Method, apparatus, electronic device, and storage medium for determining vehicle trajectory

Abstract

This disclosure relates to a method, apparatus, electronic device, and storage medium for determining a vehicle's trajectory. The method includes the steps of: (S1) determining a plurality of historical entry trajectory points for the entry section of a target road section and a plurality of historical exit trajectory points for the exit section of a target road section based on historical trajectory information of at least one vehicle in a target road section; (S2) determining the intersection of the entry section of the target road section based on the plurality of historical entry trajectory points and determining the intersection of the exit section of the target road section based on the plurality of historical exit trajectory points; and (S3) determining a recommended trajectory for the target road section based on the entry section intersection and the exit section intersection. This allows for the rational planning of a recommended trajectory for a target road section, reducing the probability that a vehicle will be unable to enter the planned route, and ensuring the stability and speed of vehicle operation.

Description

Technical Field

[0001] (Cross - reference to related applications) This disclosure claims the priority of a Chinese patent application with the application number CN202310445870.9 and the invention title "Method, apparatus, electronic device, and storage medium for determining a vehicle driving trajectory", which was filed with the China National Intellectual Property Administration on April 23, 2023, and all of its contents are incorporated herein by reference.

[0002] This disclosure relates to the field of autonomous driving technology, and more specifically, to a method, apparatus, electronic device, and storage medium for determining a vehicle driving trajectory.

Background Art

[0003] Currently, a vehicle controls its travel along the center line of the lane in its planned route in a driving assistance mode or an autonomous driving mode. When the vehicle needs to turn or enter a ramp, if the vehicle travels completely along the center line of the lane, there is a possibility that the vehicle cannot turn or enter a reasonable position on the ramp.

[0004] How to reasonably determine the vehicle driving trajectory is an urgent problem to be solved.

Summary of the Invention

Problems to be Solved by the Invention

[0005] Embodiments of this disclosure provide a method, apparatus, electronic device, and storage medium for determining a vehicle driving trajectory to solve the above technical problems. It can not only reasonably plan a route and reduce the probability that a vehicle cannot enter the planned route, but also ensure the stability and speed of vehicle driving.

Means for Solving the Problems

[0006] The method for determining a vehicle driving trajectory according to the first aspect of the embodiments of this disclosure is The steps include determining a plurality of historical entry trajectory points for the entry section of the target road section and determining a plurality of historical exit trajectory points for the exit section of the target road section based on historical trajectory information of at least one vehicle in the target road section, The steps include determining the intersection of the entry cross section of the target road section based on the plurality of historical entry trajectory points, and determining the intersection of the exit cross section of the target road section based on the plurality of historical exit trajectory points, The process includes the step of determining a recommended driving trajectory for the target road section based on the aforementioned entry cross-section intersection and the aforementioned exit cross-section intersection.

[0007] A second embodiment of the embodiments of this disclosure is an apparatus for determining a vehicle's trajectory. An entry / exit trajectory point determination module for determining multiple historical entry trajectory points of the entry section of the target road section and extracting multiple historical exit trajectory points of the exit section of the target road section, based on historical driving trajectory information of at least one vehicle in the target road section, A cross-section intersection determination module for determining the entry cross-section intersection of the target road section based on the plurality of historical entry trajectory points and for determining the exit cross-section intersection of the target road section based on the plurality of historical exit trajectory points, The system includes a recommended driving trajectory determination module for determining a recommended driving trajectory for the target road section based on the aforementioned entry cross-section intersection and the aforementioned exit cross-section intersection.

[0008] A computer-readable storage medium according to a third embodiment of the embodiments of this disclosure stores a computer program for performing the method for determining the vehicle trajectory described in the first embodiment.

[0009] The electronic device relating to the fourth embodiment of the embodiments of this disclosure is A processor and a memory for storing instructions that the processor can execute, The processor reads and executes the executable instructions from the memory to realize a method for determining the vehicle trajectory described in any one of the embodiments.

[0010] A fifth embodiment of the embodiments of the present disclosure provides a computer program product in which, when instructions in the computer program product are executed by a processor, a method for determining a vehicle trajectory as described in any one of the above embodiments of the present disclosure is performed. [Effects of the Invention]

[0011] According to the method, apparatus, electronic device, and storage medium for determining a vehicle's trajectory in the embodiments of this disclosure, before planning the trajectory, it is possible to obtain historical trajectory information uploaded to a designated server after the vehicle or another vehicle has passed through a target road section. Multiple historical entry trajectory points for the entry section and multiple historical exit trajectory points for the exit section of the target road section can be extracted from the historical trajectory information. Based on the multiple historical entry trajectory points, the entry section intersection of the target road section can be rationally determined. Based on the multiple historical exit trajectory points, the exit section intersection of the target road section can be rationally determined. Furthermore, based on the entry and exit section intersections of the target road section, a recommended trajectory passing through the entry and exit section intersections can be rationally planned. This not only reduces the probability that the vehicle will be unable to enter the planned route, but also guarantees the stability and speed of vehicle operation. [Brief explanation of the drawing]

[0012] [Figure 1] This is a flowchart of a method for determining a vehicle's trajectory in one embodiment of the present disclosure. [Figure 2] This is a schematic diagram showing how to determine the recommended driving trajectory for a target road section using an entry cross-section intersection and an exit cross-section intersection in one example of the present disclosure. [Figure 3] This is a flowchart of step S2 in one embodiment of the present disclosure. [Figure 4] This is a flowchart of step S3 in one embodiment of the present disclosure. [Figure 5] This is a flowchart following step S3 in one embodiment of the present disclosure. [Figure 6]It is a flowchart of step S7 in one embodiment of the present disclosure. [Figure 7] It is a flowchart of step S5 in one embodiment of the present disclosure. [Figure 8] It is a partial flowchart of a method for determining a vehicle driving trajectory in one embodiment of the present disclosure. [Figure 9] It is a flowchart of step S10 in one embodiment of the present disclosure. [Figure 10] It is a structural block diagram of a device for determining a vehicle driving trajectory in one embodiment of the present disclosure. [Figure 11] It is a structural block diagram of a cross-section intersection determination module 200 in one embodiment of the present disclosure. [Figure 12] It is a structural block diagram of a recommended driving trajectory determination module 300 in one embodiment of the present disclosure. [Figure 13] It is a structural block diagram of a device for determining a vehicle driving trajectory in another embodiment of the present disclosure. [Figure 14] It is a structural block diagram of a recommended vehicle speed determination module 700 in one embodiment of the present disclosure. [Figure 15] It is a structural block diagram of a reference driving trajectory determination module 500 in one embodiment of the present disclosure. [Figure 16] It is a structural block diagram of a recommended vehicle speed determination module 700 in another embodiment of the present disclosure. [Figure 17] It is a structural block diagram of an electronic device in one embodiment of the present disclosure.

Embodiments for Carrying out the Invention

[0013] Hereinafter, in order to interpret the present disclosure, exemplary embodiments of the present disclosure will be described in detail with reference to the drawings. The described embodiments are only some embodiments of the present disclosure, not all embodiments, and the present disclosure is not limited to the exemplary embodiments.

[0014] The relative arrangement of components and steps, numerical expressions, and numerical values ​​described in these embodiments do not limit the scope of this disclosure unless specifically described otherwise.

[0015] (Summary of the application) In driver assistance mode or autonomous driving mode, the vehicle controls its movement along the center line of the lane on the planned route. If the vehicle needs to turn or enter a ramp, and it is traveling perfectly along the center line of the lane, it may not be able to turn or enter the ramp at a reasonable position.

[0016] The inventors of this disclosure argue that, when a large amount of creative labor necessitates entering a ramp along a planned route, prematurely entering the lane closest to the ramp may reduce the vehicle's stability and speed due to the premature lane change. Furthermore, entering the ramp too close to the entrance may prevent the vehicle from smoothly entering the target lane due to a high volume of vehicles at the entrance. How to rationally plan routes is an urgent issue that needs to be addressed.

[0017] (Example method) Figure 1 is a flowchart of a method for determining a vehicle trajectory in one embodiment of the present disclosure. This embodiment can be applied to electronic devices and includes the following steps S1 to S3, as shown in Figure 1.

[0018] In step S1, based on the historical driving trajectory information of at least one vehicle in the target road section, multiple historical entry trajectory points are determined at the entry section of the target road section, and multiple historical exit trajectory points are determined at the exit section of the target road section.

[0019] In several selectable embodiments, the target road section may include a road section with ramp entrances and exits, a road section with lane change scenes, a road section with curve scenes, a normal road section, and other types of road sections. Of these, ramp entrances and exits may include ramp entrances and / or ramp exits. Lane change scenes may include lane increase scenes and lane decrease scenes. Normal road sections may include single-lane straight road sections and multi-lane straight road sections.

[0020] In several selectable embodiments, during the process of the vehicle or another vehicle passing through a target road section once, the vehicle's own positioning device or a positioning device located inside the vehicle (e.g., a positioning device for an in-vehicle mobile terminal) intermittently collects its own position information to obtain multiple positional information points for the vehicle in the target road section, and based on the multiple positional information points, a single historical driving trajectory information for the vehicle's journey through the target road section can be generated.

[0021] In several selectable embodiments, before planning the driving trajectory, historical driving trajectory information of the vehicle or another vehicle traveling along the target road section can be obtained from a designated server. After passing through the target road section, the vehicle or another vehicle can upload its own historical driving trajectory information to the designated server. The designated server may include a Vehicle Internet of Vehicles (IoV) server and a navigation software server, among others.

[0022] In several selectable embodiments, during the process of each vehicle passing through a target road section once, the vehicle's own positioning device or a positioning device located inside the vehicle (e.g., a positioning device for an in-vehicle mobile terminal) intermittently collects its own position information to obtain multiple positional information points for the vehicle in the target road section, and based on the multiple positional information points, one historical driving trajectory information for the vehicle's journey through the target road section is generated.

[0023] In several selectable embodiments, obtaining one historical trajectory from a specified server allows for the extraction of one or more trajectory point locations close to the approach cross-section of a target road section. For example, if it can be determined based on this historical trajectory information that a trajectory point exists that is precisely located at the approach cross-section of a target road section, this trajectory point can be determined as the historical approach trajectory point of this historical trajectory information. If it can be determined based on this historical trajectory information that none of any trajectory points are located at the approach cross-section of a target road section, then multiple trajectory point locations close to the approach cross-section of a target road section can be extracted. Based on these multiple trajectory point locations, a corresponding approach trajectory curve can be generated for this historical trajectory information, and the intersection between the approach trajectory curve and the approach cross-section of a target road section can be determined as the historical approach trajectory point of this historical trajectory information.

[0024] In several selectable embodiments, the history exit trajectory point of any history travel trajectory can be determined by employing a method similar to or identical to the method used to determine the history entry trajectory point of any history travel trajectory.

[0025] In one possible example, step S1 can be performed by the processor calling a corresponding instruction stored in memory, or it can be performed by an entry / exit trajectory point determination module operating within the processor.

[0026] In step S2, the entry cross-section intersection of the target road section is determined based on multiple historical entry trajectory points, and the exit cross-section intersection of the target road section is determined based on multiple historical exit trajectory points.

[0027] In several selectable embodiments, clustering can be performed on multiple historical entry trajectory points, and the entry cross-section intersection of the target road section is determined based on the results of the clustering. Alternatively, multiple historical entry trajectory points can be determined as multiple entry cross-section intersections of the target road section.

[0028] By performing clustering on multiple historical exit trajectory points, the exit cross-section intersection of the target road section can be determined based on the results of the clustering process. Furthermore, multiple historical exit trajectory points can also be used to determine multiple entry cross-section intersections of the target road section.

[0029] In one possible example, step S2 can be performed by the processor calling a corresponding instruction stored in memory, or it can be performed by a cross-section intersection determination module operating within the processor.

[0030] In step S3, the recommended driving trajectory for the target road section is determined based on the entry and exit cross-section intersections.

[0031] In several selectable embodiments, if there is only one entry cross-section intersection and one exit cross-section intersection, it is possible to obtain first historical driving trajectory information from the historical driving trajectory information that passes through both the input cross-section intersection and the exit cross-section intersection. It is also possible to obtain second historical driving trajectory information from the historical driving trajectory information that passes through both the input cross-section intersection and the exit cross-section while being within a preset distance range from the exit cross-section intersection. Furthermore, it is possible to obtain third historical driving trajectory information from the historical driving trajectory information that passes through both the entry cross-section intersection and the exit cross-section while being within a preset distance range from the exit cross-section intersection. Based on the trajectory point position of any one of the first, second, and third historical driving trajectory information, it is possible to generate one recommended driving trajectory that passes through both the entry cross-section intersection and the exit cross-section intersection, has a smooth curve, and whose curvature is less than a preset curvature threshold.

[0032] In several selectable embodiments, if there are multiple entry and / or exit intersections, it is possible to generate multiple recommended driving trajectories that pass through different entry and exit intersections, have smooth curves, and have curvature lower than a preset curvature threshold.

[0033] Figure 2 is a schematic diagram showing how to determine a recommended driving trajectory for a target road section based on the entry and exit intersections in one example of the present disclosure. As shown in Figure 2, the entry section of the target road section is S, and the exit section is E. The entry section has entry intersections S1, S2, S3, S4, S5, and S6. The exit section has exit intersections E1, E2, E3, E4, and E5. The recommended driving trajectory for the target road section may include the recommended driving trajectory from the entry intersection S1 to the exit intersection E1, the recommended driving trajectory from the entry intersection S2 to the exit intersection E2, the recommended driving trajectory from the entry intersection S3 to the exit intersection E3, the recommended driving trajectory from the entry intersection S4 to the exit intersection E4, the recommended driving trajectory from the entry intersection S5 to the exit intersection E5, and the recommended driving trajectory from the entry intersection S6 to the exit intersection E5.

[0034] In one possible example, step S3 can be performed by the processor calling a corresponding instruction stored in memory, or it can be performed by a recommended driving trajectory determination module operating within the processor.

[0035] In this embodiment, before planning the driving trajectory, it is possible to obtain historical driving trajectory information uploaded to a designated server after the vehicle or another vehicle has passed through the target road section. Multiple historical entry trajectory points for the entry section and multiple historical exit trajectory points for the exit section of the target road section are extracted from the historical driving trajectory information. Based on the multiple historical entry trajectory points, the entry section intersection of the target road section can be rationally determined. Based on the multiple historical exit trajectory points, the exit section intersection of the target road section can be rationally determined. Furthermore, based on the entry section intersection and the exit section intersection of the target road section, a recommended driving trajectory passing through the entry section intersection and the exit section intersection can be rationally planned. This not only reduces the probability that the vehicle will not be able to enter the planned route, but also guarantees the stability and speed of vehicle operation.

[0036] Figure 3 is a flowchart of step S2 in one embodiment of the present disclosure. As shown in Figure 3, step S2 may include the following steps S2-1 to S2-2.

[0037] In step S2-1, the first clustering is performed on multiple historical entry trajectory points to determine the entry cross-section intersection.

[0038] In several selectable embodiments, a first clustering operation can be performed on multiple historical trajectory points based on a set clustering distance, and the entry cross-section intersection can be determined based on the results of the first clustering operation. Here, clustering can be performed on the historical entry trajectory points of each lane in the target road section to obtain the entry cross-section intersection for each lane. There may be one entry cross-section intersection for each lane, or there may be multiple.

[0039] If the target road section is a one-way, single-lane road section, the entry crossing intersection may include only one intersection (e.g., the center point) in the entry crossing of the one-way, single-lane road section. Alternatively, the entry crossing intersection may include multiple intersections in the entry crossing of this one-way, single-lane road section. For example, if the entry crossing of the target road section is a T-junction, the entry crossing intersection may include the intersection (usually the center point) where a vehicle passes through the T-junction in a straight line, and the intersection (usually a non-center point) where a vehicle passes through the T-junction in a curve.

[0040] If the target road section is a one-way multi-lane road section, one entry cross-section intersection can be determined for the outermost lane, and this entry cross-section intersection may be, for example, the center point of the entry cross-section of the outermost lane. Alternatively, two entry cross-section intersections can be determined for the outermost lane, and these two entry cross-section intersections may include, for example, the center point of the entry cross-section of the outermost lane and an entry cross-section intersection determined by changing lanes from an adjacent lane to the outermost lane. For intermediate lanes that are not the outermost lanes, three entry cross-section intersections can be determined, and these three entry cross-section intersections may include, for example, the center point of the entry cross-section of an intermediate lane and an entry cross-section intersection determined by changing lanes to the left or to the right, respectively.

[0041] Furthermore, the number of entry cross-section intersections can be further reduced by performing a selection process based on the results of the first clustering. For example, after the first clustering, a quantitative threshold can be set for the historical travel trajectory points that generate clustering points, and clustering points smaller than the quantitative threshold can be selected and removed. The clustering points that have been retained through this selection process can then be designated as entry cross-section intersections.

[0042] In one possible example, step S2-1 can be performed by the processor calling a corresponding instruction stored in memory, or it can be performed by a first clustering unit operating within the processor.

[0043] In step S2-2, a second clustering operation is performed on multiple historical exit trajectory points to determine the exit cross-section intersection.

[0044] In several selectable embodiments, a second clustering operation can be performed on multiple historical exit trajectory points using a method similar to or identical to the first clustering operation to determine the exit cross-section intersection of the target road section.

[0045] Furthermore, the embodiments of this disclosure are not limited to the order in which the first and second clustering operations are performed. The first clustering may be performed first, followed by the second clustering (i.e., step S2-1 may be performed first, followed by step S2-2), or the second clustering may be performed first, followed by the first clustering (i.e., step S2-2 may be performed first, followed by step S2-1), or the first and second clustering may be performed simultaneously (i.e., step S2-1 and step S2-2 may be performed simultaneously).

[0046] In one possible example, step S2-2 can be performed by the processor calling a corresponding instruction stored in memory, or it can be performed by a second clustering unit operating within the processor.

[0047] In this embodiment, the entry cross-section intersection is determined by performing a first clustering operation on multiple historical entry trajectory points, and the exit cross-section intersection is determined by performing a second clustering operation on multiple historical exit trajectory points. This significantly reduces the number of planning start and end points when planning the trajectory, improving the efficiency of generating recommended driving trajectories. Furthermore, it helps the vehicle to travel along the recommended driving trajectory during autonomous driving, reducing the probability that the vehicle will not be able to enter the planned route, and ensuring the stability and speed of vehicle operation.

[0048] Figure 4 is a flowchart of step S3 in one embodiment of the present disclosure. As shown in Figure 4, step S3 may include the following steps S3-1 to S3-3.

[0049] In step S3-1, the relevant historical driving trajectories associated with the entry cross-section intersection and the exit cross-section intersection are determined from the historical driving trajectory information.

[0050] In several selectable embodiments, the interval between the entry cross-section intersection and the history entry trajectory point corresponding to each history travel trajectory can be compared with a preset interval threshold, and history travel trajectories with an interval smaller than the preset interval threshold can be determined as a first associated history travel trajectory set associated with the entry cross-section intersection.

[0051] In several selectable embodiments, the interval between the exit cross-section intersection and the history exit trajectory point corresponding to each history travel trajectory can be compared with a preset interval threshold, and history travel trajectories with an interval smaller than the preset interval threshold can be determined as a second set of associated history travel trajectories associated with the exit cross-section intersection.

[0052] In some embodiments, the same historical related driving trajectory in the first related historical driving trajectory set and the second related historical driving trajectory set can be determined as the related historical driving trajectory. Here, the interval between the historical entry trajectory point and the entry cross-section intersection of the related historical driving trajectory is smaller than a preset interval threshold, and the interval between the historical exit trajectory point and the exit cross-section intersection is smaller than a preset interval threshold, meaning that the related historical driving trajectory and the recommended driving trajectory are close in position to each other in terms of entry points and exit points in the target road section.

[0053] In one selectable example, step S3-1 can be performed by the processor calling a corresponding instruction stored in memory, or it can be performed by an associated history trajectory determination unit operating within the processor.

[0054] In step S3-2, trajectory point interpolation clustering is performed on the related historical trajectories to determine at least one interpolated trajectory point.

[0055] In several selectable embodiments, trajectory point interpolation is performed on the trajectory-related history travel trajectory based on the positions of multiple trajectory points of the related history travel trajectory to increase the number of trajectory points of the related history travel trajectory. The interpolated trajectory points can be clustered to obtain the most trajectory point between the vehicle's entry and exit cross-section intersections, i.e., at least one interpolated trajectory point.

[0056] In one possible example, step S3-2 can be performed by the processor calling a corresponding instruction stored in memory, or it can be performed by a trajectory point interpolation clustering unit operating within the processor.

[0057] In step S3-3, a recommended driving trajectory is determined based on the entry cross-section intersection, the trajectory points in the related historical driving trajectory, at least one interpolated trajectory point, and the exit cross-section intersection.

[0058] When planning a recommended driving trajectory, it is possible to plan at least one recommended driving trajectory that starts at the entry cross-section intersection, ends at the exit cross-section intersection, and passes through the entry cross-section intersection, a trajectory point in the related historical driving trajectory, at least one interpolated trajectory point, and the exit cross-section intersection.

[0059] In one selectable example, step S3-3 can be performed by the processor calling a corresponding instruction stored in memory, or it can be performed by a recommended trajectory determination unit operating within the processor.

[0060] In this embodiment, related historical driving trajectories associated with the entry and exit cross-section intersections are determined from the historical driving trajectory information, and at least one interpolated trajectory point is obtained by performing trajectory point interpolation clustering on the related historical driving trajectories. This allows for the rational planning of at least one recommended driving trajectory that starts at the entry cross-section intersection, ends at the exit cross-section intersection, and passes through the entry cross-section intersection, the trajectory points in the related historical driving trajectories, at least one interpolated trajectory point, and the exit cross-section intersection. This helps the vehicle to travel along the recommended driving trajectory during autonomous driving, reducing the probability that the vehicle will not be able to enter the planned route, and also guarantees the stability and speed of vehicle operation.

[0061] Figure 5 is a flowchart following step S3 in one embodiment of the present disclosure. As shown in Figure 5, in one embodiment of the present disclosure, the method for determining the vehicle trajectory may further include the following steps S4 to S7.

[0062] In step S4, multiple historical driving trajectories for the target road section are determined from the historical driving trajectory information, and the trajectory point positions and trajectory point speeds for the multiple historical driving trajectories are determined.

[0063] When at least one vehicle is traveling along the target road section, each vehicle can transmit not only its own trajectory position to the designated server, but also its own vehicle speed information to the designated server. In this case, the designated server can store historical trajectory information, including the location of trajectory points and vehicle speed.

[0064] In several selectable embodiments, the location and velocity of the track points of multiple historical driving trajectories for a target road section can be extracted from historical driving trajectory information obtained from a specified server, and multiple historical driving trajectories can be generated based on the location and velocity of the track points.

[0065] In one possible example, step S4 can be performed by the processor calling a corresponding instruction stored in memory, or it can be performed by a trajectory information determination module operating within the processor.

[0066] In step S5, a reference trajectory is determined based on the trajectory point positions and trajectory point velocities in multiple historical trajectories. Here, the reference trajectory is one of the historical trajectories among the multiple historical trajectories.

[0067] In several selectable embodiments, trajectory velocity curves for multiple historical travel trajectories can be generated based on the trajectory point velocities and trajectory point positions of multiple historical travel trajectories. The trajectory velocity curves for the multiple historical travel trajectories are evaluated according to a pre-set evaluation rule, and the historical travel trajectory with the highest evaluation score is determined as the reference travel trajectory.

[0068] In one possible example, step S5 can be performed by the processor calling a corresponding instruction stored in memory, or it can be performed by a reference trajectory determination module operating within the processor.

[0069] In step S6, based on the trajectory point positions and trajectory point velocities in multiple historical driving trajectories, aggregate filtering is performed on the trajectory point positions and trajectory point velocities in the reference driving trajectory to determine the trajectory velocity curve for the target road section.

[0070] In several selectable embodiments, an influence model can be used to aggregate the trajectory point positions and trajectory point velocities in a reference trajectory based on the trajectory point positions and trajectory point velocities in multiple historical trajectories, thereby obtaining a first trajectory velocity curve. Here, a Gaussian model or other models can be selected as the influence model.

[0071] In some selectable embodiments, the first trajectory velocity curve obtained through aggregate processing may have velocity and position distortions. Therefore, the first trajectory velocity curve is filtered to remove the distortions and obtain a second trajectory velocity curve, which is then determined to be the trajectory velocity curve for the target road section.

[0072] In one possible example, step S6 can be performed by the processor calling a corresponding instruction stored in memory, or it can be performed by a trajectory velocity curve determination module operating within the processor.

[0073] In step S7, the recommended vehicle speed for the target road section is determined based on the trajectory speed curve.

[0074] In several selectable embodiments, the recommended vehicle speed at different locations on the target road section can be determined based on the trajectory speed curve.

[0075] In one possible example, step S7 can be performed by the processor calling a corresponding instruction stored in memory, or it can be performed by a recommended vehicle speed determination module operating within the processor.

[0076] In this embodiment, a reference driving trajectory is selected from multiple historical driving trajectories of the target road section, and aggregate filtering is performed on the reference driving trajectory based on the trajectory point positions and trajectory point speeds in the multiple historical driving trajectories to obtain a trajectory speed curve that displays the recommended vehicle speed at different locations in the target road section. Furthermore, based on the trajectory speed curve, the recommended vehicle speed for the target road section can be rationally obtained, which can help improve the rationality of the vehicle speed and the safety of the vehicle when driving at the vehicle's recommended speed in automatic driving mode.

[0077] Figure 6 is a flowchart of step S7 in one embodiment of the present disclosure. As shown in Figure 6, step S7 may include the following steps S7-1 to S7-4.

[0078] In step S7-1, the maximum velocity difference between adjacent trajectory points on the trajectory velocity curve is obtained.

[0079] In several selectable embodiments, the vehicle speed at different points on the target road section can be extracted from the trajectory speed curve of the target road section, and the speed difference between adjacent trajectory points can be compared to obtain the maximum speed difference between adjacent trajectory points.

[0080] In one possible example, step S7-1 can be performed by the processor calling a corresponding instruction stored in memory, or it can be performed by a maximum speed difference acquisition unit operating within the processor.

[0081] In step S7-2, if the maximum speed difference is greater than a preset speed difference threshold, segmentation processing is performed on the trajectory speed curve to obtain multiple trajectory speed curve segments.

[0082] Here, if the maximum speed difference is greater than a preset speed difference threshold, there is a possibility that a speed limit sign is installed between adjacent position points corresponding to the maximum speed difference. In this case, segmentation processing can be performed on the trajectory speed curve to obtain multiple trajectory speed curve segments. Different trajectory speed curve segments can indicate that the vehicle has different speed ranges.

[0083] In one possible example, step S7-2 can be performed by the processor calling a corresponding instruction stored in memory, or it can be performed by a segmentation processing unit operating within the processor.

[0084] In step S7-3, statistics are performed on the trajectory point velocities of multiple historical driving trajectories to determine the speed limit calibration value for the target road section.

[0085] In one example of the embodiments of this disclosure, an average speed value can be calculated for the trajectory point speeds of multiple historical travel trajectories, and a speed limit calibration value can be obtained by multiplying the average speed value by a coefficient between 0 and 1. Here, the coefficient can be a single preset number between 0.8 and 0.9, for example, the coefficient can be 0.85.

[0086] In one possible example, step S7-3 can be performed by the processor calling a corresponding instruction stored in memory, or it can be performed by a speed limit calibration value determination unit operating within the processor.

[0087] In step S7-4, multiple trajectory speed curve segments are calibrated using speed limit calibration values, and the recommended vehicle speed for the target road section is determined based on the calibration results.

[0088] In several selectable embodiments, the average vehicle speed of multiple trajectory speed curve segments can be calculated. If the average vehicle speed of a trajectory speed curve segment is less than the speed limit calibration value, it can be determined that this trajectory speed curve segment has passed calibration, and the average speed of this trajectory speed curve segment can be determined as the recommended vehicle speed for this trajectory speed curve segment. If the average vehicle speed of a trajectory speed curve segment is greater than or equal to the speed limit calibration value, it can be determined that this trajectory speed curve segment has not passed calibration. In this case, the speed curve of the trajectory speed of this trajectory speed curve segment can be adjusted until calibration is passed, and the recommended vehicle speed for this trajectory speed curve segment can be obtained, which can help improve the rationality of the vehicle speed and the safety of the vehicle when driving at the recommended vehicle speed in autonomous driving mode.

[0089] In one possible example, step S7-4 can be performed by the processor calling a corresponding instruction stored in memory, or it can be performed by a recommended vehicle speed determination unit operating within the processor.

[0090] In this embodiment, the maximum speed difference between adjacent trajectory points in the trajectory speed curve is compared with a preset speed difference threshold, and based on the comparison result, the target road section can be segmented into multiple trajectory speed curve segments. By statistically analyzing the trajectory points of multiple historical driving trajectories, a speed limit calibration value for the target road section can be obtained, and for example, the multiple trajectory speed curve segments can be calibrated with the speed limit calibration value to rationally obtain the recommended vehicle speed for the target road section.

[0091] Figure 7 is a flowchart of step S5 in one embodiment of the present disclosure. As shown in Figure 7, step S5 may include the following steps S5-1 to S5-2.

[0092] In step S5-1, the number of trajectory points for multiple historical travel trajectories is determined based on the trajectory time decay coefficient, the rate of change in trajectory direction, and the rate of change in speed of the multiple historical travel trajectories.

[0093] In some selectable embodiments, the time decay coefficient may be a log function or any other function capable of achieving the same purpose. The rate of change in trajectory direction can represent the stability and comfort of vehicle travel. The rate of change in trajectory speed can reflect the traffic flow density in the target road section.

[0094] In several selectable embodiments, multiple historical driving trajectories can be scored based on the trajectory time decay coefficient, trajectory direction change rate, and speed change rate of the multiple historical driving trajectories, thereby obtaining trajectory scores for the multiple historical driving trajectories. Here, the trajectory scores can comprehensively display the status of indicators such as the stability, comfort, and traffic flow density of the historical driving trajectories.

[0095] In one possible example, step S5-1 can be performed by the processor calling a corresponding instruction stored in memory, or it can be performed by a trajectory scoring unit operating within the processor.

[0096] In step S5-2, the historical driving trajectory with the highest score is determined to be the reference driving trajectory.

[0097] In one selectable example, step S5-2 can be performed by the processor calling a corresponding instruction stored in memory, or it can be performed by a reference trajectory determination unit operating within the processor.

[0098] In this embodiment, the time decay coefficient can display the degree of influence of time on the trajectory planning time of the historical trajectory distance, the rate of change in trajectory direction can display the stability and comfort of vehicle driving, and the rate of change in trajectory speed can respond to the traffic flow density in the target road section. Based on the trajectory time decay coefficient, trajectory direction change rate, and speed change rate of multiple historical trajectories, the multiple historical trajectories are scored, and the historical trajectory with the highest score is determined as the reference trajectory, thereby achieving overall optimization of stability, comfort, and traffic flow density. This helps generate a trajectory speed curve that is overall optimized in terms of stability, comfort, and traffic flow density in the dimensions of the target road section, and further helps generate a recommended vehicle speed that is overall optimized in terms of stability, comfort, and traffic flow density in the dimensions of the target road section, thereby contributing to overall optimization in terms of stability, comfort, and traffic flow density during vehicle driving in autonomous driving.

[0099] Figure 8 is a flowchart of a part of the method for determining a vehicle trajectory in one embodiment of the present disclosure. As shown in Figure 8, the method for determining a vehicle trajectory in one embodiment of the present disclosure may further include the following steps S8 to S10.

[0100] In step S8, the target lane is obtained for which no historical driving trajectory exists within the target road section.

[0101] If the target road section is a multi-lane road section, there may be target lanes for which no historical driving trajectory exists, either due to the limited historical driving trajectory data for the target road section or due to the driver's driving habits.

[0102] In one possible example, step S8 can be performed by the processor calling a corresponding instruction stored in memory, or it can be performed by a target lane determination unit operating within the processor.

[0103] In step S9, the traffic route of the target lane is determined based on the lane topology relationship of the target road section.

[0104] Here, the lane topology of the target road section may include the connectivity status of each lane within the target road section. From the lane topology of the target road section, lane information for the target lane and information for other lanes connected to the target lane can be obtained. Based on the lane information for the target lane and the information for other lanes connected to the target lane, a traffic route for the target lane can be established.

[0105] In one possible example, step S9 can be performed by the processor calling a corresponding instruction stored in memory, or it can be performed by a path determination unit operating within the processor.

[0106] In step S10, the recommended speed for the target lane is determined based on the type of road for the target lane, the route of the target lane, and at least one of the speed limit signs within a predetermined distance range for the target lane.

[0107] The target lane road types can include expressways, Class 1 roads, Class 2 roads, Class 3 roads, and Class 4 roads. Here, a Class 1 road may be a road connecting important political and economic centers, or a Class 1 road may be a road leading to an important airport or port. A Class 2 road may also connect political and economic centers, but may be slightly lower in level than a Class 1 road; for example, a Class 2 road may be a road leading to a general political and economic center or a general airport or port. A Class 3 road may connect cities at the county level (lower than a city level). A Class 4 road may connect counties, townships, and villages. Different road types usually have different speed limits or different recommended speeds.

[0108] In some possible embodiments, other lanes connecting to the target lane may already have a recommended speed in the target lane's travel path.

[0109] In several selectable embodiments, the speed limit signs within a predetermined distance range of the target lane are directed towards the target lane, and in this case, the speed limit value of the speed limit signs can influence the recommended speed of the target lane.

[0110] The recommended speed for the target lane can be reasonably determined based on at least one of the following: the type of road for the target lane, the route of the target lane, and speed limit signs within a predetermined distance range for the target lane.

[0111] In one possible example, step S10 can be performed by the processor calling a corresponding instruction stored in memory, or it can be performed by a recommended vehicle speed determination unit operating within the processor.

[0112] In this embodiment, the type of road for the target lane usually has different speed limits or different recommended speeds, and other lanes connecting to the target lane may already have recommended speeds along the target lane's route. Furthermore, the speed limits of speed markers within a predetermined distance range of the target lane may affect the recommended speed of the target lane. Therefore, by rationally determining the recommended speed of the target lane based on at least one of the type of road for the target lane, the route of the target lane, and the speed markers within a predetermined distance range of the target lane, it is possible to improve the rationality of the vehicle speed and the safety of the vehicle when driving at the vehicle's recommended speed in automatic driving mode.

[0113] Figure 9 is a flowchart of step S10 in one embodiment of the present disclosure. As shown in Figure 9, step S10 may include the following steps S10-1 to S10-2.

[0114] In step S10-1, if no speed limit sign is installed within a predetermined distance range of the target road section, the number of lanes in the same direction for the target lane is determined based on the route of the target road section, and the recommended speed for the target lane is determined based on the type of road for the target lane and the number of lanes in the same direction for the target lane.

[0115] If no speed limit signs are installed within a predetermined distance range of the target road section, it is not possible to directly obtain speed limit information for the target lane. Different road types usually have different speed limits or different recommended speeds, and the more lanes there are in the same direction, the higher the speed limit value. Therefore, the recommended speed for the target lane can be reasonably determined based on the road type of the target lane and the number of lanes in the same direction.

[0116] In one possible example, step S10-1 can be performed by the processor calling a corresponding instruction stored in memory, or it can be performed by a recommended vehicle speed determination unit operating within the processor.

[0117] In step S10-2, if a speed limit sign is installed within a predetermined distance range of the target road section, the relationship between the speed limit sign and the target lane is determined based on the relative positional relationship between the speed limit sign and the target lane and the route taken through the target road section. Based on the predetermined speed limit value of the speed limit sign, the relationship, the type of road in the target lane, and the number of lanes in the same direction in the target lane, the recommended speed for the target lane is determined.

[0118] If a speed limit sign is installed within a predetermined distance range of the target road section, the predetermined speed limit value on the speed limit sign can indicate a speed limit for the target lane and also for other lanes besides the target lane. The relationship between the speed limit sign and the target lane can be determined by the route of travel in the target road section; that is, whether or not the speed limit sign indicates a speed limit for the target lane.

[0119] Based on the relevant relationships, if it is determined that a speed limit sign can display a speed limit for the target lane, the recommended speed for the target lane can be reasonably determined based on the predetermined speed limit value of the speed limit sign, the type of road in the target lane, and the number of lanes going in the same direction in the target lane. Based on the relevant relationships, if it is determined that a speed limit sign cannot display a speed limit for the target lane, the recommended speed for the target lane can be reasonably determined based on the type of road in the target lane and the number of lanes going in the same direction in the target lane.

[0120] In one selectable example, step S10-2 can be performed by the processor calling a corresponding instruction stored in memory, or it can be performed by a recommended vehicle speed determination unit operating within the processor.

[0121] In this embodiment, based on whether or not a speed limit sign is provided within a predetermined distance range of the target road section, the recommended vehicle speed for the target lane can be rationally determined by combining the relationship between the speed limit sign and the target lane, the type of road in the target lane, and the number of lanes in the same direction in the target lane. This helps to improve the rationality of the vehicle speed and the safety of the vehicle when driving at the vehicle's recommended speed in automatic driving mode.

[0122] Any method for determining a vehicle trajectory according to the embodiments of this disclosure can be performed by any device having appropriate data processing capabilities, including but not limited to terminal devices and servers. Alternatively, any method for determining a vehicle trajectory according to the embodiments of this disclosure can be performed by a processor, for example, by calling a corresponding instruction stored in memory, thereby performing any method for determining a vehicle trajectory as described in the embodiments of this disclosure. These methods will not be described in detail below.

[0123] Those skilled in the art will understand that implementing all or some of the steps of the embodiments of the above method involves instructing the relevant hardware to complete the steps by program. The aforementioned program may be stored in a computer-readable storage medium, and when the program is executed, it performs the steps included in the embodiments of the above method, and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0124] (Example device) Figure 10 is a structural block diagram of a device for determining a vehicle trajectory in one embodiment of the present disclosure. As shown in Figure 10, the device for determining a vehicle trajectory may include an entry / exit trajectory point determination module 100, a cross-section intersection determination module 200, and a recommended trajectory determination module 300.

[0125] The entry / exit trajectory point determination module 100 determines multiple historical entry trajectory points for the entry section of the target road section and multiple historical exit trajectory points for the exit section of the target road section, based on the historical driving trajectory information of at least one vehicle in the target road section.

[0126] The cross-section intersection determination module 200 determines the entry cross-section intersection of the target road section based on multiple historical entry trajectory points, and determines the exit cross-section intersection of the target road section based on multiple historical exit trajectory points.

[0127] The recommended driving trajectory determination module 300 determines the recommended driving trajectory for the target road section based on the entry cross-section intersection and the exit cross-section intersection.

[0128] Figure 11 is a structural block diagram of a cross-sectional intersection determination module 200 in one embodiment of the present disclosure. As shown in Figure 11, the cross-sectional intersection determination module 200 may include a first clustering unit 210 and a second clustering unit 220.

[0129] The first clustering unit 210 performs the first clustering on multiple historical entry trajectory points to determine the entry cross-section intersection.

[0130] The second clustering unit 220 performs a second clustering operation on multiple historical exit trajectory points to determine the exit cross-section intersection.

[0131] Figure 12 is a structural block diagram of a recommended driving trajectory determination module 300 in one embodiment of the present disclosure. As shown in Figure 12, the recommended driving trajectory determination module 300 may include an associated history driving trajectory determination unit 310, a trajectory point interpolation clustering unit 320, and a recommended driving trajectory determination unit 330.

[0132] The related historical driving trajectory determination unit 310 determines the related historical driving trajectory associated with the entry cross-section intersection and the exit cross-section intersection from the historical driving trajectory information.

[0133] The trajectory point interpolation clustering unit 320 performs trajectory point interpolation clustering on the associated historical trajectories to determine at least one interpolated trajectory point.

[0134] The recommended driving trajectory determination unit 330 determines the recommended driving trajectory based on the entry cross-section intersection, trajectory points in the related historical driving trajectory, at least one interpolated trajectory point, and the exit cross-section intersection.

[0135] Figure 13 is a structural block diagram of a device for determining a vehicle trajectory in another embodiment of the present disclosure. As shown in Figure 13, the device for determining a vehicle trajectory may further include a trajectory information determination module 400, a reference trajectory determination module 500, a trajectory speed curve determination module 600, and a recommended vehicle speed determination module 700.

[0136] The trajectory information determination module 400 determines multiple historical trajectories for the target road section from the historical trajectory information, and determines the trajectory point positions and trajectory point speeds for the multiple historical trajectories.

[0137] The reference trajectory determination module 500 determines a reference trajectory based on the trajectory point positions and trajectory point velocities in multiple historical trajectories, where the reference trajectory is one historical trajectory among multiple historical trajectories.

[0138] The trajectory velocity curve determination module 600 determines the trajectory velocity curve for the target road section by performing aggregate filtering on the trajectory point positions and trajectory point velocities in the reference trajectory, based on the trajectory point positions and trajectory point velocities in multiple historical trajectories.

[0139] The recommended vehicle speed determination module 700 determines the recommended vehicle speed for the target road section based on the trajectory speed curve.

[0140] Figure 14 is a structural block diagram of a recommended vehicle speed determination module 700 in one embodiment of the present disclosure. As shown in Figure 14, the recommended driving trajectory determination module 700 may include a maximum speed difference acquisition unit 710, a segmentation processing unit 720, a speed limit calibration value determination unit 730, and a recommended vehicle speed determination unit 740.

[0141] The maximum speed difference acquisition unit 710 acquires the maximum speed difference between adjacent trajectory points in the trajectory speed curve.

[0142] The segmentation processing unit 720 performs segmentation processing on the trajectory velocity curve to obtain multiple trajectory velocity curve segments if the maximum velocity difference is greater than a preset velocity difference threshold.

[0143] The speed limit calibration value determination unit 730 performs statistical analysis on the trajectory point speeds of multiple historical driving trajectories to determine the speed limit calibration value for the target road section.

[0144] The recommended vehicle speed determination unit 740 calibrates multiple trajectory speed curve segments using speed limit calibration values ​​and determines the recommended vehicle speed for the target road section based on the calibration results.

[0145] Figure 15 is a structural block diagram of a reference trajectory determination module 500 in one embodiment of the present disclosure. As shown in Figure 15, the reference trajectory determination module 500 may include a trajectory scoring unit 510 and a reference trajectory determination unit 520.

[0146] The trajectory scoring unit 510 determines the trajectory score for multiple historical travel trajectories based on the trajectory time decay coefficient, the rate of change in trajectory direction, and the rate of change in speed of the multiple historical travel trajectories.

[0147] The reference trajectory determination unit 520 determines the historical trajectory with the highest score as the reference trajectory.

[0148] Figure 16 is a structural block diagram of a recommended vehicle speed determination module 700 in another embodiment of the present disclosure. As shown in Figure 16, the recommended vehicle speed determination module 700 may include a target lane determination unit 750, a route determination unit 760, and a recommended vehicle speed determination unit 770.

[0149] The target lane determination unit 750 acquires a target lane for which no historical driving trajectory exists in the target road section.

[0150] The traffic route determination unit 760 determines the traffic route of the target lane based on the lane topology relationship of the target road section.

[0151] The recommended vehicle speed determination unit 770 determines the recommended vehicle speed for the target lane based on the type of road for the target lane, the route of travel for the target lane, and at least one of the vehicle speed markers within a predetermined distance range for the target lane.

[0152] In one embodiment of the present disclosure, if no speed limit sign is provided within a preset distance range of the target road section, the recommended vehicle speed determination unit 770 determines the number of lanes in the same direction of the target lane based on the travel route of the target road section, and determines the recommended vehicle speed of the target lane based on the road type of the target lane and the number of lanes in the same direction of the target lane. Furthermore, if a speed limit sign is provided within a preset distance range of the target road section, the recommended vehicle speed determination unit 770 determines the relationship between the speed limit sign and the target lane based on the relative positional relationship between the speed limit sign and the target lane, and the travel route passing through the target road section, and determines the recommended vehicle speed of the target lane based on the predetermined speed limit value of the speed limit sign, the relationship, the road type of the target lane, and the number of lanes in the same direction of the target lane.

[0153] Furthermore, the specific embodiments of the apparatus for determining a vehicle trajectory according to the embodiments of this disclosure are similar to the specific embodiments of the method for determining a vehicle trajectory according to the embodiments of this disclosure, and the beneficial technical effects corresponding to the exemplary embodiments of the apparatus can be referenced from the corresponding beneficial technical effects of the exemplary method portion described above, and will not be described in detail here.

[0154] (Example electronic device) Figure 17 is a structural block diagram of an electronic device in one embodiment of the present disclosure. As shown in Figure 17, the electronic device includes at least one processor 10 and memory 20.

[0155] The processor 10 can be a central processing unit (CPU) or another form of processing unit having data processing and / or instruction execution functions, and can control other components in an electronic device to perform a desired function.

[0156] The memory 20 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored in the computer-readable storage media, and the processor 11 may execute one or more computer program instructions to realize the method for determining the vehicle trajectory of each embodiment of the present disclosure and / or other desired functions.

[0157] As an example, the electronic equipment may further include input devices 30 and output devices 40 connected to each other by a bus system and / or other form of connection mechanism (not shown).

[0158] This input device 30 may further include, for example, a keyboard, a mouse, and the like.

[0159] This output device 40 can output various types of information to the outside. This output device 40 may include, for example, a display, a speaker, a printer, a communication network, and remote output devices connected thereto.

[0160] For simplicity, Figure 17 shows only some of the components in the electronic device relevant to this disclosure, omitting components such as buses and input / output interfaces. Beyond these, the electronic device may further include any other appropriate components depending on the specific application.

[0161] (Examples of computer program products and computer-readable storage media) Embodiments of this disclosure further provide a computer program product, including computer program instructions, in addition to the methods and apparatus described above. When the computer program instructions are executed by a processor, the processor is caused to perform steps in the method for determining a vehicle trajectory of the various embodiments of this disclosure described in the “Exemplary Methods” portion above.

[0162] Computer program products can be created using one or any combination of programming languages ​​to produce program code for performing the operations of the embodiments of this disclosure, including object-oriented programming languages ​​such as Java® and C++, and conventional procedural programming languages ​​such as the C language or similar programming languages. The program code may run entirely on a user computing device, partially on a user device, run as a standalone software package, run partially on a user computing device and partially on a remote computing device, or run entirely on a remote computing device or a server.

[0163] Furthermore, embodiments of the present disclosure further provide a computer-readable storage medium in which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor is caused to perform steps in the method for determining a vehicle trajectory of various embodiments of the present disclosure described in the “Exemplary Methods” portion above.

[0164] Computer-readable storage media can employ any combination of one or more readable media. A readable medium can be a readable signal medium or a readable storage medium. A readable storage medium may include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include electrical connections with one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0165] While the basic principles of this disclosure have been explained above with reference to specific examples, the advantages, merits, and effects mentioned in this disclosure are merely illustrative and not limiting, and these advantages, merits, and effects are not necessarily present in every example of this disclosure. Furthermore, the specific details of the above disclosure are merely illustrative and easy-to-understand effects and are not limiting, and the above details do not necessarily limit this disclosure to being realized by the above specific details.

[0166] Those skilled in the art can make various modifications and alterations to the present disclosure without departing from the spirit and scope of the present application. Thus, if such modifications and alterations of the present application fall within the claims of the present disclosure and the equivalent art thereto, the present disclosure also includes such modifications and alterations.

Claims

1. The steps include determining a plurality of historical entry trajectory points of the entry section of the target road section and determining a plurality of historical exit trajectory points of the exit section of the target road section based on the historical driving trajectory information of at least one vehicle in the target road section, The steps include determining the intersection of the entry cross section of the target road section based on the plurality of historical entry trajectory points, and determining the intersection of the exit cross section of the target road section based on the plurality of historical exit trajectory points, A method for determining a vehicle's trajectory, comprising the step of determining a recommended trajectory for the target road section based on the entry cross-section intersection and the exit cross-section intersection.

2. The steps of determining the intersection of the entry cross-section of the target road section based on the plurality of historical entry trajectory points and determining the intersection of the exit cross-section of the target road section based on the plurality of historical exit trajectory points are as follows: The steps include: performing a first clustering operation on the plurality of historical entry trajectory points to determine the entry cross-section intersection; A method for determining a vehicle travel trajectory according to claim 1, comprising the step of performing a second clustering on the plurality of historical exit trajectory points to determine the exit cross-sectional intersection.

3. The step of determining the recommended driving trajectory for the target road section based on the aforementioned entry cross-section intersection and the aforementioned exit cross-section intersection is: The steps include determining the associated historical driving trajectory from the historical driving trajectory information, and determining the related historical driving trajectory associated with the entry cross-section intersection and the exit cross-section intersection. The steps include: performing trajectory point interpolation clustering on the aforementioned related historical trajectories to determine at least one interpolated trajectory point; A method for determining a vehicle travel trajectory according to claim 1, comprising the step of determining the recommended travel trajectory based on the entry cross-section intersection, the trajectory points in the related history travel trajectory, the at least one interpolated trajectory point, and the exit cross-section intersection.

4. The method for determining the vehicle's trajectory is: The steps include determining multiple historical driving trajectories for the target road section from the historical driving trajectory information, and determining the trajectory point positions and trajectory point speeds in the multiple historical driving trajectories, A step of determining a reference travel trajectory based on the trajectory point positions and trajectory point velocities in the plurality of historical travel trajectories, wherein the reference travel trajectory is one of the historical travel trajectories in the plurality of historical travel trajectories, The steps include: determining the trajectory speed curve of the target road section by performing aggregate filtering on the trajectory point positions and trajectory point speeds in the reference trajectory based on the trajectory point positions and trajectory point speeds in the plurality of historical travel trajectories; A method for determining a vehicle travel trajectory according to any one of claims 1 to 3, further comprising the step of determining a recommended vehicle speed for the target road section based on the trajectory speed curve.

5. The step of determining the recommended vehicle speed for the target road section based on the trajectory speed curve is: The steps include obtaining the maximum velocity difference between adjacent trajectory points in the trajectory velocity curve, If the aforementioned maximum speed difference is greater than a preset speed difference threshold, the trajectory speed curve is subjected to segmentation processing to obtain multiple trajectory speed curve segments. The steps include: performing statistical analysis on the trajectory point velocities of the aforementioned multiple historical travel trajectories to determine the speed limit calibration value for the target road section; A method for determining a vehicle trajectory according to claim 4, comprising the steps of: calibrating the plurality of trajectory speed curve segments using the speed limit calibration value, and determining the recommended vehicle speed for the target road section based on the calibration result.

6. The step of determining a reference travel trajectory based on the trajectory point positions and trajectory point velocities in the plurality of historical travel trajectories is as follows: A step of determining the number of trajectory points for the plurality of historical travel trajectories based on the trajectory time decay coefficient, the rate of change in trajectory direction, and the rate of change in speed of the plurality of historical travel trajectories, A method for determining a vehicle travel trajectory according to claim 4, comprising the step of determining the historical travel trajectory with the highest score as the reference travel trajectory.

7. The method for determining the vehicle's trajectory is: The steps include: acquiring a target lane in the aforementioned target road section for which no historical driving trajectory exists; The steps include determining the traffic route of the target lane based on the lane topology relationship of the target road section, A method for determining a vehicle trajectory according to any one of claims 1 to 3, further comprising the step of determining a recommended vehicle speed for the target lane based on at least one of the type of road for the target lane, the route of the target lane, and a vehicle speed marker within a predetermined distance range of the target lane.

8. An entry / exit trajectory point determination module for determining multiple historical entry trajectory points of the entry section of the target road section and extracting multiple historical exit trajectory points of the exit section of the target road section, based on historical driving trajectory information of at least one vehicle in the target road section, A cross-section intersection determination module for determining the entry cross-section intersection of the target road section based on the plurality of historical entry trajectory points and for determining the exit cross-section intersection of the target road section based on the plurality of historical exit trajectory points, A vehicle trajectory determination device, comprising a recommended trajectory determination module for determining a recommended trajectory for the target road section based on the entry cross-section intersection and the exit cross-section intersection.

9. A computer-readable storage medium characterized by storing a computer program for performing a method for determining a vehicle trajectory according to any one of claims 1 to 7.

10. An electronic device comprising a processor and a memory for storing instructions that the processor can execute, An electronic device characterized in that the processor reads and executes the executable instructions from the memory to realize a method for determining a vehicle trajectory according to any one of claims 1 to 7.

Images