embodiment of the embodiment of the application, on the basis of the above embodiment, after obtaining the optimized global driving trajectory, the following steps can be further included:

[0053] The optimized global driving trajectory is taken as a new historical global driving trajectory, and the step of obtaining the current driving trajectory of the vehicle is continued to be executed.

[0054] It can be understood that in the mapping process, multiple mapping trajectories can be generated for the same scene, and therefore, the formed driving trajectory needs to be continuously optimized. The process of driving trajectory optimization provided in the embodiment is an iterative processing process, that is, in the next iteration, after obtaining the optimized global driving trajectory, the optimized global driving trajectory is taken as a new historical global driving trajectory, and the step of obtaining the current driving trajectory of the vehicle is continued to be executed, until the mapping is completed and the formed driving trajectory is traversed, and then the optimization step of the driving trajectory is stopped.

[0055] The above technical solution increases the iterative step of the global driving trajectory, saves only one driving trajectory for the same parking lot, and can save storage resources and simplify the trajectory.

[0056] As a further optional embodiment of the embodiment of the application, on the basis of the above embodiment, when the current driving trajectory is the first driving trajectory, the step of constructing the factor graph can be optimized, and the step of constructing the factor graph comprises:

[0057] a1) for each two adjacent trajectory points in the current driving trajectory, respectively denoted as a first trajectory point and a second trajectory point.

[0058] In this embodiment, when the current driving trajectory is the first driving trajectory, since there is only one driving trajectory, only the factor relationship between each trajectory point and its adjacent trajectory point in the driving trajectory needs to be established. For each two adjacent trajectory points in the current driving trajectory, in order to facilitate distinction, they are respectively denoted as a first trajectory point and a second trajectory point.

[0059] b1) obtaining first position information and first attitude information of the first trajectory point, and second position information and second attitude information of the second trajectory point.

[0060] In this embodiment, the factor relationship includes the position relationship between the trajectory points and the attitude relationship between the trajectory points. Therefore, the position information and the attitude information of the first trajectory point need to be obtained, which are respectively denoted as the first position information and the first attitude information. The position information and the attitude information of the second trajectory point are obtained, which are respectively denoted as the second position information and the second attitude information.

[0061] c1) determining the position relationship between the first trajectory point and the second trajectory point according to the first position information, the second position information, and the first attitude information.

[0062] For example, assuming that there are N trajectory points in the first mapping, there are N elements factor in the factor graph i i = 1 … N, for the i-th trajectory point, it has a factor relationship with the i+1-th trajectory point wherein, represents the attitude relationship, represents the position relationship, the lower index i represents the factor relationship of the trajectory point i, and the upper index 1 represents the first factor relationship of the trajectory point i. There can be multiple factor relationships. At this time, the i-th trajectory point can be taken as the first trajectory point, and the i+1-th trajectory point can be taken as the second trajectory point. The position relationship between the first trajectory point and the second trajectory point is is represented as: wherein, i+1 represents the position information of the i+1-th trajectory point, i represents the position information of the i-th trajectory point, i = (x i , y i , z i ), x i , yi ,z i represent the coordinates of three coordinate axes, respectively, in meters, R i T denotes the transpose of the attitude information of the i-th trajectory point.

[0063] d1) determining an attitude relationship between the first trajectory point and the second trajectory point according to the first attitude information and the second attitude information.

[0064] Continuing the above example, R i denotes the rotation matrix of the i-th trajectory point, i.e. the attitude information, R i composed of a yaw angle yaw, a pitch angle pitch, and a roll angle roll, in radians, the angles here are from the ego vehicle to the global coordinate system:

[0065]

[0066]

[0067] R i = R yaw · R roll · R ptich .

[0068] At this time, the i-th trajectory point can be taken as the first trajectory point, and the i+1-th trajectory point can be taken as the second trajectory point, and the attitude relationship between the first trajectory point and the second trajectory point is represented as: wherein R i+1 denotes the attitude information of the i+1-th trajectory point, R i denotes the attitude information of the i-th trajectory point, R i T denotes the transpose of the attitude information of the i-th trajectory point.

[0069] e1) taking the position relationship and the attitude relationship as the first factor relationship of the first trajectory point.

[0070] Specifically, the position relationship and the attitude relationship between the first trajectory point and the second trajectory point are taken as the factor relationship of the first trajectory point, and the factor relationships of the internal trajectory points in one driving trajectory are recorded as the first factor relationship.

[0071] f1) constructing the factor graph from the first factor relationships associated with the current driving trajectory.

[0072] Specifically, the current driving trajectory is composed of a plurality of trajectory points, each trajectory point corresponds to a first factor relationship, and the first factor relationship associated with the current driving trajectory forms a factor graph. The factor graph not only contains the trajectory points of the current driving trajectory, but also contains the first factor relationship of each trajectory point.

[0073] The above technical solution specifically realizes how to construct a factor graph when the current driving trajectory is the first driving trajectory. By determining the position relationship and the attitude relationship of the connected trajectory points as the factor relationship of the trajectory points, the construction of the factor graph of the first driving trajectory is realized, which provides a basis for subsequent global driving trajectory optimization.

[0074] Embodiment two

[0075] Figure 3 Another flowchart of a multi-driving trajectory optimization method in a mapping process is provided for the second embodiment of the application. This embodiment is a further optimization of the above-mentioned embodiment. In this embodiment, the optimization of "judging whether the current driving trajectory overlaps with the historical global driving trajectory" is further limited, and the optimization of "replacing the historical overlapping driving trajectory in the historical global driving trajectory with the current overlapping driving trajectory in the current driving trajectory" is further limited, and the optimization of "updating the factor graph to obtain the optimized global driving trajectory" is further limited.

[0076] As shown in Figure 3 , the second embodiment provides a multi-driving trajectory optimization method in a mapping process, which specifically includes the following steps:

[0077] S201, in a mapping process, obtaining a current driving trajectory of a vehicle.

[0078] S202, obtaining position information of a current trajectory point in the current driving trajectory and position information of each historical trajectory point in the historical global driving trajectory.

[0079] In this embodiment, in order to judge whether the current driving trajectory overlaps with the historical global driving trajectory, the position information of the trajectory point in the current driving trajectory is needed, which is recorded as the position information of the current trajectory point. At the same time, the position information of the trajectory point in the historical global driving trajectory is also needed, which is recorded as the position information of the historical trajectory point.

[0080] S203, judging whether there is a historical trajectory point whose position information and the position information of the current trajectory point have a difference less than a set distance threshold.

[0081] In the embodiment, the distance threshold can be understood as a threshold for distinguishing whether two trajectory points belong to the same lane, and can be set as 0.5 m according to actual conditions. The distance between each historical trajectory point and the current trajectory point is calculated according to the position information of each historical trajectory point and the position information of the current trajectory point, and whether the calculated distance is less than the set distance threshold is determined.

[0082] S204, if the difference between the position information of a historical trajectory point and the position information of the current trajectory point is less than the set distance threshold, it is determined that the current driving trajectory and the historical global driving trajectory overlap.

[0083] Specifically, if the difference between the position information of a historical trajectory point and the position information of the current trajectory point is less than the set distance threshold, it indicates that the two driving trajectories are close to overlap, and it can be assumed that the same lane is driven, and it is determined that the current driving trajectory and the historical global driving trajectory overlap.

[0084] S205, if the difference between the position information of a historical trajectory point and the position information of the current trajectory point is not less than the set distance threshold, it is determined that the current driving trajectory and the historical global driving trajectory do not overlap.

[0085] Specifically, if the difference between the position information of a historical trajectory point and the position information of the current trajectory point is not less than the set distance threshold, it indicates that the two driving trajectories do not overlap, and two different lanes are driven, and it is determined that the current driving trajectory and the historical global driving trajectory do not overlap.

[0086] S206, if there is overlap, the trajectory point in the current overlapping driving trajectory is used to replace the corresponding trajectory point in the historical overlapping driving trajectory.

[0087] Specifically, if the two driving trajectories overlap, it is considered that the overlapping part belongs to the same lane, and the new value is used to replace the original trajectory, that is, the trajectory point in the current overlapping driving trajectory is used to replace the corresponding trajectory point in the historical overlapping driving trajectory.

[0088] For example, the trajectories of multiple mapping of the same scene are obtained, and a factor graph is established by taking two trajectories as an example. Figure 4 Another example of a driving trajectory in a mapping process multi-driving trajectory optimization method provided by the second embodiment of the present application is shown in FIG. 2. Figure 4As shown, yellow represents the first mapping driving trajectory, blue represents the second mapping driving trajectory, and 'o' represents the trajectory point. Assuming that the distance threshold is set to 0.5 meters, it is considered to belong to the same lane, and the latest trajectory point can be replaced. The two trajectories are close to overlap in the yellow box, and it is assumed that the same lane is driven by default, so the newly built blue trajectory can replace the red trajectory point in the same lane. The constraint relationship between the trajectory points belonging to the two trajectories in the blue box is retained, and the two trajectories form a loop, which can be globally optimized trajectory. In the blue box, the second driving trajectory combines with the first driving trajectory to form a loop, and a loop constraint is added; the final trajectory point is the point represented by 'o' in the middle.

[0089] S207, replacing the factor relationship of each corresponding trajectory point in the history overlapping driving trajectory in the factor graph with the first factor relationship of each trajectory point in the current overlapping driving trajectory.

[0090] In this embodiment, for the trajectories that overlap, the factor relationship of each trajectory point in the current overlapping driving trajectory needs to be replaced with the factor relationship of each corresponding trajectory point in the history overlapping driving trajectory in the factor graph. The factor relationship of the trajectory points inside the driving trajectory is recorded as the first factor relationship.

[0091] Continue to describe the above example, assuming that the second trajectory has M points, of which j=1…m overlap with the first driving trajectory, and the corresponding factor relationship needs to be replaced, as follows:

[0092]

[0093] Where, t j+1 represents the position information of the j+1th trajectory point, t j represents the position information of the jth trajectory point, R j+1 represents the pose information of the j+1th trajectory point, R j represents the pose information of the jth trajectory point, R j T represents the transpose of the pose information of the jth trajectory point.

[0094] S208, for each two adjacent trajectory points in the current non-overlapping driving trajectory in the current driving trajectory, determining the first factor relationship of each two adjacent trajectory points.

[0095] In the embodiment, the part of the current driving trajectory which does not overlap with the historical global driving trajectory is recorded as a current non-overlapping driving trajectory. In addition to replacing the factor relationship of the overlapping part with the corresponding original factor relationship, the factor relationship of the trajectory points in the non-overlapping part of the current driving trajectory also needs to be determined, and the factor relationship of the trajectory points inside the driving trajectory is recorded as a first factor relationship. Specifically, for each two adjacent trajectory points in the current non-overlapping driving trajectory in the current driving trajectory, the first factor relationship of each two adjacent trajectory points is determined. The calculation method can refer to the calculation method of the first factor relationship described above, which will not be described here.

[0096] S209, the trajectory points at which the current driving trajectory and the historical overlapping driving trajectory are separated are recorded as a first separated trajectory point and a second separated trajectory point respectively, and a second factor relationship between the first separated trajectory point and the second separated trajectory point is determined.

[0097] In the embodiment, the constraint relationship between the two trajectory points at which the two driving trajectories are separated is recorded as a second factor relationship. Specifically, the trajectory points at which the current driving trajectory and the historical overlapping driving trajectory are separated are recorded as a first separated trajectory point and a second separated trajectory point respectively, and the factor relationship between the first separated trajectory point and the second separated trajectory point is determined, and the constraint relationship between the two trajectories is recorded as a second factor relationship.

[0098] Continue to describe the above example, the green box indicates that the two trajectories are in a separation area, and the factor relationship between the two trajectories needs to be established. As shown in the figure, at the mth point, 2 factor relationships need to be established, one of which is the factor relationship between the mth point and the m+1th point of the second driving trajectory, that is, the first factor relationship, which can refer to the construction formula described above, which will not be described here. The other is to add the relationship between the mth point and the kth point in the first driving trajectory, which ensures that the updated trajectory does not diverge when globally optimized, and the formula is as follows, wherein the index 2 indicates the second factor relationship of the trajectory point m:

[0099]

[0100] wherein, t m represents the position information of the mth trajectory point on the second driving trajectory, and the mth trajectory point corresponds to the first separated trajectory point, t k represents the position information of the kth trajectory point on the first driving trajectory, and the kth trajectory point corresponds to the second separated trajectory point, R k represents the attitude information of the kth trajectory point, R m represents the attitude information of the jth trajectory point, R m T represents the transpose of the attitude information of the mth trajectory point.

[0101] It should be noted that the factor graph will also update and retain the factor relationship at the separation of the new trajectory and the original trajectory, which is crucial for subsequent trajectory global optimization and path recommendation during cruising.

[0102] As a specific implementation, the step of determining the second factor relationship between the first separation trajectory point and the second separation trajectory point can be optimized, comprising:

[0103] a2) obtaining first separation position information and first separation attitude information of the first separation trajectory point, and second separation position information and second separation attitude information of the second separation trajectory point.

[0104] In this embodiment, the factor relationship includes the position relationship between the trajectory points and the attitude relationship between the trajectory points. Therefore, the position information and the attitude information of the first separation trajectory point are obtained, which are denoted as the first separation position information and the first separation attitude information, respectively. The position information and the attitude information of the second separation trajectory point are obtained, which are denoted as the second separation position information and the second separation attitude information, respectively.

[0105] b2) determining the separation position relationship between the first separation trajectory point and the second separation trajectory point according to the first separation position information, the second separation position information and the first separation attitude information.

[0106] In this embodiment, the second factor relationship between the first separation trajectory point and the second separation trajectory point is represented as: wherein the index 2 represents the 2nd factor relationship of the trajectory point m, represents the attitude relationship, represents the position relationship. The separation position relationship is represented as: wherein, t m represents the position information of the mth trajectory point on the current driving trajectory, i.e. the first separation position information, t k represents the position information of the kth trajectory point on the historical global driving trajectory, i.e. the second separation position information.

[0107] c2) determining the separation attitude relationship between the first separation trajectory point and the second separation trajectory point according to the first separation attitude information and the second separation attitude information.

[0108] In this embodiment, the separation attitude relationship is represented as: wherein, R k represents the attitude information of the kth trajectory point on the historical global driving trajectory, i.e. the first separation attitude information, R m represents the attitude information of the mth trajectory point on the current driving trajectory, i.e. the second separation attitude information, R mT represents a transpose of the pose information of the mth track point.

[0109] d2) taking the separated position relationship and the separated pose relationship as a second factor relationship between the first separated track point and the second separated track point.

[0110] Specifically, the separated position relationship and the separated pose relationship are taken as a second factor relationship between the first separated track point and the second separated track point.

[0111] The above technical solution specifically implements the step of determining a second factor relationship between the first separated track point and the second separated track point.

[0112] S210, updating each first factor relationship and second factor relationship associated with the current driving track to the factor graph to obtain an optimized global driving track.

[0113] In the embodiment, each first factor relationship and second factor relationship associated with the current driving track is updated to the factor graph, and at this time, the factor graph in the factor graph includes the latest global track point and the factor relationship of each track point, which is equivalent to obtaining the optimized global driving track. During cruising, the positioning module can recommend the optimal parking path according to the current repositioning position. The factor graph data in the factor graph is that, after the above processing, the finally formed track point is L, there are L factor relationships in total, and each factor exists 1-2 factor relationships.

[0114] The above technical solution specifically implements the steps of judging whether the current driving track and the historical global driving track overlap, replacing the historical overlapping driving track in the historical global driving track with the current overlapping driving track in the current driving track, and updating the factor graph to obtain the optimized global driving track, which can meet the requirement of saving only one track graph for the same parking lot, saving one road for the repeated road section, and adding the factor relationship at the branching point between different tracks, thereby facilitating the later loop detection and global optimization. The coupling between modules is reduced, and mapping and positioning can be performed in two modules.

[0115] In order to more clearly describe the multi-driving track optimization method provided in the mapping process of the embodiment, an actual application scenario of multi-driving track optimization in a certain mapping process is taken as an example for description. The factor graph can also be used for loop detection, and the factor graph is optimized based on the loop detection. With the continuous extension of the path, there will be some cumulative errors in the mapping process. In addition to adjusting by using local optimization and global optimization, the loop detection can also be used to optimize the pose. Loop detection, also known as closed loop detection, refers to the ability of a vehicle to recognize that it has arrived at a certain scene, so that the map is closed. The position and pose parameters P of the L track points are l = (Rl ,t l ), l=1…L. Error equations are constructed, with the initial values ​​of the parameters being the received trajectory point values ​​with noise and cumulative deviation during the driving process. Observed values ​​are factor plots Error equation: Where k represents the index of the trajectory point corresponding to the factor related to trajectory point l. For example, Figure 5 This is another example diagram of the driving trajectory in the multi-driving trajectory optimization method provided in Embodiment 2 of the present invention, as shown in the figure. Figure 5 As shown, the red 'o' represents the initial value with bias and noise. The two trajectories form a loop. After updating and adding the factor graph relationship, and through global optimization, the obtained trajectory points (yellow 'o') tend to be close to the true values ​​(blue 'o'). This illustrates that the use of factor graphs not only reduces the coupling between modules and reduces memory storage, but also serves as a necessity for optimizing loops between trajectories.

[0116] Example 3

[0117] Figure 6 This is a schematic diagram of a multi-trajectory optimization device for mapping processes provided in Embodiment 3 of the present invention. This device is applicable to situations where multiple driving trajectories need to be optimized during mapping. This multi-trajectory optimization device can be implemented in hardware and / or software and is generally integrated into electronic devices. For example... Figure 6 As shown, the device includes: a trajectory acquisition module 31, an overlap judgment module 32, and a first optimization module 33, wherein,

[0118] The trajectory acquisition module 31 is used to acquire the current driving trajectory of the vehicle during the mapping process;

[0119] The overlap judgment module 32 is used to determine whether the current driving trajectory overlaps with the historical global driving trajectory. The historical global driving trajectory is represented in the form of a factor graph, which includes each trajectory point in the historical global driving trajectory and the factor relationship of the trajectory points.

[0120] The first optimization module 33 is used to replace the historical overlapping driving trajectory in the historical global driving trajectory with the current overlapping driving trajectory in the current driving trajectory if there is overlap, and update the factor graph to obtain the optimized global driving trajectory.

[0121] The current overlapping driving trajectory is the driving trajectory in the current driving trajectory that overlaps with the historical global driving trajectory, and the historical overlapping driving trajectory is the driving trajectory in the historical global driving trajectory that overlaps with the current driving trajectory.

[0122] The technical solution described above, for a plurality of driving trajectories in the mapping process, establishes a factor graph, and represents the historical global driving trajectory in the form of a factor graph. The factor graph includes not only each trajectory point but also the factor relationship of each trajectory point. After generating the current driving trajectory, a judgment is made on whether the current driving trajectory and the historical global driving trajectory overlap. If they overlap, the current overlapping driving trajectory is used to replace the historical overlapping driving trajectory, that is, for trajectories that are close to each other and within the same lane range, the original trajectory is replaced by a new value, which can save storage resources and simplify the trajectory.

[0123] Optionally, the device further comprises a cycle module, after obtaining the optimized global driving trajectory, for:

[0124] returning to continue executing the step of obtaining the current driving trajectory of the vehicle, with the optimized global driving trajectory as a new historical global driving trajectory.

[0125] Optionally, the overlap judgment module 32 is specifically configured to:

[0126] obtain the position information of the current trajectory point in the current driving trajectory and the position information of each historical trajectory point in the historical global driving trajectory;

[0127] determine whether the position information of a historical trajectory point and the position information of the current trajectory point differ by less than a set distance threshold;

[0128] if so, determine that the current driving trajectory and the historical global driving trajectory overlap;

[0129] if not, determine that the current driving trajectory and the historical global driving trajectory do not overlap.

[0130] Optionally, the device further comprises a construction module, and when the current driving trajectory is the first driving trajectory, the construction module is specifically configured to:

[0131] for each two adjacent trajectory points in the current driving trajectory, denoted as a first trajectory point and a second trajectory point;

[0132] obtain first position information and first attitude information of the first trajectory point, and second position information and second attitude information of the second trajectory point;

[0133] determine a position relationship between the first trajectory point and the second trajectory point according to the first position information, the second position information, and the first attitude information;

[0134] determine an attitude relationship between the first trajectory point and the second trajectory point according to the first attitude information and the second attitude information;

[0135] the position relationship and the pose relationship as first factor relationships of the first trajectory point;

[0136] the first factor relationships associated with the current driving trajectory form a factor graph.

[0137] Optionally, the first optimization module 33 comprises a replacing unit and an updating unit, the replacing unit is specifically used for:

[0138] replacing the corresponding trajectory point in the historical overlapping driving trajectory with the trajectory point in the current overlapping driving trajectory.

[0139] Optionally, the updating unit is used for:

[0140] replacing the factor relationship of the corresponding trajectory point in the historical overlapping driving trajectory in the factor graph with the first factor relationship of each trajectory point in the current overlapping driving trajectory;

[0141] determining, for each two adjacent trajectory points in the current non-overlapping driving trajectory in the current driving trajectory, a first factor relationship of the each two adjacent trajectory points;

[0142] taking the trajectory points at which the current driving trajectory and the historical overlapping driving trajectory are separated as a first separated trajectory point and a second separated trajectory point respectively, and determining a second factor relationship between the first separated trajectory point and the second separated trajectory point;

[0143] updating each of the first factor relationship and the second factor relationship associated with the current driving trajectory to the factor graph to obtain an optimized global driving trajectory.

[0144] Optionally, the updating unit is used for performing the step of determining the second factor relationship between the first separated trajectory point and the second separated trajectory point, and comprises:

[0145] obtaining first separated position information and first separated pose information of the first separated trajectory point, and second separated position information and second separated pose information of the second separated trajectory point;

[0146] determining a separated position relationship between the first separated trajectory point and the second separated trajectory point according to the first separated position information, the second separated position information and the first separated pose information;

[0147] determining a separated pose relationship between the first separated trajectory point and the second separated trajectory point according to the first separated pose information and the second separated pose information;

[0148] The separation position relationship and the separation posture relationship are taken as a second factor relationship between the first separation trajectory point and the second separation trajectory point.

[0149] Optionally, the apparatus further comprises a second updating module configured to:

[0150] If the current trajectory and the historical global trajectory do not overlap, the first factor relationship of each trajectory point in the current trajectory is updated to the factor graph to obtain an optimized global trajectory.

[0151] The mapping process multi-trajectory optimization apparatus provided by the embodiment of the application can execute the mapping process multi-trajectory optimization method provided by any embodiment of the application, has the function modules and beneficial effects corresponding to the execution method.

[0152] Embodiment four

[0153] Figure 7 A structural schematic diagram of an electronic device is provided for embodiment four of the application. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices (such as headsets, glasses, watches, etc.), and other similar computing devices. The components shown here, their connections, and their functions, as well as their implementation, are merely examples and are not intended to limit the implementations described and / or claimed herein.

[0154] As shown in Figure 7 The electronic device 40 includes at least one processor 41, and a memory, such as a read-only memory (ROM) 42, a random access memory (RAM) 43, etc., which is communicatively connected to the at least one processor 41, wherein the memory stores a computer program executable by the at least one processor, and the processor 41 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 42 or loaded from the storage unit 48 into the random access memory (RAM) 43. In the RAM 43, various programs and data required for the operation of the electronic device 40 can also be stored. The processor 41, the ROM 42, and the RAM 43 are connected to each other through a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0155] A plurality of components in the electronic device 40 are connected to the I / O interface 45, including: an input unit 46, such as a keyboard, a mouse, etc.; an output unit 47, such as various types of displays, speakers, etc.; a storage unit 48, such as a magnetic disk, an optical disk, etc.; and a communication unit 49, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 49 allows the electronic device 40 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0156] The processor 41 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 41 performs various methods and processes described above, such as the multi-drive trajectory optimization method in mapping.

[0157] In some embodiments, the multi-drive trajectory optimization method in mapping can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 48. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 40 via the ROM 42 and / or the communication unit 49. When the computer program is loaded onto the RAM 43 and executed by the processor 41, one or more steps of the multi-drive trajectory optimization method in mapping described above can be performed. Alternatively, in other embodiments, the processor 41 can be configured to perform the multi-drive trajectory optimization method in mapping by any other appropriate means, such as by means of firmware.

[0158] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0159] Computer programs for implementing the methods of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer program, when executed, can cause instructions defined in the flow charts and / or block diagrams to be implemented. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, and partially on a remote machine or entirely on a remote machine or server.

[0160] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0161] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0162] The systems and techniques described here can be implemented in a computing system that includes a back end component, e.g., as a data server, or that includes a middleware component, e.g., an application server, or that includes a front end component, e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here, or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication, e.g., a communication network. Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0163] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0164] The embodiment of the present application further provides a computer program product comprising a computer program which, when executed by a processor, implements the multi-travel trajectory optimization method in the mapping process as provided by any embodiment of the present application.

[0165] The computer program product, in the implementation process, can be written in one or more programming languages or combinations thereof to implement computer program codes for performing the operations of the present disclosure, including but not limited to object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" language or similar programming languages. The program code can be executed entirely on a user computer, partially on a user computer, as an independent software package, partially on a user computer and partially on a remote computer, or entirely on a remote computer or server. In the case involving a remote computer, the remote computer can be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, through the Internet by using an Internet service provider).

[0166] It should be understood that the various forms of flow shown above can be used to reorder, add, or remove steps. For example, the steps recited in the present application can be performed in parallel, in series, or in a different order, as long as the desired results of the technical solutions of the present application can be achieved, which are not limited herein.

[0167] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for optimizing multiple driving trajectories during mapping, characterized in that, include: During the mapping process, the current driving trajectory of the vehicle is obtained; Determine whether the current driving trajectory overlaps with the historical global driving trajectory. The historical global driving trajectory is represented in the form of a factor graph, which includes each trajectory point in the historical global driving trajectory and the factor relationships between the trajectory points. If there is overlap, the current overlapping driving trajectory in the current driving trajectory is used to replace the historical overlapping driving trajectory in the historical global driving trajectory, and the factor graph is updated to obtain the optimized global driving trajectory; The current overlapping driving trajectory is the driving trajectory in the current driving trajectory that overlaps with the historical global driving trajectory, and the historical overlapping driving trajectory is the driving trajectory in the historical global driving trajectory that overlaps with the current driving trajectory.

2. The method according to claim 1, characterized in that, After obtaining the optimized global driving trajectory, it also includes: The optimized global driving trajectory is used as the new historical global driving trajectory, and the process returns to continue executing the step of obtaining the vehicle's current driving trajectory.

3. The method according to claim 1, characterized in that, The step of determining whether the current driving trajectory overlaps with the historical global driving trajectory includes: Obtain the position information of the current trajectory point in the current driving trajectory, and the position information of each historical trajectory point in the historical global driving trajectory; Determine whether there exists a historical trajectory point whose location information differs from the current trajectory point's location information by a less than a set distance threshold; If so, it is determined that the current driving trajectory overlaps with the historical global driving trajectory; If not, it is determined that the current driving trajectory does not overlap with the historical global driving trajectory.

4. The method according to claim 1, characterized in that, When the current driving trajectory is the first driving trajectory, the steps for constructing the factor graph include: For each pair of adjacent trajectory points in the current driving trajectory, they are respectively denoted as the first trajectory point and the second trajectory point; Obtain the first position information and first attitude information of the first trajectory point, and the second position information and second attitude information of the second trajectory point; Based on the first position information, the second position information, and the first attitude information, determine the positional relationship between the first trajectory point and the second trajectory point; Based on the first attitude information and the second attitude information, determine the attitude relationship between the first trajectory point and the second trajectory point; The positional relationship and the attitude relationship are used as the first factor relationship of the first trajectory point; The factor graph is constructed by associating the first factor relationships with the current driving trajectory.

5. The method according to claim 1, characterized in that, The step of replacing the historical overlapping driving trajectory in the historical global driving trajectory with the current overlapping driving trajectory in the current driving trajectory includes: Replace the corresponding trajectory points in the historical overlapping driving trajectory with the trajectory points in the current overlapping driving trajectory.

6. The method according to claim 1, characterized in that, Updating the factor graph to obtain the optimized global driving trajectory includes: The factor relationships of corresponding trajectory points in the historical overlapping driving trajectories in the factor graph are replaced with the first factor relationships of each trajectory point in the current overlapping driving trajectory. For every two adjacent trajectory points in the current non-overlapping trajectory of the current driving trajectory, determine the first factor relationship between the two adjacent trajectory points; The trajectory points where the current driving trajectory separates from the historical overlapping driving trajectory are respectively recorded as the first separated trajectory point and the second separated trajectory point, and a second factor relationship between the first separated trajectory point and the second separated trajectory point is determined; The first factor relationship and the second factor relationship associated with the current driving trajectory are updated in the factor graph to obtain the optimized global driving trajectory.

7. The method according to claim 6, characterized in that, Determining the second factor relationship between the first separation trajectory point and the second separation trajectory point includes: Obtain the first separation position information and the first separation attitude information of the first separation trajectory point, and the second separation position information and the second separation attitude information of the second separation trajectory point; Based on the first separation position information, the second separation position information, and the first separation attitude information, the separation position relationship between the first separation trajectory point and the second separation trajectory point is determined; Based on the first separation attitude information and the second separation attitude information, the separation attitude relationship between the first separation trajectory point and the second separation trajectory point is determined; The separation position relationship and the separation attitude relationship are used as the second factor relationship between the first separation trajectory point and the second separation trajectory point.

8. The method according to claim 1, characterized in that, Also includes: If the current driving trajectory does not overlap with the historical global driving trajectory, the first factor relationship of each trajectory point in the current driving trajectory is updated to the factor graph to obtain the optimized global driving trajectory.

9. A multi-trajectory optimization device for mapping process, characterized in that, include: The trajectory acquisition module is used to acquire the current driving trajectory of the vehicle during the mapping process; The overlap determination module is used to determine whether the current driving trajectory overlaps with the historical global driving trajectory. The historical global driving trajectory is represented in the form of a factor graph, which includes each trajectory point in the historical global driving trajectory and the factor relationship of the trajectory points. The first optimization module is used to replace the historical overlapping driving trajectory in the historical global driving trajectory with the current overlapping driving trajectory in the current driving trajectory if there is overlap, and update the factor graph to obtain the optimized global driving trajectory. The current overlapping driving trajectory is the driving trajectory in the current driving trajectory that overlaps with the historical global driving trajectory, and the historical overlapping driving trajectory is the driving trajectory in the historical global driving trajectory that overlaps with the current driving trajectory.

10. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the multi-trajectory optimization method in the mapping process as described in any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the multi-trajectory optimization method for mapping as described in any one of claims 1-8.

12. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the multi-trajectory optimization method in the mapping process as described in any one of claims 1-8.

Images