Vehicle driving control method and device, computer equipment, readable storage medium and program product

By filtering and calculating reference lines in high-precision maps, the problem of poor vehicle driving control effect in complex urban road scenarios is solved, the optimal reference lines selection in complex scenarios is achieved, and the effect of vehicle driving control is improved and stability.

CN119078858APending Publication Date: 2024-12-06NINGBO LOTUS ROBOTICS CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411097596.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-12
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

In complex urban road scenarios, it is difficult for the prior art to select the optimal reference line in high-precision maps, resulting in a reduction in vehicle driving control effect.

Method used

By determining multiple driving reference lines based on map data and vehicle location, screening out adjacent reference lines, determining whether a lane change command has been received, calculating the driving cost of each candidate reference line, and selecting the optimal target reference line for vehicle follow-up.

Benefits of technology

In complex scenarios, the effect of vehicle driving control is improved, ensuring that the selected reference line is optimal, and improving the stability and stability of driving control.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119078858A_ABST
    Figure CN119078858A_ABST
Patent Text Reader

Abstract

The invention relates to a vehicle driving control method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: determining a plurality of driving reference lines based on map data and a current vehicle position; screening out adjacent reference lines from the plurality of driving reference lines; judging whether a lane changing instruction is received or not, and determining candidate reference lines from the adjacent reference lines based on a judgment result; calculating the driving cost of each candidate reference line, and determining a target reference line from the candidate reference lines based on the driving cost; and controlling the vehicle to drive along with the target reference line. By adopting the method, the vehicle driving control effect in a complex scene can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a vehicle driving control method, device, computer equipment, computer-readable storage medium and computer program product. Background Art

[0002] Smart driving vehicles can reduce the driver's driving pressure and related responsibilities. They can rely on their own sensors and processors to obtain driving information and navigate the vehicle to the target location. High-precision maps are an important component of smart driving vehicles. Relying on high-precision maps, vehicles can obtain beyond-visual-range perception capabilities and reduce the vehicle's dependence on sensors. However, the number of lane center lines in the raw data provided by high-precision maps is large and the data is huge. Therefore, how to select a suitable reference line for the vehicle to follow in a more complex urban road scene based on high-precision maps is a topic that needs to be studied.

[0003] At present, multiple reference lines are often generated based on map data, and then the vehicle calculates the driving cost of each reference line, thereby selecting an optimal reference line for the vehicle to follow. However, this solution can only be applied to simple vehicle driving environments. For complex vehicle driving environments, the reference line selected by this method is not necessarily the optimal one, thereby reducing the effect of vehicle driving control in complex scenarios. Summary of the invention

[0004] Based on this, it is necessary to provide a vehicle driving control method, device, computer equipment, computer-readable storage medium and computer program product that can improve the effect of vehicle driving control in complex scenarios in response to the above technical problems.

[0005] In a first aspect, the present application provides a vehicle driving control method, comprising:

[0006] Determine multiple driving reference lines based on map data and the current vehicle position;

[0007] Filtering adjacent reference lines from the plurality of driving reference lines;

[0008] Determine whether a lane change instruction is received, and determine a candidate reference line from the adjacent reference lines based on the determination result; calculate a driving cost of each candidate reference line, and determine a target reference line from the candidate reference lines based on the driving cost;

[0009] The vehicle is controlled to drive along the target reference line.

[0010] In one embodiment, the step of selecting adjacent reference lines from the plurality of driving reference lines comprises:

[0011] Determining a lateral offset between each of the plurality of driving reference lines and a center line of the vehicle;

[0012] Based on the lateral offset, a preset offset threshold, and historical candidate reference lines, an adjacent reference line is screened out from the plurality of driving reference lines.

[0013] In one embodiment, the preset offset threshold includes a real offset threshold, a forked offset threshold and an original offset threshold;

[0014] The step of selecting an adjacent reference line from the plurality of driving reference lines based on the lateral offset, a preset offset threshold, and historical candidate reference lines includes:

[0015] For each driving reference line, when the first absolute value is less than the real offset threshold, the current driving reference line is used as the real class adjacent reference line; the first absolute value includes the absolute value of the lateral offset of the current driving reference line, or the absolute value of the difference between the lateral offset of the current driving reference line and the minimum lateral offset; the minimum lateral offset is the minimum value of the lateral offsets of the multiple driving reference lines;

[0016] When there is a bifurcation point between the current driving reference line and other reference lines in the multiple reference lines, and the second absolute value is greater than the real offset threshold and less than the bifurcation offset threshold, the current driving reference line is used as a bifurcation-type adjacent reference line; the second absolute value includes the absolute value of the lateral offset of the current driving reference line, or the absolute value of the difference between the lateral offset of the current driving reference line and the minimum lateral offset;

[0017] When the current driving reference line matches the historical candidate reference line and the third absolute value is less than the original offset threshold, the current driving reference line is used as the original class neighboring reference line; the third absolute value includes the absolute value of the lateral offset of the current driving reference line, or the absolute value of the difference between the lateral offset of the current driving reference line and the minimum lateral offset;

[0018] The real class neighboring reference line, the forked class neighboring reference line and the original class neighboring reference line are all used as the neighboring reference lines.

[0019] In one embodiment, the determining of the candidate reference line from the adjacent reference lines based on the judgment result includes:

[0020] When the result of the judgment is that no lane change instruction is received, taking the adjacent reference line as a candidate reference line;

[0021] When the judgment result is that a lane change instruction is received, the lane after the lane change indicated in the lane change instruction is determined; and an adjacent reference line located in the lane after the lane change is selected from the adjacent reference lines as the candidate reference line.

[0022] In one of the embodiments, after determining the target reference line from the candidate reference lines, the method further includes:

[0023] Determining whether the target reference line has a bifurcation;

[0024] In the case where the target reference line is bifurcated, the reference line identifier of the target reference system after the bifurcation point is determined;

[0025] Accordingly, controlling the vehicle to drive along the target reference line includes:

[0026] The vehicle is controlled to drive along the reference line indicated by the reference line marker.

[0027] In one embodiment, calculating the driving cost of each candidate reference line includes:

[0028] Determine at least one of the driving task cost, smoothness cost, length cost, navigation direction cost, offset cost, distance cost between the current reference line and the lane boundary line, lane width cost of the lane where the current reference line is located, or lane type cost of the lane where the current reference line is located, for each candidate reference line; wherein the driving task cost includes at least one of the lane change task cost or the U-turn task cost;

[0029] Based on the at least one cost, a driving cost of the candidate reference line is obtained.

[0030] In one embodiment, after controlling the vehicle to follow the target reference line indicated by the target reference line marker, the method further includes:

[0031] In the case of detecting a lane change failure, determining a lane before the vehicle changes lane and a lane change direction of the vehicle based on the target reference line;

[0032] Based on the lane change direction, determining a return reference line from a driving reference line of the lane before the lane change;

[0033] The vehicle is controlled to drive along the return reference line.

[0034] In a second aspect, the present application also provides a vehicle driving control device, comprising:

[0035] A determination module, for determining a plurality of driving reference lines based on map data and a current position of the vehicle;

[0036] A screening module, used for screening out adjacent reference lines from the plurality of driving reference lines;

[0037] A judgment module, configured to judge whether a lane change instruction is received, and determine a candidate reference line from the adjacent reference lines based on the judgment result; calculate a driving cost of each candidate reference line, and determine a target reference line from the candidate reference lines based on the driving cost;

[0038] The control module is used to control the vehicle to drive along the target reference line.

[0039] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method of each embodiment when executing the computer program.

[0040] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the method of each embodiment when executed by a processor.

[0041] In a fifth aspect, the present application also provides a computer program product, including a computer program, which implements the steps of the methods of each embodiment when executed by a processor.

[0042] The above-mentioned vehicle driving control method, device, computer equipment, computer-readable storage medium and computer program product can determine multiple driving reference lines based on map data and the current vehicle position, and then screen out adjacent reference lines from the multiple driving reference lines to determine whether a lane change instruction is received, and determine candidate reference lines from the adjacent reference lines based on the judgment result. Taking into account the complex scenario of lane change, the reference line screening in this complex scenario can be achieved, thereby calculating the driving cost of each candidate reference line, and based on the driving cost, determining the target reference line from the candidate reference lines. The optimal reference line can be selected in the complex scenario, and then the vehicle is controlled to follow the target reference line for driving, thereby improving the effect of vehicle driving control in complex scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1 A schematic flow chart of a vehicle driving control method in one embodiment;

[0045] Figure 2A schematic diagram of filtering the neighboring reference lines of the true class;

[0046] Figure 3 A schematic diagram of the reference line for filtering the bifurcation class;

[0047] Figure 4 A schematic diagram of filtering the neighboring reference lines of the original class;

[0048] Figure 5 This is a schematic diagram of the reference line after locking the bifurcation point;

[0049] Figure 6 Schematic diagram of lane change section;

[0050] Figure 7 Schematic diagram for determining a return reference line for a lane change failure;

[0051] Figure 8 It is a structural schematic diagram of a vehicle driving control system;

[0052] Fig. 9 A schematic flow chart of a vehicle driving control method in another embodiment;

[0053] Fig.10 It is a structural schematic diagram of a vehicle driving control device;

[0054] Fig.11 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0056] In one embodiment, Figure 1 As shown, a vehicle driving control method is provided. This embodiment uses the method applied to a vehicle as an example for illustration. The method includes the following steps:

[0057] Step 102: determining a plurality of driving reference lines based on the map data and the current position of the vehicle;

[0058] The current position of the vehicle may be the current coordinate position of the vehicle, and the map data may be data of a high-precision map;

[0059] Step 104: Filter out adjacent reference lines from the plurality of driving reference lines;

[0060] In this embodiment, by setting a preset offset threshold, two or more adjacent reference lines can be screened out from multiple driving reference lines.

[0061] The two or more neighboring reference lines specifically include: real neighboring reference lines, bifurcated neighboring reference lines, and original neighboring reference lines. The screening methods of these three types of neighboring reference lines will be described in the following embodiments.

[0062] Step 106: determine whether a lane change instruction is received, and determine a candidate reference line from the adjacent reference lines based on the determination result; calculate the driving cost of each candidate reference line, and determine a target reference line from the candidate reference lines based on the driving cost;

[0063] In this embodiment, lane change refers to a lane change actively initiated by the driver, or a lane change actively initiated by the driving system in an autonomous driving vehicle.

[0064] In this embodiment, different judgment results result in different selected candidate reference lines.

[0065] In this embodiment, based on the driving costs of the candidate reference lines, the candidate reference line with the minimum driving cost may be selected as the target reference line.

[0066] Step 108: Control the vehicle to drive along the target reference line.

[0067] In this embodiment, multiple driving reference lines can be currently determined based on map data and vehicle position, and then adjacent reference lines can be screened out from the multiple driving reference lines to determine whether a lane change instruction is received, and candidate reference lines can be determined from the adjacent reference lines based on the judgment result. Taking into account the complex scenario of lane change, the screening of reference lines in this complex scenario can be achieved, thereby calculating the driving cost of each candidate reference line, and determining the target reference line from the candidate reference lines based on the driving cost. The optimal reference line can be selected in the complex scenario, and then the vehicle can be controlled to follow the target reference line, thereby improving the effect of vehicle driving control in complex scenarios.

[0068] In the embodiment of the present application, the screening of adjacent reference lines is mainly to screen out adjacent reference lines such as real class adjacent reference lines (real_near_lane), forked class adjacent reference lines (split_near_lane) and original class adjacent reference lines (pre_near_lane) by comparing the lateral offsets of multiple driving reference lines. That is, the method of screening these three types of adjacent reference lines is:

[0069] In one of the embodiments, filtering out adjacent reference lines from the multiple driving reference lines includes: determining a lateral offset between each driving reference line in the multiple driving reference lines and a center line of the vehicle; and filtering out adjacent reference lines from the multiple driving reference lines based on the lateral offset, a preset offset threshold, and historical candidate reference lines.

[0070] The vehicle centerline refers to the centerline of the vehicle body. For the three types of adjacent reference lines, the preset offset thresholds are different. The lateral offset of the reference line refers to the lateral offset of the reference line relative to the vehicle centerline.

[0071] In the present application, when selecting the target reference line in each frame, the vehicle driving control method of the present application needs to be executed to obtain the target reference line. Therefore, the vehicle driving control method of the present application is executed cyclically. Specifically, the present application scheme can be described as:

[0072] Based on the map data and the current position of the vehicle, multiple driving reference lines are determined; the lateral offset between each driving reference line in the multiple driving reference lines and the center line of the vehicle is determined; based on the lateral offset, a preset offset threshold and the historical candidate reference lines, adjacent reference lines are screened out from the multiple driving reference lines; it is determined whether a lane change instruction is received, and a current candidate reference line is determined from the adjacent reference lines based on the determination result; the driving cost of each current candidate reference line is calculated, and based on the driving cost, a target reference line is determined from the current candidate reference lines; the vehicle is controlled to drive along the target reference line, and after the reference line selection cycle is reached (i.e., the next frame), the historical candidate reference line is updated based on the current candidate reference line, and the step of determining multiple driving reference lines based on the map data and the current position of the vehicle is returned to continue until the vehicle stops.

[0073] It can be seen that the historical candidate reference lines refer to all candidate reference lines used for driving cost calculation when the target reference line is selected in the previous frame.

[0074] In one embodiment, based on the lateral offset, a preset offset threshold, and historical candidate reference lines, selecting an adjacent reference line from the plurality of driving reference lines specifically includes:

[0075] Based on the lateral offset and a preset offset threshold, selecting a real adjacent reference line and a bifurcated adjacent reference line from a plurality of driving reference lines;

[0076] Based on the lateral offset, a preset offset threshold, and historical candidate reference lines, selecting an original class neighboring reference line from a plurality of driving reference lines;

[0077] The real class neighboring reference line, the fork class neighboring reference line and the original class neighboring reference line are collectively used as the neighboring reference lines.

[0078] In one embodiment, the preset offset threshold includes a real offset threshold, a bifurcation offset threshold, and an original offset threshold; based on the lateral offset, the preset offset threshold, and the historical candidate reference lines, selecting an adjacent reference line from the plurality of driving reference lines specifically includes:

[0079] For each driving reference line, when the first absolute value is less than the real offset threshold, the current driving reference line is used as the real class adjacent reference line; the first absolute value includes the absolute value of the lateral offset of the current driving reference line, or the absolute value of the difference between the lateral offset of the current driving reference line and the minimum lateral offset; the minimum lateral offset is the minimum value of the lateral offsets of the multiple driving reference lines; when there is a bifurcation point between the current driving reference line and other reference lines in the multiple reference lines, and the second absolute value is greater than the real offset threshold and less than the bifurcation offset threshold, the current driving reference line is used as the bifurcation class adjacent reference line; the second absolute value The value includes the absolute value of the lateral offset of the current driving reference line, or the absolute value of the difference between the lateral offset of the current driving reference line and the minimum lateral offset; when the current driving reference line matches the historical candidate reference line and the third absolute value is less than the original offset threshold, the current driving reference line is used as the original class neighboring reference line; the third absolute value includes the absolute value of the lateral offset of the current driving reference line, or the absolute value of the difference between the lateral offset of the current driving reference line and the minimum lateral offset; the real class neighboring reference line, the fork class neighboring reference line and the original class neighboring reference line are all used as the neighboring reference lines.

[0080] In this embodiment, screening the real class adjacent reference line needs to meet the following conditions: case A1, that is, the absolute value of the lateral offset of the current driving reference line is less than the real offset threshold, or case A2, that is, the absolute value of the difference between the lateral offset of the current driving reference line and the minimum lateral offset is less than the real offset threshold, or when both cases A1 and A2 are met, the current driving reference line is used as the real class adjacent reference line;

[0081] The minimum lateral offset is the minimum value of the lateral offsets of all driving reference lines. For example, if there are k driving reference lines, there are k corresponding lateral offsets. The minimum value of the k lateral offsets is determined to be the minimum lateral offset.

[0082] For example Figure 2In the example, the lateral offset 2 of Line 2 is 0.0, the lateral offset 3 of Line 3 is 0.0, the lateral offset 1 of Line 1 is -1.6, the minimum lateral offset is 0.0, and the lateral offset screening threshold of the real class adjacent reference line is set to 0.5 meters, so Line 2 and Line 3 are both real class adjacent reference lines. Beam identifies the lane, lane indicates the reference line, real_near_lane: 1 indicates that the number of real class adjacent reference lines is 1, and pre_near_lane: 1 indicates that the number of original class adjacent reference lines is 1.

[0083] In this embodiment, the screening of the forked adjacent reference lines needs to meet the following conditions: the current driving reference line exists within a preset distance in front of the vehicle or within a preset distance behind the vehicle, and there is a fork point between the current driving reference line and other reference lines in the multiple reference lines;

[0084] Among them, the scenario indicated by the presence of a bifurcation point between the current driving reference line and other reference lines among the multiple reference lines is: the current driving reference line and the other reference lines are bifurcated from the bifurcation point.

[0085] It is also necessary to satisfy condition B1, that is, the absolute value of the lateral offset of the current driving reference line is greater than the real offset threshold and less than the bifurcation offset threshold, or satisfy condition B2, that is, the absolute value of the difference between the lateral offset of the current driving reference line and the minimum lateral offset is greater than the real offset threshold and less than the bifurcation offset threshold, or satisfy conditions B1 and B2, and the current driving reference line is used as the bifurcation adjacent reference line;

[0086] For example Figure 3 In the example, the lateral offset 1 of Line 1 is -8.0, the lateral offset 2 of Line 2 is -4.0, the lateral offset 3 of Line 3 is -0.5, the lateral offset 3 of Line 4 is -0.9, the minimum lateral offset min is -0.5, and the lateral offset screening threshold of the fork-like adjacent reference line is set to 1.5 meters, then Line 4 is the fork-like adjacent reference line, and Line 3 is the real-like adjacent reference line. Beam identifies the lane, lane indicates the reference line, real_near_lane:1 indicates that the number of real-like adjacent reference lines is 1, pre_near_lane:1 indicates that the number of original-like adjacent reference lines is 1, and split_near_lane:1 indicates that the number of fork-like adjacent reference lines is 1.

[0087] In this embodiment, the current driving reference line matches the historical candidate reference line, that is, the identifier of the current driving reference line is the same as the identifier of the historical candidate reference line;

[0088] If condition C1 is satisfied, i.e., the absolute value of the lateral offset of the current driving reference line is less than the original offset threshold, or condition C2 is satisfied, i.e., the absolute value of the difference between the lateral offset of the current driving reference line and the minimum lateral offset is less than the original offset threshold, or conditions C1 and C2 are satisfied, the current driving reference line is used as the original adjacent reference line;

[0089] For example Figure 4 In the example, the lateral offset 1 of Line 1 is -5.43, the lateral offset 2 of Line 2 is -1.43, the lateral offset 3 of Line 3 is 1.45, and the minimum lateral offset min is -1.43. The lateral offset screening threshold of the original class adjacent reference line is set to 3.5 meters. When changing lanes or when the driver takes over, the threshold will be reduced to 0.5 meters to prevent driving discomfort caused by selecting the wrong reference line. Lines 2 and 3 are the original class adjacent reference lines. Beam identifies the lane, lane indicates the reference line, real_near_lane:1 indicates that the number of real class adjacent reference lines is 1, and pre_near_lane:1 indicates that the number of original class adjacent reference lines is 1.

[0090] It can be seen that the present application can preliminarily screen out adjacent reference lines through the above method, and thus select the optimal reference line from the adjacent reference lines in complex driving scenarios, thereby realizing the selection of the optimal reference line in complex driving scenarios, thereby improving the driving control of the vehicle in complex scenarios.

[0091] In one of the embodiments, the determining of the candidate reference line from the adjacent reference lines based on the judgment result includes: when the judgment result is that no lane change instruction is received, taking the adjacent reference line as the candidate reference line; when the judgment result is that a lane change instruction is received, determining the lane after lane change indicated in the lane change instruction; and screening out the adjacent reference line located in the lane after lane change from the adjacent reference lines as the candidate reference line.

[0092] In this embodiment, when the judgment result is that no lane change instruction is received, all adjacent reference lines are used as candidate reference lines; when the judgment result is that a lane change instruction is received, the lane change instruction can indicate a lane change from one lane to another lane, and the lane after the lane change indicated in the lane change instruction is determined, and the lane after the lane change is another lane, thereby determining the adjacent reference line located in the lane after the lane change among the adjacent reference lines, and using the adjacent reference line located in the lane after the lane change as a candidate reference line.

[0093] In this embodiment, lane change refers to a lane change initiated by the driver or the driving system in an autonomous vehicle. This type of lane change requires the use of a turn signal, which is a change from one lane to another. For the scenario of driving along different reference lines at a fork point, it does not belong to lane change and does not require the use of a turn signal. The following reference line fork scenario generally occurs before an intersection, when there are fewer lanes and more lanes, and does not fall into the category of lane change.

[0094] In this embodiment, the complex scenario of lane change is taken into consideration, and different candidate reference lines are selected based on the judgment result of whether a lane change instruction is received, thereby ultimately achieving the selection of the optimal reference line in the lane change scenario, thereby improving the driving control of the vehicle in complex scenarios.

[0095] In the embodiment of the present application, each reference line has a unique reference line identifier, and the vehicle identifies different reference lines through the reference line identifiers. The above-mentioned vehicle screens out adjacent reference lines from multiple driving reference lines, specifically including: the vehicle screens out the reference line identifier of the adjacent reference line from the reference line identifiers of the multiple driving reference lines, and then searches for the data corresponding to the reference line identifier of the adjacent reference line to obtain the adjacent reference line. Similarly, the above-mentioned determination of candidate reference lines from the adjacent reference lines is specifically: determining the reference line identifier of the candidate reference line from the reference line identifier of the adjacent reference line, thereby determining the candidate reference line; the above-mentioned determination of the target reference line from the candidate reference lines is specifically: determining the reference line identifier of the target reference line from the reference line identifier of the candidate reference line, thereby determining the target reference line.

[0096] The vehicle follows the reference line based on the reference line mark during driving. If the reference line is bifurcated, the reference line mark after the bifurcation point needs to be determined to prevent vehicle driving errors. Specifically:

[0097] One possible situation is that after determining the target reference line from the candidate reference lines, the method further includes: determining whether the target reference line has a fork; if the target reference line has a fork, determining a reference line identifier of the target reference line after the bifurcation point; accordingly, controlling the vehicle to follow the target reference line includes: controlling the vehicle to follow the reference line indicated by the reference line identifier.

[0098] The vehicle determines whether the target reference line has a fork. If the target reference line has no fork, the vehicle is controlled to directly follow the target reference line.

[0099] If the target reference line is forked, the reference line identifier of the target reference line after the fork point is determined. In this embodiment, based on the reference line identifier after the fork point, a reference line from a distance behind the vehicle (for example, 50 meters behind the vehicle) to a distance in front of the vehicle (for example, 200 meters in front of the vehicle) can be found. The distance of this reference line includes a distance from the vehicle position to a distance before the fork point and a distance from the vehicle position to a distance after the fork point. Therefore, the vehicle determines a unique reference line based on the reference line identifier after the fork point, and the vehicle follows the unique reference line to avoid the vehicle being unable to lock the reference line after the fork point.

[0100] like Figure 5 As shown, if the target reference line 50 meters in front of the vehicle is bifurcated, the reference line identifier (split-lock-lane-id) after the bifurcation point is locked. Based on the reference line identifier after the bifurcation point, a reference line from 50 meters behind the vehicle to 200 meters in front of the vehicle can be found, namely, the target reference line, so as to control the vehicle to follow the target reference line. In the process of following the target reference line, after the vehicle drives to the bifurcation point, the target reference line can be locked based on the reference line identifier after the bifurcation point to follow the driving, so as to avoid driving to the left or right, which may cause driving errors.

[0101] Another possible situation is that after determining the candidate reference line from the neighboring reference lines based on the judgment result and before calculating the driving cost of each candidate reference line, the method further includes: for each candidate reference line, determining whether the current candidate reference line has a fork; when the current candidate reference line has a fork, determining the reference line identifier of the current candidate reference line after the bifurcation point; accordingly, controlling the vehicle to follow the target reference line includes: determining the target reference line identifier of the target reference line after the bifurcation point, and controlling the vehicle to follow the reference line indicated by the target reference line identifier.

[0102] The vehicle can also determine whether there is a bifurcation for each candidate reference line. If the current candidate reference line has a bifurcation, the reference line identifier of the current candidate reference line after the bifurcation point is determined, and after determining the target reference line, if the target reference line has a bifurcation, the target reference line identifier of the target reference line is determined from the reference line identifiers of the candidate reference lines. When the vehicle follows the target reference line based on the target reference line identifier, if it reaches the bifurcation point, it continues to lock on to the unique target reference line for following driving based on the target reference line identifier.

[0103] For example, 8 candidate reference lines are determined from 10 adjacent reference lines, of which 3 candidate reference lines have bifurcations, that is, for these 3 candidate reference lines, the reference line identifiers after the bifurcation points are locked.

[0104] In this embodiment, the complex driving scenario of bifurcation of the reference line is taken into consideration. By determining the identifier of the reference line after the bifurcation point, it is possible to ensure that the selection of the reference line does not jump, so that in the complex driving scenario of bifurcation of the reference line, the vehicle can be controlled to follow the selected target reference line, further improving the effect of vehicle driving control in complex scenarios. It also improves the stability of the planning algorithm.

[0105] The present application can be applied to the scenario where the reference line forks or merges. There is a special treatment to lock the reference line mark in advance at the place where the reference line forks or merges. This treatment measure can better ensure the smoothness of driving under complex urban road conditions.

[0106] In one embodiment, the calculation of the driving cost of each candidate reference line includes: determining a driving task cost, a smoothness cost, a length cost, a navigation direction cost, an offset cost, a distance cost between the current reference line and the lane boundary line, a lane width cost of the lane where the current reference line is located, or at least one of the lane type costs of the lane where the current reference line is located, for each candidate reference line; wherein the driving task cost includes at least one of a lane change task cost or a U-turn task cost; and based on the at least one cost, obtaining the driving cost of the candidate reference line.

[0107] The following are the calculation methods of these costs:

[0108] a. Driving mission cost.

[0109] The driving task cost mainly includes at least one of the lane change task cost or the U-turn task cost. In urban scenarios, if the starting distance of the lane change task is too far, this cost will not be considered. Otherwise, the cost will be calculated by finding the maximum lane change interval.

[0110] as follows Figure 6 ,The larger lane changing interval is ,the longer longitudinal distance the vehicle can travel, which is considered to be safe and reliable, so the larger lane changing interval is, the smaller the corresponding lane changing task cost.

[0111] The lane change task cost is determined by the maximum lane change interval length, the lane change driving distance, and the number of lane changes required to reach the target lane. The lane change driving distance is the longitudinal distance traveled by the vehicle within the preset time threshold. The specific formula is:

[0112] .

[0113] b. Smoothness cost;

[0114] The smoothness cost is related to the relative rate of change of the orientation angle of the points on the reference line. The smoother the reference line, the higher the driving comfort and the lower the smoothness cost.

[0115] When calculating the smoothness cost, we must first ensure that the distance between every two reference points in the reference line is greater than 0.5 meters, otherwise the middle reference point needs to be deleted. This is because the orientation angle change rate calculated from two reference points that are too close is unreliable.

[0116] The smoothness cost is the sum of the orientation angle change rates of all points on the reference line and 20 times the maximum orientation angle change rate. The specific formula is:

[0117] ;

[0118] Among them, cost_smooth is the smoothness cost, kappa is the orientation angle change rate between every two reference points, and kappa_max is the maximum orientation angle change rate on the reference line.

[0119] c. Length cost;

[0120] The length cost is calculated by the remaining length of the reference line and the remaining path length of the navigation. The longer the reference line is, the more distance can be traveled, and the smaller the length cost will be. The specific formula is:

[0121] ;

[0122] Among them, cost_length is the length cost, refline_length refers to the remaining length of the reference line, and PassageLength refers to the remaining length of the navigation route.

[0123] d. Lane width cost of the lane where the current reference line is located;

[0124] The lane width cost is related to the length of the narrow lane. Lanes with a width less than 3 meters are considered narrow lanes. When traversing all reference lines, the length of the narrow lane where each reference line is located is recorded to calculate the lane width cost. The specific formula is:

[0125] ; where narrow_lane_width is the length of the narrow lane, k is the preset value, currently 255.0, and cost_lane_width is the lane width cost.

[0126] e. The distance cost between the current reference line and the lane boundary line;

[0127] When lane lines merge or diverge, the center line of the lane often intersects with the lane lines on both sides. This cost is mainly to ensure that the vehicle does not cross the lane line as much as possible in this scenario. As long as the distance between the reference point on the reference line and the left or right boundary of the lane is less than the preset distance value (for example, 0.5m), it is considered that there is a cross-line situation, and the distance cost is set to the preset value.

[0128] f. Lane type cost of the lane where the current reference line is located;

[0129] The lane type cost is related to the lane type, and the purpose is to avoid vehicles driving on bus lanes or variable lanes as much as possible. The type of lane within a preset distance of the vehicle (for example, 50 meters behind the vehicle and 300 meters in front of the vehicle) is detected. If the lane type is a bus stop, the first preset value is added to the initial lane type cost to obtain the lane type cost, and the first preset value can be 10; if the lane type is a bus lane, the second preset value is added to the initial lane type cost to obtain the lane type cost, and the second preset value can be 1; if the lane type is a variable lane, the third preset value is added to the lane type cost to obtain the lane type cost, and the third preset value can be 0.5.

[0130] The initial lane type cost is pre-set. If the lane type does not belong to a bus stop, bus lane, or variable lane, the lane type cost is the initial lane type cost.

[0131] g. Navigation direction cost;

[0132] The navigation direction cost is related to the navigation path. When the distance is within x meters from the intersection, if there is a recommended lane, the reference line cost in the non-recommended lane increases by the fourth preset value, where x is the preset value;

[0133] If there is no recommended lane, the cost is calculated based on the navigation direction. If there is a turning task, when turning right, and the right turn lane is on the right, the closer the right turn lane is to the right, the smaller the cost of the reference line; the same is true for turning left, the left turn lane is on the left, the closer the left turn lane is to the left, the smaller the cost of the reference line. When there is no turning task, if the reference line can go straight and turn, the cost increases by the fifth preset value. If it cannot be executed and can only turn, the cost increases by the sixth preset value.

[0134] h, offset cost;

[0135] The offset cost is related to the lateral distance between the reference line and the center line of the vehicle. It mainly plays a role in the left and right lane line selection. For the left lane, the offset cost is smaller when the reference line is closer to the right relative to the vehicle position; for the right lane, the offset cost is smaller when the reference line is closer to the left relative to the vehicle position.

[0136] Based on the calculated at least one cost and the coefficient corresponding to each cost, the driving cost of the candidate reference line is obtained, and the reference line with the lowest cost is finally used as the target reference line.

[0137] It can be seen that this application specifically records the method of calculating at least one of the above costs, so that based on at least one cost, the driving cost of the candidate reference line is obtained, and the reference line with the lowest cost is selected as the target reference line based on the driving cost, so that the selection of the optimal reference line can be achieved, so that the optimal reference line can be selected for complex driving scenes, and the effect of vehicle driving control in complex scenes is improved. At the same time, the driving cost of the reference line is calculated from eight dimensions, and the reference line with the lowest cost is finally selected, so the rationality of the algorithm is improved.

[0138] In one of the embodiments, after the vehicle is controlled to follow the target reference line indicated by the target reference line identifier, the method further includes: in case a lane change failure is detected, determining a front lane for the vehicle to change lane and a lane change direction for the vehicle based on the target reference line; based on the lane change direction, determining a return reference line from the driving reference line of the front lane for lane change; and controlling the vehicle to follow the return reference line.

[0139] In this embodiment, the lane change process may fail and the vehicle may return to the original lane. The return reference line needs to be determined based on the position of the target reference line. If the vehicle changes lanes to the left, the leftmost reference line in the original lane is selected as the return reference line; if the vehicle changes lanes to the right, the rightmost reference line in the original lane is selected as the return reference line. Therefore, after the lane change fails, the vehicle follows the return reference line.

[0140] like Figure 7 As shown, the vehicle needs to change lanes to the left, the target reference line selects the left reference line, and the return reference line selects the leftmost lane in the vehicle lane as the return reference line.

[0141] It can be seen that after the lane change fails, the present application can determine the return reference line and drive along the return reference line, taking into account the driving scenario of lane change failure and improving the scenario adaptability of the solution.

[0142] Reference Figure 8 The vehicle driving control of the present application specifically includes a perception module, a positioning module, a map module, a prediction module, a routing module, a decision and planning module, and a control module.

[0143] Among them, the perception module determines the environmental information around the intelligent driving car, including but not limited to the surrounding obstacle information (such as vehicles, pedestrians, cones, non-motor vehicles, etc.), and can determine traffic lights, traffic signs, lane information, etc. in combination with positioning information and map information; the positioning module determines the current position of the intelligent driving car and manages the travel data of the intelligent car; the map module stores map information, including but not limited to road shape, lane information, merging and diverging information, intersection information, pedestrian crossing information, speed bumps, etc.; the routing module generates global planning path information based on the positioning module and the map module, as well as the tasks of the intelligent driving car; the prediction module generates the predicted trajectory of the obstacle based on the obstacle information in the perception module and the map information in the map module; the decision-making and planning module generates a trajectory that meets the vehicle dynamics constraints, is safe, and comfortable based on the obstacle prediction trajectory of the prediction module, the self-vehicle positioning of the positioning module, and the travel tasks of the intelligent driving car of the routing module; the control module outputs the corresponding steering wheel angle, driving or braking torque according to the trajectory of the decision-making and planning module to control the trajectory of the vehicle.

[0144] The vehicle driving control in this application is performed by the decision planning module and the control module. When the decision planning module receives the global path information from the routing module, it will generate one or more driving reference lines according to the vehicle position information sent by the positioning module. Subsequent path planning will depend on the driving reference lines generated here. In the reference line selection process, the decision planning module uses the above-mentioned vehicle driving control method to select a target reference line from multiple driving reference lines, and then the control module controls the vehicle to follow the driving based on the target reference line selected by the decision planning module.

[0145] Specifically, refer to Fig. 9 , the vehicle driving control method of the present application is described:

[0146] Based on the map data and the current position of the vehicle, the reference lines are updated and integrated. After multiple driving reference lines are determined, a preliminary screening is first performed on all upstream inputs, that is, adjacent reference lines are screened out from multiple driving reference lines. The specific method of screening out adjacent reference lines is: based on the lateral offset of the reference line and the preset offset threshold, the real class adjacent reference lines and the fork class adjacent reference lines are screened out from multiple driving reference lines based on the lateral offset of the reference line, the preset offset threshold and the historical candidate reference lines. The original class adjacent reference lines are screened out from multiple driving reference lines, and the real class adjacent reference lines, the fork class adjacent reference lines and the original class adjacent reference lines are integrated to obtain the above-mentioned adjacent reference lines. Then determine whether there is a lane change;

[0147] Case 1: If there is no lane change and the vehicle is going straight, the driving cost of each adjacent reference line is calculated, sorted and compared, and the adjacent reference line with the smallest cost is determined as the target reference line.

[0148] Driving cost of adjacent reference line = driving task cost * coefficient 1 + smoothness cost * coefficient 2 + length cost * coefficient 3 + navigation direction cost * coefficient 4 + offset cost * coefficient 5 + distance cost between current reference line and lane boundary line * coefficient 6 + lane width cost * coefficient 7 + lane type cost * coefficient 8; among which, coefficient 1 to coefficient 8 are all preset coefficients.

[0149] Determine whether the target reference line has a fork. If not, the vehicle locks onto the mark of the target reference line so that the vehicle always follows the target reference line.

[0150] If there is a fork, for example, the target reference line in front of the vehicle forks or merges, it is necessary to lock the reference line identifier of the target reference line after the fork, so as to determine a reference line from a distance behind the vehicle to a distance in front of the vehicle based on the reference line identifier, so that the reference line can be filtered out all the time for following driving to ensure that the line selection does not jump.

[0151] Once the target reference line is determined, there are no major requirements for the selection of the left reference line or the right reference line because it does not involve lane changing.

[0152] Case 2: If there is a lane change, the lane after the lane change indicated in the lane change instruction is determined, and the adjacent reference lines located in the lane after the lane change are selected from the adjacent reference lines as candidate reference lines. The driving cost of each candidate reference line is calculated in turn, and the candidate reference line with the smallest driving cost is output as the target reference line.

[0153] During the lane change process, it is necessary to ensure that the selected target reference line does not jump, that is, the reference line identifier of the target reference line of the lane after the lane change is locked, and then the target reference line is always searched for and followed. Specifically: determine whether the target reference line has a fork. If there is no fork, the vehicle locks the identifier of the target reference line, so that the vehicle always follows the target reference line; if there is a fork, such as the target reference line forks or merges in front of the vehicle, it is necessary to lock the reference line identifier of the target reference line after the fork, so as to determine a reference line from a distance behind the vehicle to a distance in front of the vehicle based on the reference line identifier, so that the reference line can be filtered out for following driving to ensure that the line selection does not jump.

[0154] At this time, the return reference line is still the reference line in the own lane, which is inferred from the target reference line on the lane-changing side. There is no requirement for the reference line selection of the adjacent lane on the non-lane-changing side.

[0155] The final output return reference line, the left reference line and the right reference line are given to the downstream for smoothing and control following.

[0156] This application obtains adjacent reference lines through preliminary screening, and then further screens adjacent reference lines to obtain candidate reference lines by judging whether a lane change command is received, and calculates the cost of each reference line to select the optimal reference line, thereby improving the rationality and intelligence of autonomous driving planning and line selection. It can also be used to select the optimal reference line for follow-up driving in complex scenarios such as lane change, improving the effect of vehicle driving control in complex scenarios.

[0157] By locking the reference line marker, it is ensured that the selected reference line does not jump. The target reference line can be locked for follow-up driving in complex scenarios such as bifurcations and confluences, which improves the stability of planning and the smoothness of vehicle driving, and further enhances the effect of vehicle driving control in complex scenarios.

[0158] The driving cost of the reference line is calculated from eight latitudes and finally the reference line with the lowest cost is selected, which improves the rationality of the algorithm.

[0159] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0160] Based on the same inventive concept, the embodiment of the present application also provides a vehicle driving control method device for implementing the vehicle driving control method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more vehicle driving control method device embodiments provided below can refer to the above limitations on the vehicle driving control method, and will not be repeated here.

[0161] In an exemplary embodiment, Fig.10 As shown, a vehicle driving control method device 100 is provided, comprising:

[0162] A determination module 1001 is used to determine a plurality of driving reference lines based on map data and a current vehicle position;

[0163] A screening module 1002, for screening out adjacent reference lines from a plurality of driving reference lines;

[0164] The judgment module 1003 is used to judge whether a lane change instruction is received, and determine a candidate reference line from the adjacent reference lines based on the judgment result; calculate the driving cost of each candidate reference line, and determine the target reference line from the candidate reference lines based on the driving cost;

[0165] The control module 1004 is used to control the vehicle to follow the target reference line.

[0166] In one embodiment, the screening module 1002 is specifically configured to:

[0167] Determining a lateral offset between each of a plurality of driving reference lines and a centerline of the vehicle;

[0168] Based on the lateral offset, a preset offset threshold, and historical candidate reference lines, an adjacent reference line is screened out from multiple driving reference lines.

[0169] In one of the embodiments, the preset offset thresholds include a real offset threshold, a forked offset threshold, and an original offset threshold;

[0170] When the screening module 1002 screens out adjacent reference lines from a plurality of driving reference lines based on the lateral offset, the preset offset threshold, and the historical candidate reference lines, it is specifically used to:

[0171] For each driving reference line, when the first absolute value is less than the real offset threshold, the current driving reference line is used as the real class adjacent reference line; the first absolute value includes the absolute value of the lateral offset of the current driving reference line, or the absolute value of the difference between the lateral offset of the current driving reference line and the minimum lateral offset; the minimum lateral offset is the minimum value of the lateral offsets of the multiple driving reference lines;

[0172] When there is a bifurcation point between the current driving reference line and other reference lines in the multiple reference lines, and the second absolute value is greater than the true offset threshold and less than the bifurcation offset threshold, the current driving reference line is used as a bifurcation-type adjacent reference line; the second absolute value includes an absolute value of a lateral offset of the current driving reference line, or an absolute value of a difference between the lateral offset of the current driving reference line and a minimum lateral offset;

[0173] When the current driving reference line matches the historical candidate reference line and the third absolute value is less than the original offset threshold, the current driving reference line is used as the original class neighboring reference line; the third absolute value includes the absolute value of the lateral offset of the current driving reference line, or the absolute value of the difference between the lateral offset of the current driving reference line and the minimum lateral offset;

[0174] The real class neighboring reference lines, the forked class neighboring reference lines, and the original class neighboring reference lines are all used as neighboring reference lines.

[0175] In one embodiment, the determination module 1003 is specifically configured to:

[0176] When the result of the judgment is that no lane change instruction is received, the adjacent reference line is used as a candidate reference line;

[0177] When the result of the determination is that a lane change instruction is received, a lane after the lane change indicated in the lane change instruction is determined; and an adjacent reference line located in the lane after the lane change is selected from adjacent reference lines as a candidate reference line.

[0178] In one of the embodiments, the device further comprises a fork determination module;

[0179] After the determination module 1003 determines the target reference line from the candidate reference lines;

[0180] A fork judgment module is used to judge whether the target reference line has a fork;

[0181] In the case where the target reference line is bifurcated, a reference line of the target reference line after the bifurcation point is determined;

[0182] Accordingly, controlling the vehicle to follow the target reference line includes:

[0183] The vehicle is controlled to drive along the reference line indicated by the reference line marker.

[0184] In one embodiment, when calculating the driving cost of each candidate reference line, the determination module 1003 is specifically used to:

[0185] Determine at least one of the driving task cost, smoothness cost, length cost, navigation direction cost, offset cost, distance cost between the current reference line and the lane boundary line, lane width cost of the lane where the current reference line is located, or lane type cost of the lane where the current reference line is located, for each candidate reference line; wherein the driving task cost includes at least one of the lane change task cost or the U-turn task cost;

[0186] Based on at least one cost, a driving cost of the candidate reference line is obtained.

[0187] In one of the embodiments, the apparatus further comprises a return reference line determination module;

[0188] After the control module controls the vehicle to drive along the target reference line indicated by the target reference line identifier, the return reference line determination module is used to: determine the front lane of the vehicle and the lane changing direction of the vehicle based on the target reference line when a lane change failure is detected; determine the return reference line from the driving reference line of the front lane based on the lane changing direction; and control the vehicle to drive along the return reference line.

[0189] Each module in the above vehicle driving control device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0190] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Fig.11 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a vehicle driving control device method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0191] Those skilled in the art will understand that Fig.11 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0192] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0193] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0194] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0195] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0196] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0197] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0198] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A vehicle driving control method, It is characterized in that The method comprises: Determine multiple driving reference lines based on map data and the current vehicle position; Filtering adjacent reference lines from the plurality of driving reference lines; Determine whether a lane change instruction is received, and determine a candidate reference line from the adjacent reference lines based on the determination result; calculate a driving cost of each candidate reference line, and determine a target reference line from the candidate reference lines based on the driving cost; The vehicle is controlled to drive along the target reference line.

2. The method according to claim 1, It is characterized in that The step of selecting adjacent reference lines from the plurality of driving reference lines comprises: Determining a lateral offset between each of the plurality of driving reference lines and a center line of the vehicle; Based on the lateral offset, a preset offset threshold, and historical candidate reference lines, an adjacent reference line is screened out from the plurality of driving reference lines.

3. The method according to claim 2, It is characterized in that The preset offset thresholds include a real offset threshold, a forked offset threshold and an original offset threshold; The step of selecting an adjacent reference line from the plurality of driving reference lines based on the lateral offset, a preset offset threshold, and historical candidate reference lines includes: For each driving reference line, when the first absolute value is less than the real offset threshold, the current driving reference line is used as the real class adjacent reference line; the first absolute value includes the absolute value of the lateral offset of the current driving reference line, or the absolute value of the difference between the lateral offset of the current driving reference line and the minimum lateral offset; the minimum lateral offset is the minimum value of the lateral offsets of the multiple driving reference lines; When there is a bifurcation point between the current driving reference line and other reference lines in the multiple reference lines, and the second absolute value is greater than the real offset threshold and less than the bifurcation offset threshold, the current driving reference line is used as a bifurcation-type adjacent reference line; the second absolute value includes the absolute value of the lateral offset of the current driving reference line, or the absolute value of the difference between the lateral offset of the current driving reference line and the minimum lateral offset; When the current driving reference line matches the historical candidate reference line and the third absolute value is less than the original offset threshold, the current driving reference line is used as the original class neighboring reference line; the third absolute value includes the absolute value of the lateral offset of the current driving reference line, or the absolute value of the difference between the lateral offset of the current driving reference line and the minimum lateral offset; The real class neighboring reference line, the forked class neighboring reference line and the original class neighboring reference line are all used as the neighboring reference lines.

4. The method according to any one of claims 1 to 3, It is characterized in that The step of determining a candidate reference line from the adjacent reference lines based on the judgment result includes: When the result of the judgment is that no lane change instruction is received, taking the adjacent reference line as a candidate reference line; When the judgment result is that a lane change instruction is received, the lane after the lane change indicated in the lane change instruction is determined; and an adjacent reference line located in the lane after the lane change is selected from the adjacent reference lines as the candidate reference line.

5. The method according to any one of claims 1 to 3, It is characterized in that After determining the target reference line from the candidate reference lines, the method further includes: Determining whether the target reference line has a fork; In the case where the target reference line is bifurcated, a reference line identifier of the target reference line after the bifurcation point is determined; Accordingly, controlling the vehicle to drive along the target reference line includes: The vehicle is controlled to drive along the reference line indicated by the reference line marker.

6. The method according to any one of claims 1 to 3, It is characterized in that The calculating the driving cost of each candidate reference line includes: Determine at least one of the driving task cost, smoothness cost, length cost, navigation direction cost, offset cost, distance cost between the current reference line and the lane boundary line, lane width cost of the lane where the current reference line is located, or lane type cost of the lane where the current reference line is located, for each candidate reference line; wherein the driving task cost includes at least one of the lane change task cost or the U-turn task cost; Based on the at least one cost, a driving cost of the candidate reference line is obtained.

7. The method according to any one of claims 1 to 3, It is characterized in that After controlling the vehicle to drive along the target reference line indicated by the target reference line identifier, the method further includes: In the case of detecting a lane change failure, determining a lane before the vehicle changes lane and a lane change direction of the vehicle based on the target reference line; Based on the lane change direction, determining a return reference line from a driving reference line of the lane before the lane change; The vehicle is controlled to drive along the return reference line.

8. A vehicle driving control device, It is characterized in that The device comprises: A determination module, for determining a plurality of driving reference lines based on map data and a current position of the vehicle; A screening module, used for screening out adjacent reference lines from the plurality of driving reference lines; A judgment module, configured to judge whether a lane change instruction is received, and determine a candidate reference line from the adjacent reference lines based on the judgment result; calculate a driving cost of each candidate reference line, and determine a target reference line from the candidate reference lines based on the driving cost; The control module is used to control the vehicle to drive along the target reference line.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program. It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

11. A computer program product comprising a computer program, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.