Method, device, electronic equipment and storage medium for determining vehicle travel trajectory

Abstract

A method and device for determining a driving track of a vehicle, an electronic device and a storage medium are disclosed. The method comprises: determining a plurality of historical driving-in track points of a driving-in cross section of a target road section and a plurality of historical driving-out track points of a driving-out cross section of the target road section based on historical driving track information of at least one vehicle on the target road section; determining a driving-in cross section intersection of the target road section based on the plurality of historical driving-in track points and determining a driving-out cross section intersection of the target road section based on the plurality of historical driving-out track points; and determining a recommended driving track of the target road section based on the driving-in cross section intersection and the driving-out cross section intersection. The embodiments of the present disclosure can reasonably plan a recommended driving track for a target road section, i.e., can reduce the probability that a vehicle cannot drive into a planned path and can ensure the stability and speed of the vehicle.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of automatic driving, in particular to a method and device for determining a driving trajectory of a vehicle, an electronic device and a storage medium. BACKGROUND

[0002] Currently, when a vehicle is in an assisted driving mode or an automatic driving mode, the vehicle drives along a lane center line in a planned path according to the planned path. When the vehicle needs to turn or enter a ramp, if the vehicle drives completely along the lane center line, the vehicle may miss a reasonable position for turning or entering the ramp.

[0003] How to reasonably determine a driving trajectory of a vehicle is a problem to be solved. SUMMARY

[0004] The present inventors have found, through a large amount of creative labor, that when a vehicle needs to enter a ramp according to a planned path, if the vehicle enters a lane closest to the ramp too early, the vehicle may reduce the stability and speed of operation due to too early lane changing; if the vehicle wants to enter the ramp very close to the entrance of the ramp, the vehicle may not be able to smoothly enter the entrance of the target lane due to too many vehicles at the entrance. How to reasonably plan a path is a problem to be solved.

[0005] To solve the above technical problems, the present disclosure provides a method and device for determining a driving trajectory of a vehicle, an electronic device and a storage medium, to reasonably plan a path, i.e., to reduce the probability that a vehicle cannot enter a planned path, and to ensure the stability and speed of operation of the vehicle.

[0006] In a first aspect, the present disclosure provides a method for determining a driving trajectory of a vehicle, comprising:

[0007] determining a plurality of historical entry trajectory points of an entry section of the target road section and a plurality of historical exit trajectory points of an exit section of the target road section based on historical driving trajectory information of at least one vehicle on the target road section;

[0008] determining an entry section intersection point of the target road section based on the plurality of historical entry trajectory points and determining an exit section intersection point of the target road section based on the plurality of historical exit trajectory points;

[0009] determining a recommended driving trajectory of the target road section based on the entry section intersection point and the exit section intersection point.

[0010] In a second aspect, the present disclosure provides a device for determining a driving trajectory of a vehicle, comprising:

[0011] The driving-in and driving-out trajectory point determination module is configured to determine a plurality of historical driving-in trajectory points of the driving-in section of the target road section and extract a plurality of historical driving-out trajectory points of the driving-out section of the target road section based on historical driving trajectory information of at least one vehicle on the target road section.

[0012] The section intersection determination module is configured to determine the driving-in section intersection of the target road section based on the plurality of historical driving-in trajectory points and determine the driving-out section intersection of the target road section based on the plurality of historical driving-out trajectory points.

[0013] The recommended driving trajectory determination module is configured to determine the recommended driving trajectory of the target road section based on the driving-in section intersection and the driving-out section intersection.

[0014] In a third aspect of the present disclosure, a computer-readable storage medium is provided, which stores a computer program for executing the method for determining a driving trajectory of a vehicle according to the first aspect.

[0015] In a fourth aspect of the present disclosure, an electronic device is provided, which includes:

[0016] a processor;

[0017] a memory for storing executable instructions of the processor;

[0018] the processor is configured to read the executable instructions from the memory and execute the instructions to implement the method for determining a driving trajectory of a vehicle according to the first aspect.

[0019] In a fifth aspect of the present disclosure, a computer program product is provided, which, when executed by an instruction processor, performs the method for determining a driving trajectory of a vehicle according to the first aspect.

[0020] The method, device, electronic device and storage medium for determining a driving trajectory of a vehicle according to the embodiments of the present disclosure can reasonably determine the driving-in section intersection of the target road section according to the plurality of historical driving-in trajectory points and determine the driving-out section intersection of the target road section according to the plurality of historical driving-out trajectory points, and then can reasonably plan the recommended driving trajectory passing through the driving-in section intersection and the driving-out section intersection according to the driving-in section intersection and the driving-out section intersection of the target road section, that is, can reduce the probability that the vehicle cannot drive into the planned path and ensure the stability and speed of the vehicle. BRIEF DESCRIPTION OF DRAWINGS

[0021] Figure 1 is a flowchart of a method for determining a driving trajectory of a vehicle in one embodiment of the present disclosure;

[0022] Figure 2 is a schematic diagram of determining a recommended driving trajectory of a target road segment according to an entry cross-section intersection and an exit cross-section intersection in one example of the present disclosure;

[0023] Figure 3 is a flowchart of step S2 in one embodiment of the present disclosure;

[0024] Figure 4 is a flowchart of step S3 in one embodiment of the present disclosure;

[0025] Figure 5 is a flowchart after step S3 in one embodiment of the present disclosure;

[0026] Figure 6 is a flowchart of step S7 in one embodiment of the present disclosure;

[0027] Figure 7 is a flowchart of step S5 in one embodiment of the present disclosure;

[0028] Figure 8 is a partial flowchart of a method for determining a driving trajectory of a vehicle in one embodiment of the present disclosure;

[0029] Figure 9 is a flowchart of step S10 in one embodiment of the present disclosure;

[0030] Figure 10 is a structural block diagram of an apparatus for determining a driving trajectory of a vehicle in one embodiment of the present disclosure;

[0031] Figure 11 is a structural block diagram of a cross-section intersection determining module 200 in one embodiment of the present disclosure;

[0032] Figure 12 is a structural block diagram of a recommended driving trajectory determining module 300 in one embodiment of the present disclosure;

[0033] Figure 13 is a structural block diagram of an apparatus for determining a driving trajectory of a vehicle in another embodiment of the present disclosure;

[0034] Figure 14 is a structural block diagram of a recommended speed determining module 700 in one embodiment of the present disclosure;

[0035] Figure 15 is a structural block diagram of a reference driving trajectory determining module 500 in one embodiment of the present disclosure;

[0036] Figure 16is a structural block diagram of a recommended vehicle speed determination module 700 in another embodiment of the present disclosure.

[0037] Figure 17 is a structural block diagram of an electronic device in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0038] In order to explain the present disclosure, the example embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings, obviously, the described embodiments are only part of the embodiments of the present disclosure, not all the embodiments, it should be understood that the present disclosure is not limited by the example embodiments.

[0039] It should be noted that: unless otherwise specified, the relative arrangement, numerical expression and numerical value of the components and steps set forth in these embodiments do not limit the scope of the present disclosure.

[0040] SUMMARY

[0041] When the vehicle is in an assisted driving mode or an automatic driving mode, the vehicle is controlled to travel along the lane center line in the planned path. When the vehicle needs to turn or enter a ramp, if the vehicle travels completely along the lane center line, it may cause the vehicle to miss the reasonable position of the turn or the ramp.

[0042] The inventors of the present disclosure have found through a large amount of creative labor that when the vehicle needs to enter a ramp according to the planned path, if the vehicle enters the lane closest to the ramp too early, it may cause the vehicle to reduce the running stability and speed due to too early lane changing; if the vehicle wants to enter the ramp very close to the ramp entrance, it may cause the vehicle to be unable to smoothly enter the lane entrance of the target lane due to too many vehicles at the entrance. How to reasonably plan the path is a problem to be solved.

[0043] Example method

[0044] Figure 1 is a flowchart of a method for determining a vehicle travel trajectory in an embodiment of the present disclosure. The present embodiment can be applied on an electronic device, such as Figure 1 As shown in the figure, the method comprises the following steps:

[0045] S1: based on at least one historical travel trajectory information of a vehicle on a target road section, determining a plurality of historical entry trajectory points of an entry section of the target road section, and determining a plurality of historical exit trajectory points of an exit section of the target road section.

[0046] The target road section can include: a travel road section with a ramp entrance (ramp entrance and / or ramp exit), a travel road section with a lane number change scene (lane increase or lane decrease), a travel road section with a turn scene, a normal (single lane straight travel or multi-lane straight travel) travel road section, and other types of travel road sections.

[0047] The vehicle or other vehicles collect position information of the vehicle at intervals through the positioning device of the vehicle itself or the positioning device in the vehicle (for example, the positioning device of the mobile terminal in the vehicle) when passing through a target road section, to obtain multiple position information of the vehicle at the target road section, and generate a historical driving trajectory information of the vehicle when driving at the target road section according to the multiple position information.

[0048] The historical driving trajectory information of the vehicle or other vehicles when driving at the target road section is obtained from a designated server before the driving trajectory planning is performed. The vehicle or other vehicles upload the historical driving trajectory information of the vehicle itself to the designated server after passing through the target road section. The designated server can include the server of the Internet of Vehicles and the server of the navigation software, etc.

[0049] The vehicle or other vehicles collect position information of the vehicle at intervals through the positioning device of the vehicle itself or the positioning device in the vehicle (for example, the positioning device of the mobile terminal in the vehicle) when passing through a target road section, to obtain multiple position information of the vehicle at the target road section, and generate a historical driving trajectory information of the vehicle when driving at the target road section according to the multiple position information.

[0050] For any historical driving trajectory information obtained from the designated server, one or more trajectory point positions close to the entry section of the target road section are extracted from the historical driving trajectory information. For example, when it can be determined according to the historical driving trajectory information that there is a trajectory point located on the entry section of the target road section, the trajectory point is determined as the historical entry trajectory point of the historical driving trajectory information; when it can be determined according to the historical driving trajectory information that none of the trajectory points is located on the entry section of the target road section, multiple trajectory point positions close to the entry section of the target road section are extracted, a corresponding entry trajectory curve of the historical driving trajectory information is generated based on the multiple trajectory point positions, and the intersection point between the entry trajectory curve and the entry section of the target road section is determined as the historical entry trajectory point of the historical driving trajectory information.

[0051] The historical exit trajectory point of any historical driving trajectory can be determined in the same or similar manner as the historical entry trajectory point of any historical driving trajectory.

[0052] S2: determine the entry section intersection point of the target road section based on the multiple historical entry trajectory points, and determine the exit section intersection point of the target road section based on the multiple historical exit trajectory points.

[0053] The multiple historical entry trajectory points are clustered, and the entry section intersection point of the target road section is determined according to the clustering result. The multiple historical entry trajectory points can also be determined as multiple entry section intersection points of the target road section.

[0054] The plurality of historical exit trajectory points can be clustered, and the exit cross-section intersection of the target road section is determined according to the clustering result. The plurality of historical exit trajectory points can also be determined as the plurality of entry cross-section intersections of the target road section.

[0055] Figure 2 is a schematic diagram of determining the recommended driving trajectory of the target road section according to the entry cross-section intersection and the exit cross-section intersection in one example of the present disclosure.

[0056] S3: determining the recommended driving trajectory of the target road section based on the entry cross-section intersection and the exit cross-section intersection.

[0057] When the entry cross-section intersection and the exit cross-section intersection are both one, the first historical driving trajectory information passing through the entry cross-section intersection and the exit cross-section intersection can be obtained from the historical driving trajectory information, the second historical driving trajectory information passing through the entry cross-section intersection and being within a preset distance range of the exit cross-section intersection when passing through the exit cross-section intersection can be obtained from the historical driving trajectory information, and the third historical driving trajectory information passing through the entry cross-section intersection and being within a preset distance range of the entry cross-section intersection when passing through the entry cross-section intersection and being within a preset distance range of the exit cross-section intersection when passing through the exit cross-section intersection can be obtained from the historical driving trajectory information. According to the trajectory point position of any one of the first historical driving trajectory information, the second historical driving trajectory information and the third historical driving trajectory information, a recommended driving trajectory passing through the entry cross-section intersection and the exit cross-section intersection and having smooth curve and lower curvature than a preset curvature threshold is generated.

[0058] When the entry cross-section intersection and / or the exit cross-section intersection are multiple, a plurality of recommended driving trajectories passing through different entry cross-section intersections and exit cross-section intersections and having smooth curve and lower curvature than a preset curvature threshold can be generated.

[0059] Figure 2 is a schematic diagram of determining the recommended driving trajectory of the target road section according to the entry cross-section intersection and the exit cross-section intersection in one example of the present disclosure. As Figure 2As shown, the entry section of the target road section is S, and the exit section is E. The entry section has entry section intersection S1, entry section intersection S2, entry section intersection S3, entry section intersection S4, entry section intersection S5, and entry section intersection S6. The exit section has exit section intersection E1, entry section intersection E2, entry section intersection E3, entry section intersection E4, and entry section intersection E5. The recommended driving trajectory of the target road section can include: the recommended driving trajectory between entry section intersection S1 and exit section intersection E1, the recommended driving trajectory between entry section intersection S2 and exit section intersection E2, the recommended driving trajectory between entry section intersection S3 and exit section intersection E3, the recommended driving trajectory between entry section intersection S4 and exit section intersection E4, the recommended driving trajectory between entry section intersection S5 and exit section intersection E5, and the recommended driving trajectory between entry section intersection S6 and exit section intersection E5.

[0060] In this embodiment, before the driving trajectory planning is performed, the historical driving trajectory information uploaded by the vehicle or other vehicles to the designated server after passing through the target road section is acquired, a plurality of historical entry trajectory points of the entry section of the target road section and a plurality of historical exit trajectory points of the exit section are extracted from the historical driving trajectory information, the entry section intersection of the target road section can be reasonably determined according to the plurality of historical entry trajectory points, and the exit section intersection of the target road section can be reasonably determined according to the plurality of historical exit trajectory points, and then the recommended driving trajectory passing through the entry section intersection and the exit section intersection can be reasonably planned according to the entry section intersection and the exit section intersection of the target road section, that is, the probability that the vehicle cannot enter the planned path can be reduced, and the stability and speed of the vehicle operation can be ensured.

[0061] Figure 3 is a flowchart of step S2 in one embodiment of the present disclosure. As shown in Figure 3 Step S2 can include:

[0062] S2-1: First clustering of the plurality of historical entry trajectory points to determine the entry section intersection.

[0063] The plurality of historical trajectory points are first clustered according to the set clustering distance, and the entry section intersection is determined according to the result of the first clustering. The historical entry trajectory points of each lane of the target road section can be clustered respectively to obtain the entry section intersection of each lane. The entry section intersection of each lane can be one or more.

[0064] When the target road segment is a one-way single-vehicle road segment, the entering cross-section intersection can only include one intersection (e.g., a center point) with the one-way single-vehicle road segment at the entering cross-section. The entering cross-section intersection can also include multiple intersections with the one-way single-vehicle road segment at the entering cross-section, for example, when the entering cross-section of the target road segment is a T-junction, the entering cross-section intersection can include an intersection (usually a center point) when a vehicle travels straight through the T-junction entering cross-section, and an intersection (usually a non-center point) when a vehicle turns through the T-junction entering cross-section.

[0065] When the target road segment is a one-way multi-vehicle road segment, for the outermost lane, one entering cross-section intersection (e.g., a center point of the entering cross-section of the outermost lane) or two entering cross-section intersections (e.g., a center point of the entering cross-section of the outermost lane and an entering cross-section intersection determined due to lane changing from an adjacent lane into the outermost lane) can be determined. For the middle lanes other than the outermost lane, three entering cross-section intersections can be determined, for example, including a center point of the entering cross-section of the middle lane, and entering cross-section intersections determined due to left lane changing or right lane changing of a vehicle, respectively.

[0066] In addition, a screening process can also be performed based on the results of the first clustering to further reduce the number of entering cross-section intersections. For example, a number threshold of historical driving trajectory points generated after the first clustering can be set, and the clustering points below the number threshold can be screened out, and the clustering points retained after screening can be determined as the entering cross-section intersections.

[0067] S2-2: Second clustering is performed on the plurality of historical exiting trajectory points to determine exiting cross-section intersections.

[0068] The second clustering can be performed on the plurality of historical exiting trajectory points in the same or similar manner as the first clustering, thereby determining the exiting cross-section intersections of the target road segment.

[0069] It should be noted that the disclosure does not limit the execution relationship between the first clustering and the second clustering. The first clustering can be performed first and then the second clustering (i.e., step S2-1 is performed first and then step S2-2 is performed), or the second clustering can be performed first and then the first clustering (i.e., step S2-2 is performed first and then step S2-1 is performed), or the first clustering and the second clustering can be performed simultaneously (i.e., step S2-1 and step S2-2 are performed simultaneously).

[0070] In the embodiment, the first clustering of the plurality of historical entry trajectory points is performed to determine the entry cross-section intersection, and the second clustering of the plurality of historical exit trajectory points is performed to determine the exit cross-section intersection, so that the number of planning start points and planning end points in trajectory planning can be greatly reduced, the efficiency of generating the recommended driving trajectory is improved, and the vehicle is driven according to the recommended driving trajectory in automatic driving, so that the probability of the vehicle failing to enter the planned path is reduced, and the stability and speed of the vehicle are ensured.

[0071] Figure 4 is a flowchart of step S3 in one embodiment of the present disclosure. As shown in Figure 4 , step S3 can include:

[0072] S3-1: determining, from the historical driving trajectory information, the associated historical driving trajectory associated with the entry cross-section intersection and the exit cross-section intersection.

[0073] The distance between the entry cross-section intersection and the historical entry trajectory point corresponding to each historical driving trajectory is compared with the preset distance threshold, and the historical driving trajectory with a distance less than the preset distance threshold is determined as the first associated historical driving trajectory set associated with the entry cross-section intersection.

[0074] The distance between the exit cross-section intersection and the historical exit trajectory point corresponding to each historical driving trajectory is compared with the preset distance threshold, and the historical driving trajectory with a distance less than the preset distance threshold is determined as the second associated historical driving trajectory set associated with the exit cross-section intersection.

[0075] The same historical associated driving trajectory in the first associated historical driving trajectory set and the second associated historical driving trajectory set is determined as the associated historical driving trajectory. The distance between the historical entry trajectory point of the associated historical driving trajectory and the entry cross-section intersection is less than the preset distance threshold, and the distance between the historical exit trajectory point and the exit cross-section intersection is less than the preset distance threshold, that is, the entry point and the exit point of the associated historical driving trajectory and the recommended driving trajectory are close in position on the target road section.

[0076] S3-2: trajectory point interpolation clustering of the associated historical driving trajectory is performed to determine at least one interpolation trajectory point.

[0077] The trajectory associated historical driving trajectory is interpolated according to the positions of the plurality of trajectory points of the associated historical driving trajectory, so that the number of trajectory points of the associated historical driving trajectory is increased. The interpolated trajectory points are clustered to obtain the most possible trajectory points of the vehicle between the entry cross-section intersection and the exit cross-section intersection, that is, at least one interpolation trajectory point.

[0078] S3-3: determining the recommended driving trajectory based on the driving-in cross-section intersection, the trajectory points in the associated historical driving trajectory, the at least one interpolated trajectory point, and the driving-out cross-section intersection.

[0079] When the recommended driving trajectory is planned, at least one recommended driving trajectory passing through the driving-in cross-section intersection, the trajectory points in the associated historical driving trajectory, the at least one interpolated trajectory point, and the driving-out cross-section intersection is planned with the driving-in cross-section intersection as the starting point and the driving-out cross-section intersection as the ending point.

[0080] In this embodiment, the associated historical driving trajectory associated with the driving-in cross-section intersection and the driving-out cross-section intersection is determined from the historical driving trajectory information, the at least one interpolated trajectory point is obtained by trajectory point interpolation clustering on the associated historical driving trajectory, and at least one recommended driving trajectory passing through the driving-in cross-section intersection, the trajectory points in the associated historical driving trajectory, the at least one interpolated trajectory point, and the driving-out cross-section intersection can be reasonably planned with the driving-in cross-section intersection as the starting point and the driving-out cross-section intersection as the ending point, which helps the vehicle to drive according to the recommended driving trajectory when the vehicle is automatically driven, reduces the probability that the vehicle cannot drive into the planned path, and ensures the stability and speed of the vehicle operation.

[0081] Figure 5 is a flowchart after 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 driving trajectory can further include:

[0082] S4: determining a plurality of historical driving trajectories of the target road section from the historical driving trajectory information, and determining the trajectory point positions and the trajectory point speeds in the plurality of historical driving trajectories.

[0083] When at least one vehicle drives on the target road section, not only the trajectory position of the vehicle itself is sent to the designated server, but also the vehicle speed information of the vehicle itself is sent to the designated server. In this way, the designated server can store the historical driving trajectory information including the trajectory point positions and the vehicle speeds.

[0084] The trajectory point positions and the trajectory point speeds of the plurality of historical driving trajectories of the target road section are extracted from the historical driving trajectory information obtained from the designated server, and the plurality of historical driving trajectories can be generated according to the trajectory point positions and the trajectory point speeds.

[0085] S5: determining a reference driving trajectory based on the trajectory point positions and the trajectory point speeds in the plurality of historical driving trajectories. The reference driving trajectory is one of the plurality of historical driving trajectories.

[0086] The trajectory speed curves of the plurality of historical driving trajectories are generated according to the trajectory point speeds and the trajectory point positions of the plurality of historical driving trajectories. The historical driving trajectory with the highest evaluation score is determined as the reference driving trajectory according to the evaluation of the trajectory speed curves of the plurality of historical driving trajectories according to a preset evaluation rule.

[0087] S6: The trajectory point position and the trajectory point speed pair in the reference driving trajectory are aggregated and filtered based on the trajectory point position and the trajectory point speed pair in the plurality of historical driving trajectories, to determine the trajectory speed curve of the target road section.

[0088] The trajectory point position and the trajectory point speed pair in the reference driving trajectory are aggregated by using an influence model according to the trajectory point position and the trajectory point speed pair in the plurality of historical driving trajectories, to obtain a first trajectory speed curve. The influence model can be a Gaussian model or other models.

[0089] Since the first trajectory speed curve obtained by the aggregation processing can have a deformation in speed and position, the first trajectory speed curve needs to be filtered to eliminate the deformation and obtain a second trajectory speed curve, and the second trajectory speed curve is determined as the trajectory speed curve of the target road section.

[0090] S7: The recommended vehicle speed of the target road section is determined based on the trajectory speed curve.

[0091] The recommended vehicle speed of the vehicle at different positions of the target road section is determined according to the trajectory speed curve.

[0092] In this embodiment, the reference driving trajectory is selected from the plurality of historical driving trajectories of the target road section, and the reference driving trajectory is aggregated and filtered according to the trajectory point position and the trajectory point speed pair in the plurality of historical driving trajectories, to obtain the trajectory speed curve representing the recommended vehicle speed of the target road section at different positions. Then, the recommended vehicle speed of the target road section can be reasonably obtained according to the trajectory speed curve, thereby helping to improve the rationality of the vehicle speed and the safety of the vehicle when the vehicle drives according to the recommended vehicle speed in the automatic driving mode.

[0093] Figure 6 is a flowchart of step S7 in one embodiment of the present disclosure. As shown in Figure 6 , step S7 can include:

[0094] S7-1: Obtain the maximum speed difference between adjacent trajectory points in the trajectory speed curve.

[0095] The vehicle speeds of different position points of the target road section are extracted from the trajectory speed curve of the target road section, and the speed difference between adjacent trajectory points is compared to obtain the maximum speed difference between adjacent trajectory points.

[0096] S7-2: If the maximum speed difference value is greater than the preset speed difference threshold value, segment the trajectory speed curve to obtain a plurality of trajectory speed curve segments.

[0097] When the maximum speed difference value is greater than the preset speed difference threshold value, it is possible to set a speed limit sign between the adjacent position points corresponding to the maximum speed difference value, at which time the trajectory speed curve can be segmented to obtain a plurality of trajectory speed curve segments. Different trajectory speed curve segments represent different speed ranges of the vehicle.

[0098] S7-3: Based on the trajectory point speeds of the plurality of historical driving trajectories, a speed limit check value of the target road section is determined.

[0099] In one example of the present disclosure, an average speed value is calculated based on the trajectory point speeds of the plurality of historical driving trajectories, and the average speed value is multiplied by a coefficient between 0 and 1 to obtain the speed limit check value. The coefficient can be a preset value between 0.8 and 0.9, for example, the coefficient can be 0.85.

[0100] S7-4: The speed limit check value is used to check the plurality of trajectory speed curve segments, and a recommended speed of the target road section is determined based on the checking result.

[0101] The average speed of the plurality of trajectory speed curve segments is calculated. If the average speed of a certain trajectory speed curve segment is less than the speed limit check value, it is determined that the trajectory speed curve segment passes the check, and the average speed of the trajectory speed curve segment is determined as the recommended speed of the trajectory speed curve segment. If the average speed of a certain trajectory speed curve segment is greater than or equal to the speed limit check value, it is determined that the trajectory speed curve segment fails the check, at which time the trajectory speed curve of the trajectory speed curve segment needs to be adjusted and checked again until the check passes, thereby obtaining the recommended speed of the trajectory speed curve segment, which helps to improve the rationality of the vehicle speed and the safety of the vehicle when driving in the automatic driving mode according to the recommended speed of the vehicle.

[0102] In the present embodiment, the maximum speed difference value between adjacent trajectory points in the trajectory speed curve is compared with the preset speed difference threshold value, and according to the comparison result, the target road section can be segmented into a plurality of trajectory speed curve segments. The trajectory points of the plurality of historical driving trajectories are counted to obtain a speed limit check value of the target road section, for example, the speed limit check value is used to check the plurality of trajectory speed curve segments, which can reasonably obtain the recommended speed of the target road section.

[0103] Figure 7 is a flowchart of step S5 in one embodiment of the present disclosure. As shown in Figure 7 step S5 can include:

[0104] S5-1: determining trajectory scores of the plurality of historical driving trajectories based on the trajectory time decay coefficients, the direction change rates and the speed change rates of the plurality of historical driving trajectories.

[0105] The time decay coefficient can use a log function, or a function that can achieve the same purpose. The direction change rate of the trajectory can represent the stability and comfort of the vehicle driving. The speed change rate of the trajectory can reflect the density of the vehicle flow on the target road section.

[0106] The plurality of historical driving trajectories are scored based on the trajectory time decay coefficients, the direction change rates and the speed change rates of the plurality of historical driving trajectories, to obtain trajectory scores of the plurality of historical driving trajectories. The trajectory score can comprehensively represent the stability, comfort and vehicle flow density of the historical driving trajectory.

[0107] S5-2: determining the historical driving trajectory with the highest score as the reference driving trajectory.

[0108] In this embodiment, the time decay coefficient can represent the time influence degree of the historical driving trajectory distance on the trajectory planning time, the direction change rate of the trajectory can represent the stability and comfort of the vehicle driving, and the speed change rate of the trajectory can reflect the density of the vehicle flow on the target road section. The plurality of historical driving trajectories are scored based on the trajectory time decay coefficients, the direction change rates and the speed change rates of the plurality of historical driving trajectories, and the historical driving trajectory with the highest score is determined as the reference driving trajectory, which can achieve comprehensive optimization of stability, comfort and vehicle flow density, and is helpful to generate a trajectory speed curve of the target road section that is comprehensive optimal in the dimensions of stability, comfort and vehicle flow density, and further helpful to generate a recommended vehicle speed of the target road section that is comprehensive optimal in the dimensions of stability, comfort and vehicle flow density, thereby helping the vehicle to drive comprehensive optimal in the dimensions of stability, comfort and vehicle flow density during automatic driving.

[0109] Figure 8 is a part flow schematic diagram of a method for determining a vehicle driving trajectory in an embodiment of the present disclosure. As shown in Figure 8 In an embodiment of the present disclosure, the method for determining a vehicle driving trajectory can further include:

[0110] S8: obtaining a target lane of the target road section where no historical driving trajectory exists.

[0111] When the target road section is a multi-lane road section, the target road section can have a target lane where no historical driving trajectory exists due to the small number of historical driving trajectories of the target road section, or due to the driving habits of the driver.

[0112] S9: determining a passing path of the target lane based on the lane topological relationship of the target road section.

[0113] The lane topological relationship of the target road section includes connectivity of each lane in the target road section. The lane information of the target lane and the information of other lanes connected to the target lane can be obtained from the lane topological relationship of the target road section. The passing path of the target lane can be established based on the lane information of the target lane and the information of other lanes connected to the target lane.

[0114] S10: determining a recommended speed of the target lane based on at least one of a road type of the target lane, a passing path of the target lane, and a speed limit sign within a preset distance range of the target lane.

[0115] The road type of the target lane can include a highway, a first-class road, a second-class road, a third-class road, and a fourth-class road. The first-class road is a road connecting important political and economic centers or a road leading to important airports and ports. The second-class road is also a road connecting political and economic centers, but is lower in grade than the first-class road, and is a common political and economic center or a road leading to a general airport and port. The third-class road is a road used to communicate cities above the county level. The fourth-class road is a road used to communicate counties, townships, and villages. Different road types usually have different speed limits or different recommended speeds.

[0116] The other lanes connected to the target lane in the passing path of the target lane can already have recommended speeds.

[0117] The speed limit sign within the preset distance range of the target lane can be for the target lane, and the speed limit value of the speed limit sign can affect the recommended speed of the target lane.

[0118] Based on at least one of the road type of the target lane, the passing path of the target lane, and the speed limit sign within the preset distance range of the target lane, the recommended speed of the target lane can be reasonably determined.

[0119] In this embodiment, since the road type of the target lane usually has different speed limits or different recommended speeds, the other lanes connected to the target lane in the passing path of the target lane can already have recommended speeds, and the speed limit sign within the preset distance range of the target lane can be the recommended speed of the target lane. Therefore, based on at least one of the road type of the target lane, the passing path of the target lane, and the speed limit sign within the preset distance range of the target lane, the recommended speed of the target lane can be reasonably determined, thereby helping to improve the rationality of the speed and the safety of the vehicle when the vehicle drives according to the recommended speed of the vehicle in the automatic driving mode.

[0120] Figure 9 FIG. 10 is a flowchart of step S10 in one embodiment of the present disclosure. As shown in FIG. 10, step S10 can include: Figure 9

[0121] ​S10-1: If no speed limit sign is set within the preset distance range of the target road section, determine the number of same-direction lanes of the target lane based on the passing path of the target road section, and determine the recommended speed of the target lane based on the road type of the target lane and the number of same-direction lanes of the target lane.

[0122] When no speed limit sign is set within the preset distance range of the target road section, the speed limit information of the target lane cannot be directly obtained. Since different road types usually have different speed limits or different recommended speeds, and the more same-direction lanes there are, the higher the speed limit value, the recommended speed of the target lane can be reasonably determined according to the road type of the target lane and the number of same-direction lanes of the target lane.

[0123] S10-2: If a speed limit sign is set within the preset distance range of the target road section, determine the association relationship between the speed limit sign and the target lane based on the relative position relationship between the speed limit sign and the target lane and the passing path through the target road section, and determine the recommended speed of the target lane based on the specified speed limit value of the speed limit sign, the association relationship, the road type of the target lane and the number of same-direction lanes of the target lane.

[0124] When a speed limit sign is set within the preset distance range of the target road section, the specified speed limit value of the speed limit sign may be a speed limit prompt for the target lane or a speed limit prompt for other lanes other than the target lane. According to the passing path of the target road section, the association relationship between the speed limit sign and the target lane can be determined, i.e., whether the speed limit sign is a speed limit prompt for the target lane.

[0125] When it is determined based on the association relationship that the speed limit sign is a speed limit prompt for the target lane, the recommended speed of the target lane can be reasonably determined based on the specified speed limit value of the speed limit sign, the road type of the target lane and the number of same-direction lanes of the target lane. When it is determined based on the association relationship that the speed limit sign is not a speed limit prompt for the target lane, the recommended speed of the target lane can be reasonably determined based on the road type of the target lane and the number of same-direction lanes of the target lane.

[0126] In this embodiment, whether a speed limit sign is set within the preset distance range of the target road section can be determined, and the recommended speed of the target lane can be reasonably determined in combination with the association relationship between the speed limit sign and the target lane, the road type of the target lane and the number of same-direction lanes of the target lane, thereby helping to improve the rationality of the vehicle speed and the safety of the vehicle when driving in the automatic driving mode according to the recommended speed of the vehicle.

[0127] Exemplary apparatus

[0128] Figure 10 is a structural block diagram of an apparatus for determining a vehicle driving trajectory in one embodiment of the present disclosure. As shown in Figure 10As shown, the device for determining a vehicle travel trajectory can comprise:

[0129] An entry-exit trajectory point determination module 100 is configured to determine a plurality of historical entry trajectory points of an entry section of the target road section and extract a plurality of historical exit trajectory points of an exit section of the target road section based on historical travel trajectory information of at least one vehicle on the target road section.

[0130] A section intersection determination module 200 is configured to determine an entry section intersection of the target road section based on the plurality of historical entry trajectory points and determine an exit section intersection of the target road section based on the plurality of historical exit trajectory points.

[0131] A recommended travel trajectory determination module 300 is configured to determine a recommended travel trajectory of the target road section based on the entry section intersection and the exit section intersection.

[0132] Figure 11 FIG. 2 is a structural block diagram of the section intersection determination module 200 in an embodiment of the present disclosure. As shown, Figure 11 The section intersection determination module 200 can comprise:

[0133] A first clustering unit 210 is configured to perform first clustering on the plurality of historical entry trajectory points to determine the entry section intersection.

[0134] A second clustering unit 220 is configured to perform second clustering on the plurality of historical exit trajectory points to determine the exit section intersection.

[0135] Figure 12 FIG. 3 is a structural block diagram of the recommended travel trajectory determination module 300 in an embodiment of the present disclosure.

[0136] As shown, Figure 12 The recommended travel trajectory determination module 300 can comprise:

[0137] An associated historical travel trajectory determination unit 310 is configured to determine an associated historical travel trajectory associated with the entry section intersection and the exit section intersection from the historical travel trajectory information.

[0138] A trajectory point interpolation clustering unit 320 is configured to perform trajectory point interpolation clustering on the associated historical travel trajectory to obtain at least one interpolation trajectory point.

[0139] A recommended travel trajectory determination unit 330 is configured to determine the recommended travel trajectory based on the entry section intersection, the trajectory points in the associated historical travel trajectory, the at least one interpolation trajectory point, and the exit section intersection.

[0140] Figure 13is a structural block diagram of an apparatus for determining a vehicle driving trajectory in another embodiment of the present disclosure.

[0141] As shown in Figure 13 , the apparatus for determining a vehicle driving trajectory can further include:

[0142] a trajectory information determination module 400 configured to determine a plurality of historical driving trajectories of the target road section from the historical driving trajectory information, and determine trajectory point positions and trajectory point speeds in the plurality of historical driving trajectories;

[0143] a reference driving trajectory determination module 500 configured to determine a reference driving trajectory based on the trajectory point positions and the trajectory point speeds in the plurality of historical driving trajectories, wherein the reference driving trajectory is one of the plurality of historical driving trajectories;

[0144] a trajectory speed curve determination module 600 configured to perform aggregated filtering on the trajectory point positions and the trajectory point speeds in the reference driving trajectory based on the trajectory point positions and the trajectory point speeds in the plurality of historical driving trajectories, and determine a trajectory speed curve of the target road section;

[0145] a recommended speed determination module 700 configured to determine a recommended speed of the target road section based on the trajectory speed curve.

[0146] Figure 14 is a structural block diagram of the recommended speed determination module 700 in an embodiment of the present disclosure. As shown in Figure 14 , the recommended driving trajectory determination module 700 can include:

[0147] a maximum speed difference value acquisition unit 710 configured to acquire a maximum speed difference value between adjacent trajectory points in the trajectory speed curve;

[0148] a segmentation processing unit 720 configured to, if the maximum speed difference value is greater than a preset speed difference threshold value, perform segmentation processing on the trajectory speed curve to obtain a plurality of trajectory speed curve segments;

[0149] a speed limit check value determination unit 730 configured to statistically determine trajectory point speeds of the plurality of historical driving trajectories to obtain a speed limit check value of the target road section;

[0150] a recommended speed determination unit 740 configured to check the plurality of trajectory speed curve segments using the speed limit check value, and determine a recommended speed of the target road section based on a check result.

[0151] Figure 15 is a structural block diagram of the reference driving trajectory determination module 500 in an embodiment of the present disclosure.

[0152] As shown in Figure 15As shown, the reference driving trajectory determination module 500 can comprise:

[0153] a trajectory scoring unit 510, configured to determine a trajectory score of the plurality of historical driving trajectories based on a trajectory time decay coefficient of the plurality of historical driving trajectories, a direction change rate of the trajectory, and a speed change rate of the trajectory;

[0154] a reference driving trajectory determination unit 520, configured to determine a historical driving trajectory with the highest score as the reference driving trajectory.

[0155] Figure 16 is a structural block diagram of a recommended vehicle speed determination module 700 in another embodiment of the present disclosure. As shown, Figure 16 the recommended vehicle speed determination module 700 can further comprise:

[0156] a target lane determination unit 750, configured to obtain a target lane in the target road segment in which no historical driving trajectory exists;

[0157] a traffic path determination unit 760, configured to determine a traffic path of the target lane based on a lane topological relationship of the target road segment;

[0158] a recommended vehicle speed determination unit 770, configured to determine a recommended vehicle speed of the target lane based on at least one of a road type of the target lane, the traffic path of the target lane, and a speed limit sign within a preset distance range of the target lane.

[0159] In an embodiment of the present disclosure, the recommended vehicle speed determination unit 770 is configured to, if no speed limit sign is arranged within the preset distance range of the target road segment, determine a number of same-direction lanes of the target lane based on the traffic path of the target road segment, and determine the recommended vehicle speed of the target lane based on the road type of the target lane and the number of same-direction lanes of the target lane; and the recommended vehicle speed determination unit 770 is further configured to, if a speed limit sign is arranged within the preset distance range of the target road segment, determine an association relationship between the speed limit sign and the target lane based on a relative positional relationship between the speed limit sign and the target lane and the traffic path of the target road segment, and determine the recommended vehicle speed of the target lane based on a specified speed limit value of the speed limit sign, the association relationship, the road type of the target lane, and the number of same-direction lanes of the target lane.

[0160] It should be noted that the specific implementation of the device for determining a vehicle driving trajectory in the embodiment of the present disclosure is similar to the specific implementation of the method for determining a vehicle driving trajectory in the embodiment of the present disclosure. The corresponding beneficial technical effects of the exemplary embodiment of the device can be referred to the corresponding beneficial technical effects of the above-mentioned exemplary method part, which will not be described here again.

[0161] Exemplary electronic device

[0162] Figure 17 is a structural block diagram of an electronic device in one embodiment of the present disclosure. As shown, the electronic device includes at least one processor 10 and a memory 20. Figure 17

[0163] The processor 10 can be a central processing unit (CPU) or other form of processing unit having data processing and / or instruction execution capabilities, and can control other components in the electronic device to perform desired functions.

[0164] The memory 20 can include one or more computer program products that can include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory, for example, can include random access memory (RAM), cache memory, and / or the like. The non-volatile memory, for example, can include read-only memory (ROM), hard disk, flash memory, and / or the like. One or more computer program instructions can be stored on the computer-readable storage media, and the processor 11 can execute the one or more computer program instructions to implement the method of determining a vehicle travel trajectory and / or other desired functions of various embodiments of the present disclosure described above.

[0165] In one example, the electronic device can further include an input device 30 and an output device 40, which are interconnected through a bus system and / or other forms of connection mechanisms (not shown).

[0166] The input device 30 can further include, for example, a keyboard, a mouse, and / or the like.

[0167] The output device 40 can output various information to the outside, which can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and / or the like.

[0168] Of course, in order to simplify, Figure 17 only some of the components in the electronic device related to the present disclosure are shown, and components such as buses, input / output interfaces, and / or the like are omitted. In addition, the electronic device can further include any other appropriate components according to specific application cases.

[0169] Exemplary computer program product and computer readable storage medium

[0170] In addition to the above method and device, embodiments of the present disclosure can also provide a computer program product including computer program instructions, which, when executed by a processor, cause the processor to perform the steps of the method of determining a vehicle travel trajectory of various embodiments of the present disclosure described in the “Exemplary Method” section above. ​

[0171] The computer program product can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote computing device or server. It will be appreciated that the program code can be implemented in a plurality of forms including, but not limited to, a standalone application, a plug-in, a service, or any other distribution form.

[0172] In addition, the embodiments of the present disclosure can also be a computer readable storage medium, which stores computer program instructions, and the computer program instructions make the processor execute the steps of the method for determining the vehicle driving track described in the above “Exemplary Method” section when the processor runs.

[0173] The computer readable storage medium can take the form of one or more combinations of any type of readable medium. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium, for example, but not limited to, includes an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples (non-exhaustive list) of the readable storage medium include an electrical connection having one or more wires, a portable disc, 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 above.

[0174] The above describes the basic principles of the present disclosure in combination with specific embodiments, but the advantages, advantages, effects and the like mentioned in the present disclosure are only examples and are not limited. It cannot be considered that each embodiment of the present disclosure must have the above-mentioned advantages, advantages and effects. In addition, the above-mentioned specific details are only for the purpose of example and for the purpose of understanding, and the above-mentioned details do not limit the present disclosure to the above-mentioned specific details.

[0175] Those skilled in the art can make various modifications and variations to the present disclosure without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present disclosure and their equivalents.

Claims

1. A method for determining a driving trajectory of a vehicle, comprising: determining a plurality of historical driving-in trajectory points of a driving-in cross section of a target road section and a plurality of historical driving-out trajectory points of a driving-out cross section of the target road section based on historical driving trajectory information of at least one vehicle on the target road section; determining a driving-in cross section intersection of the target road section based on the plurality of historical driving-in trajectory points and determining a driving-out cross section intersection of the target road section based on the plurality of historical driving-out trajectory points; determining a recommended driving trajectory of the target road section based on the driving-in cross section intersection and the driving-out cross section intersection; further comprising: determining a plurality of historical driving trajectories of the target road section and determining trajectory point positions and trajectory point speeds in the plurality of historical driving trajectories from the historical driving trajectory information; determining a reference driving trajectory based on the trajectory point positions and the trajectory point speeds in the plurality of historical driving trajectories, wherein the reference driving trajectory is one of the plurality of historical driving trajectories; performing an aggregated filtering on the trajectory point positions and the trajectory point speeds in the reference driving trajectory based on the trajectory point positions and the trajectory point speeds in the plurality of historical driving trajectories to determine a trajectory speed curve of the target road section; determining a recommended speed of the target road section based on the trajectory speed curve.

2. The method of claim 1, wherein, The determining of the driving-in cross section intersection of the target road section based on the plurality of historical driving-in trajectory points and the determining of the driving-out cross section intersection of the target road section based on the plurality of historical driving-out trajectory points comprises: performing a first clustering on the plurality of historical driving-in trajectory points to determine the driving-in cross section intersection; performing a second clustering on the plurality of historical driving-out trajectory points to determine the driving-out cross section intersection.

3. The method of claim 1, wherein, The determining of the recommended driving trajectory of the target road section based on the driving-in cross section intersection and the driving-out cross section intersection comprises: determining an associated historical driving trajectory associated with the driving-in cross section intersection and the driving-out cross section intersection from the historical driving trajectory information; performing a trajectory point interpolation clustering on the associated historical driving trajectory to determine at least one interpolation trajectory point; determining the recommended driving trajectory based on the driving-in cross section intersection, the trajectory points in the associated historical driving trajectory, the at least one interpolation trajectory point and the driving-out cross section intersection.

4. The method of claim 1, wherein, The determining of the recommended speed of the target road section based on the trajectory speed curve comprises: obtaining a maximum speed difference value between adjacent trajectory points in the trajectory speed curve; if the maximum speed difference value is greater than a preset speed difference threshold value, performing a segmentation processing on the trajectory speed curve to obtain a plurality of trajectory speed curve segments; determining a speed limit checking value of the target road section based on a statistical result of the trajectory point speeds of the plurality of historical driving trajectories; performing a checking on the plurality of trajectory speed curve segments by using the speed limit checking value to determine the recommended speed of the target road section based on a checking result.

5. The method of claim 1, wherein, The determining of the reference driving trajectory based on the trajectory point positions and the trajectory point speeds in the plurality of historical driving trajectories comprises: determining trajectory scores of the plurality of historical driving trajectories based on a trajectory time decay coefficient, a direction change rate and a speed change rate of the trajectory of the plurality of historical driving trajectories; The historical driving track with the highest score is determined as the reference driving track.

6. The method of any one of claims 1-3, further comprising: obtaining a target lane in the target road section in which no historical driving track exists; determining a passing path of the target lane based on a lane topological relationship of the target road section; determining a recommended speed of the target lane based on at least one of a road type of the target lane, the passing path of the target lane, and a speed limit sign within a preset distance range of the target lane.

7. An apparatus for determining a driving track of a vehicle, comprising: an entry-exit track point determination module configured to determine a plurality of historical entry track points of an entry cross section of a target road section based on historical driving track information of at least one vehicle on the target road section, and extract a plurality of historical exit track points of an exit cross section of the target road section; a cross section intersection determination module configured to determine an entry cross section intersection of the target road section based on the plurality of historical entry track points, and determine an exit cross section intersection of the target road section based on the plurality of historical exit track points; a recommended driving track determination module configured to determine a recommended driving track of the target road section based on the entry cross section intersection and the exit cross section intersection; further comprising: a track information determination module configured to determine a plurality of historical driving tracks of the target road section from the historical driving track information, and determine track point positions and track point speeds in the plurality of historical driving tracks; a reference driving track determination module configured to determine a reference driving track based on the track point positions and the track point speeds in the plurality of historical driving tracks, wherein the reference driving track is one of the plurality of historical driving tracks; a track speed curve determination module configured to aggregate and filter the track point positions and the track point speeds in the reference driving track based on the track point positions and the track point speeds in the plurality of historical driving tracks, to determine a track speed curve of the target road section; a recommended speed determination module configured to determine a recommended speed of the target road section based on the track speed curve.

8. A computer readable storage medium, the storage medium storing a computer program for executing the method for determining a driving track of a vehicle according to any one of claims 1-6.

9. An electronic device, comprising: a processor; a memory for storing executable instructions of the processor; the processor configured to read the executable instructions from the memory and execute the instructions to implement the method for determining a driving track of a vehicle according to any one of claims 1-6.

Images