Automatic driving planning decision-making method and device

By obtaining the information of bicycle trajectory points and lane line in the autonomous driving system, constructing the predicted line equation and calculating the confidence level, and determining the lane line follow-up strategy, it solves the unstable and unsafe driving of autonomous vehicles in complex urban road environments. The problem has achieved a stable and safe driving state.

CN118991826AActive Publication Date: 2024-11-22GAC AION NEW ENERGY AUTOMOBILE CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202411229826.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-03
Publication Date
2024-11-22
Estimated Expiration
2044-09-03

AI Technical Summary

Technical Problem

In complex urban road environments, it is difficult for autonomous vehicles to maintain a stable and safe driving state under irregular conditions such as lane forks and confluences, resulting in problems such as large adjustment of the steering wheel and driving direction that does not meet the driver's expectations.

Method used

By obtaining the information of bicycle track points and lane line, constructing predictive line equations, calculating lane line confidence levels, and determining lane line follow-up strategies, we optimize the vehicle's path planning and control to ensure stable driving in complex environments.

Benefits of technology

It effectively avoids the problem of large adjustment of the steering wheel and the driving direction not meeting expectations, ensures that autonomous vehicles maintain a stable and safe driving state in complex and changeable urban road environments, improves functional stability and reduces the number of times drivers take over.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118991826A_ABST
    Figure CN118991826A_ABST
Patent Text Reader

Abstract

The invention provides an automatic driving planning decision-making method and device. The method comprises the following steps: acquiring an own vehicle track point of a target vehicle in a preset time period based on a geodetic coordinate system; constructing a prediction line equation based on the self-vehicle track points; acquiring a left and right lane line equation of a current driving lane of the target vehicle, a current self-vehicle speed and a current lane width under a self-vehicle coordinate system through a sensing system of the target vehicle; determining a lane line confidence level according to the prediction line equation, the left and right lane line equation, the current own vehicle speed and the current lane width; and determining a lane line following strategy according to the lane line confidence level. According to the method and the device, the control strategy can be determined by comparing the left and right lane lines of the lane with the predicted trajectory of the vehicle, the problems that a steering wheel is greatly adjusted and the driving direction does not conform to the expectation of a driver are avoided, and the automatic driving vehicle can still keep a stable and safe driving state in a complex and changeable urban road environment.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and more specifically, to an autonomous driving planning and decision-making method and device. Background Art

[0002] Against the backdrop of the rapid development of autonomous driving technology, vehicle path planning and tracking has become one of the core technologies for achieving safe and efficient autonomous driving. Traditional autonomous driving systems often use the center line of the lane as a reference path for precise following driving, based on the premise that the lane lines on both sides of the main lane are clear and regular. However, in practice, it has been found that when autonomous driving vehicles enter complex traffic environments such as urban roads, there are often irregular lane lines such as lane bifurcations and confluences. In this case, the result of following the center line of the lane is not ideal, and there will be problems such as sudden steering and driving direction not meeting the driver's expectations. This not only affects the passengers' riding experience, but may also pose a potential threat to driving safety. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide an autonomous driving planning and decision-making method and device, which can determine the control strategy by comparing the left and right lane lines of the self-lane with the predicted trajectory of the self-vehicle, avoid problems such as large steering wheel adjustments and driving direction not meeting the driver's expectations, and ensure that the autonomous driving vehicle can still maintain a stable and safe driving state in a complex and changeable urban road environment.

[0004] The first aspect of the present application provides an autonomous driving planning and decision-making method, comprising:

[0005] Obtain the target vehicle's own vehicle trajectory points within a preset time period based on the geodetic coordinate system;

[0006] Constructing a prediction line equation based on the ego vehicle trajectory points;

[0007] Obtaining, through the perception system of the target vehicle, left and right lane line equations of the current lane of the target vehicle, the current speed of the vehicle, and the current lane width in the own-vehicle coordinate system;

[0008] Determining a lane line confidence level according to the predicted line equation, the left and right lane line equations, the current vehicle speed, and the current lane width;

[0009] A lane line following strategy is determined according to the lane line confidence level.

[0010] In the above implementation process, the method can determine the control strategy by comparing the left and right lane lines of the self-lane with the predicted trajectory of the self-vehicle, avoiding problems such as large steering wheel adjustments and driving direction that does not meet the driver's expectations, ensuring that the autonomous driving vehicle can still maintain a stable and safe driving state in the complex and changeable urban road environment.

[0011] Furthermore, constructing a prediction line equation based on the vehicle trajectory points includes:

[0012] Constructing a self-vehicle coordinate system based on the target vehicle;

[0013] Convert the vehicle trajectory points into a coordinate system to obtain the vehicle trajectory points in the vehicle coordinate system;

[0014] A cubic polynomial fitting is performed based on the vehicle trajectory points to obtain a prediction line equation.

[0015] Furthermore, after constructing the prediction line equation based on the vehicle trajectory points, the method further includes:

[0016] Determining whether the LCC centering function of the target vehicle is in an activated state within the preset time period;

[0017] If so, it is determined that the vehicle trajectory point is a valid trajectory, and it is determined that the predicted line equation can be used to predict the future driving trajectory of the vehicle, and the perception system of the target vehicle is executed to obtain the left and right lane line equations of the current lane of the target vehicle in the vehicle coordinate system, the current vehicle speed and the current lane width.

[0018] Further, the determining of the lane line confidence level according to the predicted line equation, the left and right lane line equations, the current vehicle speed and the current lane width includes:

[0019] Calculating a current preview distance based on a preset preview time and the current vehicle speed;

[0020] Calculating a distance threshold according to the current lane width and a preset offset;

[0021] Calculate the proportion of coordinate points whose lateral distance between the predicted line and the lane line is less than the distance threshold according to the left and right lane line equations, the predicted line equation, the current preview distance, and the distance threshold;

[0022] The lane line confidence level is determined based on the coordinate point ratio and a preset ratio threshold.

[0023] Further, the determining of the lane line following strategy according to the lane line confidence level includes:

[0024] When the lane line confidence level only includes the left lane line confidence level, the lane line following strategy is determined to be the left lane line following strategy;

[0025] When the lane line confidence level only includes the right lane line confidence level, the lane line following strategy is determined to be the right lane line following strategy;

[0026] When the lane line confidence level includes a left lane line confidence level and a right lane line confidence level, determining whether the left lane line confidence level and the right lane line confidence level are equal;

[0027] If yes, the lane line following strategy is determined to be a double-line following strategy.

[0028] Furthermore, the method further comprises:

[0029] When the left lane line confidence level is not equal to the right lane line confidence level, and the left lane line confidence level is greater than the right lane line confidence level, then determining that the lane line following strategy is the left lane line following strategy;

[0030] When the left lane line confidence level is not equal to the right lane line confidence level, and the left lane line confidence level is not greater than the right lane line confidence level, the lane line following strategy is determined to be the right lane line following strategy.

[0031] Further, after determining the lane line following strategy according to the lane line confidence level, it also includes:

[0032] Based on the lane line following strategy and the left and right lane line equations, calculating a planned target path equation;

[0033] The target vehicle is controlled to perform automatic driving based on the planned target path.

[0034] A second aspect of the present application provides an autonomous driving planning and decision-making device, the autonomous driving planning and decision-making device comprising:

[0035] A first acquisition unit, used for acquiring a target vehicle's own vehicle trajectory point within a preset time period based on a geodetic coordinate system;

[0036] A construction unit, used for constructing a prediction line equation based on the vehicle trajectory points;

[0037] A second acquisition unit is used to acquire, through the perception system of the target vehicle, left and right lane line equations of the current lane of the target vehicle, the current speed of the vehicle, and the current lane width in the vehicle coordinate system;

[0038] A confidence determination unit, configured to determine a lane line confidence level according to the predicted line equation, the left and right lane line equations, the current vehicle speed, and the current lane width;

[0039] A strategy determination unit is used to determine a lane line following strategy according to the lane line confidence level.

[0040] Furthermore, the construction unit comprises:

[0041] A construction subunit, used for constructing a self-vehicle coordinate system based on the target vehicle;

[0042] A conversion subunit, used for performing coordinate system conversion on the ego-vehicle trajectory point to obtain the vehicle trajectory point in the ego-vehicle coordinate system;

[0043] The fitting subunit is used to perform cubic polynomial fitting based on the vehicle trajectory points to obtain a prediction line equation.

[0044] Furthermore, the autonomous driving planning and decision-making device further includes:

[0045] a judgment unit, configured to judge whether the LCC centering function of the target vehicle is in an activated state within the preset time period after the construction unit constructs the prediction line equation based on the vehicle trajectory points;

[0046] The validity determination unit is used to determine that the self-vehicle trajectory point is a valid trajectory when the LCC centering function of the target vehicle is activated within the preset time period, and to determine that the predicted line equation can be used to predict the future driving trajectory of the self-vehicle, and to trigger the second acquisition unit to execute the operation of acquiring the left and right lane line equations of the current driving lane of the target vehicle, the current self-vehicle speed and the current lane width in the self-vehicle coordinate system through the perception system of the target vehicle.

[0047] Furthermore, the confidence determination unit includes:

[0048] A calculation subunit, configured to calculate a current preview distance based on a preset preview time and the current vehicle speed;

[0049] The calculation subunit is further used to calculate a distance threshold according to the current lane width and a preset offset;

[0050] The calculation subunit is further used to calculate the proportion of coordinate points whose lateral distance between the predicted line and the lane line is less than the distance threshold according to the left and right lane line equations, the predicted line equation, the current preview distance and the distance threshold;

[0051] The first determination subunit is used to determine the lane line confidence level according to the coordinate point ratio and a preset ratio threshold.

[0052] Furthermore, the strategy determination unit includes:

[0053] A second determining subunit, configured to determine that the lane line following strategy is a left lane line following strategy when the lane line confidence level includes only the left lane line confidence level;

[0054] The second determining subunit is further configured to determine that the lane line following strategy is a right lane line following strategy when the lane line confidence level only includes the right lane line confidence level;

[0055] a judgment subunit, configured to judge whether the left lane line confidence level and the right lane line confidence level are equal when the lane line confidence level includes the left lane line confidence level and the right lane line confidence level;

[0056] The second determining subunit is further configured to determine that the lane line following strategy is a dual-line following strategy when the left lane line confidence level is equal to the right lane line confidence level.

[0057] Further, the second determination subunit is further configured to determine that the lane line following strategy is a left lane line following strategy when the left lane line confidence level is not equal to the right lane line confidence level and the left lane line confidence level is greater than the right lane line confidence level;

[0058] The second determination subunit is further used to determine that the lane line following strategy is the right lane line following strategy when the left lane line confidence level is not equal to the right lane line confidence level and the left lane line confidence level is not greater than the right lane line confidence level.

[0059] Furthermore, the autonomous driving planning and decision-making device further includes:

[0060] a calculation unit, configured to calculate a planning target path equation based on the lane line following strategy and the left and right lane line equations after the strategy determination unit determines the lane line following strategy according to the lane line confidence level;

[0061] A control unit is used to control the target vehicle to perform automatic driving based on the planned target path.

[0062] A third aspect of the present application provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute any of the autonomous driving planning and decision-making methods described in any one of the first aspects of the present application.

[0063] A fourth aspect of the present application provides a computer-readable storage medium storing computer program instructions. When the computer program instructions are read and executed by a processor, the autonomous driving planning and decision-making method described in any one of the first aspect of the present application is executed.

[0064] The beneficial effects of the present application are as follows: the method and device can combine the predicted trajectory information of the vehicle and the lane line information to make lane selection decisions when the vehicle performs L2 level self-driving driving, thereby effectively dealing with irregular lane lines such as lane bifurcations and merging, thereby improving the stability of the function and reducing the number of times the driver takes over. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0066] Figure 1 A flowchart of an autonomous driving planning and decision-making method provided in an embodiment of the present application;

[0067] Figure 2 A flowchart of another autonomous driving planning and decision-making method provided in an embodiment of the present application;

[0068] Figure 3 A schematic diagram of the structure of an autonomous driving planning and decision-making device provided in an embodiment of the present application;

[0069] Figure 4 A schematic diagram of the structure of another autonomous driving planning and decision-making device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0070] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0071] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0072] Example 1

[0073] Please see Figure 1 , Figure 1 A flowchart of an autonomous driving planning and decision-making method provided in this embodiment. The autonomous driving planning and decision-making method includes:

[0074] S101. Acquire vehicle trajectory points of a target vehicle within a preset time period based on a geodetic coordinate system.

[0075] S102: construct a prediction line equation based on the vehicle trajectory points.

[0076] S103. Obtain, through the perception system of the target vehicle, the left and right lane line equations of the target vehicle's current driving lane in the own-vehicle coordinate system, the current own-vehicle speed, and the current lane width.

[0077] S104, determining a lane line confidence level according to the predicted line equation, the left and right lane line equations, the current vehicle speed, and the current lane width.

[0078] S105: Determine a lane line following strategy according to the lane line confidence level.

[0079] In this embodiment, the execution subject of the method may be a computing device such as a computer or a server, and no limitation is made in this embodiment.

[0080] In this embodiment, the execution subject of the method may also be a smart device such as a smart phone, a tablet computer, etc., which is not limited in this embodiment.

[0081] It can be seen that the implementation of the autonomous driving planning and decision-making method described in this embodiment can determine the control strategy by comparing the left and right lane lines of the self-lane with the predicted trajectory of the self-vehicle, thereby avoiding problems such as large steering wheel adjustments and driving direction that does not meet the driver's expectations, and ensuring that the autonomous driving vehicle can still maintain a stable and safe driving state in the complex and changeable urban road environment.

[0082] Example 2

[0083] Please see Figure 2 , Figure 2 A flowchart of an autonomous driving planning and decision-making method provided in this embodiment. The autonomous driving planning and decision-making method includes:

[0084] S201. Acquire vehicle trajectory points of a target vehicle within a preset time period based on a geodetic coordinate system.

[0085] In this embodiment, the method can obtain the position information (lateral coordinate x, longitudinal coordinate y) of the vehicle in the geodetic coordinate system through the upstream positioning module, and continuously memorize the trajectory points of the vehicle within T time, where T is a preset constant value.

[0086] S202: construct a vehicle coordinate system based on the target vehicle.

[0087] S203: Convert the vehicle trajectory points into a coordinate system to obtain the vehicle trajectory points in the vehicle coordinate system.

[0088] In this embodiment, the method can convert the set of vehicle trajectory points memorized within the time T to the current vehicle coordinate system through the following coordinate conversion formula:

[0089] x'=(x-xh)cosAg+(y-yh)sinAg

[0090] y'=(y-yh)cosAg-(x-xh)sinAg

[0091] Where x and y are the track points memorized in the geodetic coordinates, x' and y' are the track points in the vehicle coordinate system after conversion, and xh, yh, and Ag are the current position and heading angle of the vehicle in the geodetic coordinates.

[0092] S204, performing cubic polynomial fitting based on the vehicle trajectory points to obtain a prediction line equation.

[0093] In this embodiment, the method can use the converted memory trajectory point set to perform cubic polynomial fitting to obtain the polynomial coefficients P0, P1, P2, and P3 of the prediction line. The polynomial coefficients P0, P1, P2, and P3 of the prediction line can be used to predict the future driving trajectory of the vehicle.

[0094] In this embodiment, the method can predict the future driving trajectory based on the historical driving trajectory of the vehicle.

[0095] S205, determining whether the LCC centering function of the target vehicle is in an activated state within a preset time period, if so, executing step S206; if not, ending this process.

[0096] In this embodiment, if the vehicle LCC centering function is in an activated state within the past T time periods, the memorized trajectory is considered valid.

[0097] S206, determining that the vehicle trajectory point is a valid trajectory, and determining that the prediction line equation can be used to predict the future driving trajectory of the vehicle, and executing step S207.

[0098] S207. Obtain, through the perception system of the target vehicle, the left and right lane line equations of the target vehicle's current driving lane in the own-vehicle coordinate system, the current own-vehicle speed, and the current lane width.

[0099] In this embodiment, the method can obtain the left and right lane line equations of the current vehicle driving lane through the vehicle's perception system. The lane line equation is a cubic equation with four coefficients (taking the left lane as an example, there are L0, L1, L2, and L3). The lane line equation is based on the vehicle coordinate system.

[0100] S208: Calculate the current preview distance based on the preset preview time and the current vehicle speed.

[0101] In this embodiment, the method can calculate the current preview distance L by multiplying the preset preview time Tl and the current vehicle speed V (m / s); at the same time, the minimum value of L is limited by the preset minimum preview distance Lmin to ensure that there is still a certain shortest preview distance at low speed.

[0102] S209: Calculate a distance threshold according to the current lane width and a preset offset.

[0103] S210, calculating the proportion of coordinate points whose lateral distance between the predicted line and the lane line is less than the distance threshold according to the left and right lane line equations, the predicted line equation, the current preview distance, and the distance threshold.

[0104] In this embodiment, the method can use half of the current lane width plus a preset offset (such as 0.2m) as the threshold W, with a step size of 1m, substitute the distance from 1 to L into the left and right lane lines and the predicted line equations respectively, and calculate the proportion of points whose lateral distance between the predicted line and the lane line is less than W.

[0105] For example, when calculating the proportion of the predicted line and the left lane line, assuming that the current step length is 1m, there are M points from 1 to L, of which N points satisfy:

[0106] |(P3*x^3+P2*x^2+P1*x+P0)-(L3*x^3+L2*x^2+L1*x+L0)| <W

[0107] At this time, x is the longitudinal distance corresponding to these N points;

[0108] The current proportion of the left lane line is PL=N / M.

[0109] In this embodiment, the calculation method of the right lane line ratio is the same as the calculation method of the left lane line ratio. Among them, the higher the ratio coefficient, the higher the similarity between the corresponding lane line and the predicted trajectory.

[0110] S211. Determine the lane line confidence level according to the coordinate point ratio and a preset ratio threshold.

[0111] In this embodiment, the method can determine the confidence level of the lane line according to an interval composed of preset thresholds:

[0112] If the lane line ratio is greater than ThrHigh, the confidence level of the corresponding lane line is high;

[0113] If the lane line ratio is greater than ThrMid and less than or equal to ThrHigh, the confidence level of the corresponding lane line is medium;

[0114] If the lane line ratio coefficient is less than or equal to ThrMid, the confidence level of the corresponding lane line is low.

[0115] S212: Determine a lane line following strategy according to the lane line confidence level.

[0116] As an optional implementation, determining a lane line following strategy according to the lane line confidence level includes:

[0117] When the lane line confidence level only includes the left lane line confidence level, the lane line following strategy is determined to be the left lane line following strategy;

[0118] When the lane line confidence level only includes the right lane line confidence level, the lane line following strategy is determined to be the right lane line following strategy;

[0119] When the lane line confidence level includes a left lane line confidence level and a right lane line confidence level, determining whether the left lane line confidence level and the right lane line confidence level are equal;

[0120] If yes, the lane line following strategy is determined to be a double-line following strategy.

[0121] As a further optional implementation, the method further includes:

[0122] When the left lane line confidence level is not equal to the right lane line confidence level, and the left lane line confidence level is greater than the right lane line confidence level, the lane line following strategy is determined to be the left lane line following strategy;

[0123] When the left lane line confidence level is not equal to the right lane line confidence level, and the left lane line confidence level is not greater than the right lane line confidence level, the lane line following strategy is determined to be the right lane line following strategy.

[0124] In this embodiment, the method can compare the confidence of the left and right lane lines to select a following strategy, wherein the strategy is effective only when the lane lines on both sides of the lane are valid. If the perception only recognizes the lane line on one side, the vehicle will follow the recognized lane line unilaterally.

[0125] For example, when the perception recognizes that the lane lines on both sides are valid:

[0126] If the confidence levels of the left and right lane lines are equal, the vehicle follows the double line, and the planned target path is the average of the coefficients of the double line equation:

[0127] y=((L3+R3) / 2)*x^3+((L2+R2) / 2)*x^2+((L1+R1) / 2)*x+((L0+R0) / 2).

[0128] If the confidence levels of the left and right lane lines are not equal, the vehicle follows the lane line with higher confidence. For example, the left lane has higher confidence:

[0129] y=L3*x^3+L2*x^2+L1*x+((L0+R0) / 2).

[0130] S213: Calculate the planned target path equation based on the lane line following strategy and the left and right lane line equations.

[0131] S214: Control the target vehicle to perform automatic driving based on the planned target path.

[0132] In this embodiment, the execution subject of the method may be a computing device such as a computer or a server, and no limitation is made in this embodiment.

[0133] In this embodiment, the execution subject of the method may also be a smart device such as a smart phone, a tablet computer, etc., which is not limited in this embodiment.

[0134] It can be seen that the implementation of the autonomous driving planning and decision-making method described in this embodiment can determine the control strategy by comparing the left and right lane lines of the self-lane with the predicted trajectory of the self-vehicle, thereby avoiding problems such as large steering wheel adjustments and driving direction that does not meet the driver's expectations, and ensuring that the autonomous driving vehicle can still maintain a stable and safe driving state in the complex and changeable urban road environment.

[0135] Example 3

[0136] Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of an automatic driving planning and decision-making device provided in this embodiment. Figure 3 As shown, the automatic driving planning and decision-making device includes:

[0137] A first acquisition unit 310 is used to acquire the vehicle trajectory points of the target vehicle within a preset time period based on the geodetic coordinate system;

[0138] A construction unit 320, configured to construct a prediction line equation based on the ego vehicle trajectory points;

[0139] The second acquisition unit 330 is used to acquire the left and right lane line equations of the current lane of the target vehicle in the own vehicle coordinate system, the current own vehicle speed and the current lane width through the perception system of the target vehicle;

[0140] A confidence determination unit 340 is used to determine a lane line confidence level based on a predicted line equation, left and right lane line equations, a current vehicle speed, and a current lane width;

[0141] The strategy determination unit 350 is used to determine the lane following strategy according to the lane confidence level.

[0142] In this embodiment, the explanation of the autonomous driving planning and decision-making device can refer to the description in Example 1 or Example 2, and will not be further elaborated in this embodiment.

[0143] It can be seen that the implementation of the autonomous driving planning and decision-making device described in this embodiment can determine the control strategy by comparing the left and right lane lines of the self-lane with the predicted trajectory of the self-vehicle, thereby avoiding problems such as large steering wheel adjustments and driving direction that does not meet the driver's expectations, and ensuring that the autonomous driving vehicle can still maintain a stable and safe driving state in the complex and changeable urban road environment.

[0144] Example 4

[0145] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of an automatic driving planning and decision-making device provided in this embodiment. Figure 4 As shown, the automatic driving planning and decision-making device includes:

[0146] A first acquisition unit 310 is used to acquire the vehicle trajectory points of the target vehicle within a preset time period based on the geodetic coordinate system;

[0147] A construction unit 320, configured to construct a prediction line equation based on the ego vehicle trajectory points;

[0148] The second acquisition unit 330 is used to acquire the left and right lane line equations of the current lane of the target vehicle in the own vehicle coordinate system, the current own vehicle speed and the current lane width through the perception system of the target vehicle;

[0149] A confidence determination unit 340 is used to determine a lane line confidence level based on a predicted line equation, left and right lane line equations, a current vehicle speed, and a current lane width;

[0150] The strategy determination unit 350 is used to determine the lane following strategy according to the lane confidence level.

[0151] As an optional implementation, the construction unit 320 includes:

[0152] A construction subunit 321 is used to construct a self-vehicle coordinate system based on the target vehicle;

[0153] The conversion subunit 322 is used to convert the ego vehicle trajectory point into a coordinate system to obtain the vehicle trajectory point in the ego vehicle coordinate system;

[0154] The fitting subunit 323 is used to perform cubic polynomial fitting based on the vehicle trajectory points to obtain a prediction line equation.

[0155] As an optional implementation, the autonomous driving planning and decision-making device further includes:

[0156] A judging unit 360, configured to judge whether the LCC centering function of the target vehicle is in an activated state within a preset time period after the constructing unit 320 constructs the prediction line equation based on the vehicle trajectory points;

[0157] The validity determination unit 370 is used to determine that the trajectory point of the ego vehicle is a valid trajectory when the LCC centering function of the target vehicle is activated within a preset time period, and to determine that the predicted line equation can be used to predict the future driving trajectory of the ego vehicle, and to trigger the second acquisition unit 330 to execute the operation of acquiring the left and right lane line equations of the current lane of the target vehicle, the current speed of the ego vehicle, and the current lane width of the target vehicle in the ego vehicle coordinate system through the perception system of the target vehicle.

[0158] As an optional implementation, the confidence determination unit 340 includes:

[0159] A calculation subunit 341 is used to calculate a current preview distance based on a preset preview time and a current vehicle speed;

[0160] The calculation subunit 341 is further used to calculate a distance threshold according to the current lane width and a preset offset;

[0161] The calculation subunit 341 is further used to calculate the proportion of coordinate points whose lateral distance between the predicted line and the lane line is less than the distance threshold according to the left and right lane line equations, the predicted line equation, the current preview distance and the distance threshold;

[0162] The first determination subunit 342 is used to determine the lane line confidence level according to the coordinate point ratio and a preset ratio threshold.

[0163] As an optional implementation, the policy determination unit 350 includes:

[0164] A second determining subunit 351 is used to determine that the lane line following strategy is a left lane line following strategy when the lane line confidence level only includes the left lane line confidence level;

[0165] The second determining subunit 351 is further configured to determine that the lane line following strategy is a right lane line following strategy when the lane line confidence level only includes the right lane line confidence level;

[0166] A judging subunit 352, configured to judge whether the left lane line confidence level and the right lane line confidence level are equal when the lane line confidence level includes the left lane line confidence level and the right lane line confidence level;

[0167] The second determining subunit 351 is further configured to determine that the lane line following strategy is a dual-line following strategy when the left lane line confidence level and the right lane line confidence level are equal.

[0168] As an optional implementation manner, the second determining subunit 351 is further configured to determine that the lane line following strategy is the left lane line following strategy when the left lane line confidence level is not equal to the right lane line confidence level and the left lane line confidence level is greater than the right lane line confidence level;

[0169] The second determination subunit 351 is further used to determine that the lane line following strategy is the right lane line following strategy when the left lane line confidence level is not equal to the right lane line confidence level and the left lane line confidence level is not greater than the right lane line confidence level.

[0170] As an optional implementation, the autonomous driving planning and decision-making device further includes:

[0171] A calculation unit 380, configured to calculate a planned target path equation based on the lane following strategy and left and right lane line equations after the strategy determination unit 350 determines the lane following strategy according to the lane confidence level;

[0172] The control unit 390 is used to control the target vehicle to perform automatic driving based on the planned target path.

[0173] In this embodiment, the explanation of the autonomous driving planning and decision-making device can refer to the description in Example 1 or Example 2, and will not be further elaborated in this embodiment.

[0174] It can be seen that the implementation of the autonomous driving planning and decision-making device described in this embodiment can determine the control strategy by comparing the left and right lane lines of the self-lane with the predicted trajectory of the self-vehicle, thereby avoiding problems such as large steering wheel adjustments and driving direction that does not meet the driver's expectations, and ensuring that the autonomous driving vehicle can still maintain a stable and safe driving state in the complex and changeable urban road environment.

[0175] An embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the autonomous driving planning and decision-making method in embodiment 1 or embodiment 2 of the present application.

[0176] An embodiment of the present application provides a computer-readable storage medium storing computer program instructions. When the computer program instructions are read and executed by a processor, the autonomous driving planning and decision-making method in embodiment 1 or embodiment 2 of the present application is executed.

[0177] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0178] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0179] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0180] The above description is only an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0181] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0182] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

Claims

1. An automatic driving planning and decision-making method, characterized in that: include: Obtain the target vehicle's own vehicle trajectory points within a preset time period based on the geodetic coordinate system; Constructing a prediction line equation based on the ego vehicle trajectory points; Obtaining, through the perception system of the target vehicle, left and right lane line equations of the current lane of the target vehicle, the current speed of the vehicle, and the current lane width in the own-vehicle coordinate system; Determining a lane line confidence level according to the predicted line equation, the left and right lane line equations, the current vehicle speed, and the current lane width; A lane line following strategy is determined according to the lane line confidence level.

2. The autonomous driving planning and decision-making method according to claim 1, characterized in that: The step of constructing a prediction line equation based on the vehicle trajectory points includes: Constructing a self-vehicle coordinate system based on the target vehicle; Convert the vehicle trajectory points into a coordinate system to obtain the vehicle trajectory points in the vehicle coordinate system; A cubic polynomial fitting is performed based on the vehicle trajectory points to obtain a prediction line equation.

3. The autonomous driving planning and decision-making method according to claim 1, characterized in that: After constructing the prediction line equation based on the ego vehicle trajectory points, the method further includes: Determining whether the LCC centering function of the target vehicle is in an activated state within the preset time period; If so, it is determined that the vehicle trajectory point is a valid trajectory, and it is determined that the predicted line equation can be used to predict the future driving trajectory of the vehicle, and the perception system of the target vehicle is executed to obtain the left and right lane line equations of the current lane of the target vehicle in the vehicle coordinate system, the current vehicle speed and the current lane width.

4. The autonomous driving planning and decision-making method according to claim 1, characterized in that: The determining of the lane line confidence level according to the predicted line equation, the left and right lane line equations, the current vehicle speed and the current lane width includes: Calculating a current preview distance based on a preset preview time and the current vehicle speed; Calculating a distance threshold according to the current lane width and a preset offset; Calculate the proportion of coordinate points whose lateral distance between the predicted line and the lane line is less than the distance threshold according to the left and right lane line equations, the predicted line equation, the current preview distance, and the distance threshold; The lane line confidence level is determined based on the coordinate point ratio and a preset ratio threshold.

5. The autonomous driving planning and decision-making method according to claim 1, characterized in that: The determining of the lane line following strategy according to the lane line confidence level includes: When the lane line confidence level only includes the left lane line confidence level, the lane line following strategy is determined to be the left lane line following strategy; When the lane line confidence level only includes the right lane line confidence level, the lane line following strategy is determined to be the right lane line following strategy; When the lane line confidence level includes a left lane line confidence level and a right lane line confidence level, determining whether the left lane line confidence level and the right lane line confidence level are equal; If yes, the lane line following strategy is determined to be a double-line following strategy.

6. The autonomous driving planning and decision-making method according to claim 5, characterized in that: The method further comprises: When the left lane line confidence level is not equal to the right lane line confidence level, and the left lane line confidence level is greater than the right lane line confidence level, determining that the lane line following strategy is the left lane line following strategy; When the left lane line confidence level is not equal to the right lane line confidence level, and the left lane line confidence level is not greater than the right lane line confidence level, it is determined that the lane line following strategy is the right lane line following strategy.

7. The autonomous driving planning and decision-making method according to claim 1, characterized in that: After determining the lane line following strategy according to the lane line confidence level, the method further includes: Based on the lane line following strategy and the left and right lane line equations, calculating a planned target path equation; The target vehicle is controlled to perform automatic driving based on the planned target path.

8. An automatic driving planning and decision-making device, characterized in that: The autonomous driving planning and decision-making device comprises: A first acquisition unit, used for acquiring a target vehicle's own vehicle trajectory point within a preset time period based on a geodetic coordinate system; A construction unit, used for constructing a prediction line equation based on the vehicle trajectory points; A second acquisition unit is used to acquire, through the perception system of the target vehicle, left and right lane line equations of the current lane of the target vehicle, the current speed of the vehicle, and the current lane width in the vehicle coordinate system; A confidence determination unit, configured to determine a lane line confidence level according to the predicted line equation, the left and right lane line equations, the current vehicle speed, and the current lane width; A strategy determination unit is used to determine a lane line following strategy according to the lane line confidence level.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the autonomous driving planning and decision-making method according to any one of claims 1 to 7.

10. A readable storage medium, characterized in that: The readable storage medium stores computer program instructions, and when the computer program instructions are read and executed by a processor, the automatic driving planning and decision-making method described in any one of claims 1 to 7 is executed.

Citation Information

Patent Citations

  • Lane keeping method and device for autonomous vehicle

    CN114228741A

  • Cruise target selection method and device based on lane line, equipment and medium

    CN117104226A