Vehicle control method and device, vehicle and storage medium

Abstract

The application discloses a vehicle control method and device, a vehicle and a readable storage medium. The method comprises the following steps: determining a first planning path of a vehicle in a target frame according to a speed planning result of the vehicle in a previous frame of the target frame; determining a first coordinate system according to the first planning path; determining a first speed planning result according to a projection of an obstacle in a longitudinal direction of the first coordinate system; correcting a projection of the obstacle in a transverse direction of the first coordinate system according to the first speed planning result to obtain a target projection result; determining a second planning path of the vehicle in the target frame according to the target projection result; determining a second coordinate system according to the second planning path; determining a second speed planning result according to a projection of the obstacle in a longitudinal direction of the second coordinate system; and controlling the vehicle to travel according to the second speed planning result and the second planning path. In the application, two speed planning and two path planning are performed in a single frame, so that the accuracy and flexibility of local decision planning of the vehicle are improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and more specifically, to a vehicle control method, device, vehicle, and computer-readable storage medium. Background Art

[0002] With the development of autonomous driving technology, decision-making and planning have become a key component. By integrating multi-sensor information with driving requirements, decision-making is made, planning multiple collision-free and safe paths from the starting point to the destination, and selecting the optimal path from these paths as the vehicle's trajectory. Decision-making and planning can be divided into two types: global planning and local planning, depending on the level of division. Global planning uses acquired map information to plan an optimal collision-free path under specific conditions. Local planning, based on the global plan, uses local environmental information to avoid collisions and ultimately reach the destination.

[0003] Existing local decision-making planning methods are based on spatiotemporal decoupling. This approach decouples a three-dimensional trajectory planning problem into two two-dimensional ones, optimizes each two-dimensional problem, and finally merges the trajectories to obtain the vehicle's trajectory. However, the trajectory obtained using spatiotemporal decoupling is not very accurate and lacks flexibility.

[0004] Therefore, there is an urgent need for a vehicle control method to improve the accuracy and flexibility of vehicle local decision-making planning. Summary of the Invention

[0005] The present application proposes a vehicle control method, device, vehicle and computer-readable storage medium to improve the above-mentioned defects.

[0006] In a first aspect, an embodiment of the present application provides a vehicle control method, the method comprising: determining a first planned path of the vehicle in a target frame based on a speed planning result corresponding to a previous frame of the target frame; determining a first coordinate system based on the first planned path; determining a first speed planning result of the vehicle in the target frame based on a projection of an obstacle in the longitudinal direction of the first coordinate system; correcting a projection of the obstacle in the transverse direction of the first coordinate system based on the first speed planning result to obtain a target projection result corresponding to the target obstacle, the correction including any one of adding, deleting and retaining; determining a second planned path of the vehicle in the target frame based on the target projection result; determining a second coordinate system based on the second planned path; determining a second speed planning result of the vehicle in the target frame based on the projection of the obstacle in the longitudinal direction of the second coordinate system; and controlling vehicle driving based on the second speed planning result and the second planned path.

[0007] In a second aspect, an embodiment of the present application further provides a vehicle control device, the device comprising:

[0008] A first determining module is used to determine a first planned path of the vehicle in the target frame according to a speed planning result corresponding to a frame before the target frame;

[0009] A second determining module, configured to determine a first coordinate system according to the first planned path;

[0010] A third determining module is used to determine a first speed planning result of the vehicle in the target frame according to a projection of the obstacle in the longitudinal direction of the first coordinate system;

[0011] a correction module, configured to correct the projection of the obstacle in the lateral direction of the first coordinate system according to the first speed planning result to obtain a target projection result corresponding to the target obstacle, wherein the correction includes any one of adding, deleting, and retaining;

[0012] a fourth determining module, configured to determine a second planned path of the vehicle in the target frame according to the target projection result;

[0013] a fifth determining module, configured to determine a second coordinate system according to the target projection result;

[0014] a sixth determining module, configured to determine a second speed planning result of the vehicle in the target frame according to a projection of the obstacle in the longitudinal direction of the second coordinate system;

[0015] The control module is used to control the vehicle driving according to the second speed planning result and the second planned path.

[0016] In a third aspect, an embodiment of the present application also provides a vehicle, characterized in that the vehicle includes: one or more processors; a memory; one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by one or more processors, and the one or more programs are configured to execute the above method.

[0017] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores a program code executable by a processor, and when the program code is executed by the processor, the processor executes the above method.

[0018] The present application provides a vehicle control method, device, vehicle and computer-readable storage medium. In the present application, by performing two speed planning and two path planning within a single frame, the problem of mismatch between speed planning results and path planning results is solved, and the accuracy of vehicle local decision planning is improved. By correcting the lateral projection based on the first planned path and the first speed planning result, and then obtaining the second planned path and the second speed planning result according to the corrected target projection result, the vehicle driving is controlled. By performing two speed planning and path planning within a single frame, the problem of mismatch between speed planning results and path planning results is solved, and the accuracy of vehicle local decision planning is improved, thereby improving driving safety.

[0019] Other features and advantages of the embodiments of the present application will be described in the following description and, in part, will become apparent from the description or be understood by practicing the embodiments of the present application. The objectives and other advantages of the embodiments of the present application can be achieved and obtained through the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 A schematic diagram of a vehicle hardware environment suitable for an embodiment of the present application is shown.

[0022] Figure 2 A flow chart of a vehicle control method proposed according to an embodiment of the present application is shown.

[0023] Figure 3 A flow chart of a vehicle control method proposed according to another embodiment of the present application is shown.

[0024] Figure 4 A schematic diagram of a target projection result determination process in an embodiment of the present application is shown.

[0025] Figure 5 A schematic diagram of a driving trajectory determination process in an embodiment of the present application is shown.

[0026] Figure 6 A structural block diagram of a vehicle control device proposed in one embodiment of the present application is shown. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application for which protection is claimed, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work fall within the scope of protection of the present application.

[0028] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or 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 should not be understood as indicating or implying relative importance.

[0029] See also Figure 1 , Figure 1 A schematic diagram of a vehicle hardware environment suitable for an embodiment of the present application is shown, wherein the vehicle 100 includes an automatic driving system 110. The automatic driving system 110 may have multiple built-in automatic driving functions. The automatic driving system 110 controls the vehicle's automatic driving according to the built-in automatic driving functions. The automatic driving functions may include, for example, automatic lane changing function, automatic overtaking function, and automatic parking function.

[0030] The autonomous driving system 110 may include an information acquisition module 111 , one or more (only one is shown in the figure) processors 112 , and a memory 113 .

[0031] The information collection module 111 is used to collect vehicle perception, prediction, positioning, navigation, and vehicle motion status information during vehicle driving.

[0032] The map navigation module 112 is used to generate a navigation path from the current location to the target location according to the location information. The current location can be the actual location of the vehicle or any location set by the passenger.

[0033] The processor 112 may be a microcontroller unit (MCU) having a built-in memory 113 . The memory 113 stores a program that can execute the contents of the following embodiments, and the processor 112 can execute the program stored in the memory 113 .

[0034] The processor 112 can include one or more processors. The processor 112 connects various parts in the entire vehicle 100 by various interfaces and lines, executes various functions of the vehicle 100 and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 113, and calling data stored in the memory 113.

[0035] The memory 113 can include a random access memory (RAM) and can also include a read-only memory (ROM). The memory 113 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 113 can include a program storage area and a data storage area, wherein the program storage area can store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing each method embodiment described below, etc.

[0036] Please refer to Figure 2 , Figure 2 A flow chart of a vehicle control method according to an embodiment of the present application is shown, and the method is used for a vehicle, and the method comprises the following steps.

[0037] S101, determining a first planning path of the vehicle in a target frame according to a speed planning result corresponding to a previous frame of the target frame of the vehicle.

[0038] The vehicle can be any vehicle with automatic driving function. For example, the vehicle can be an electric vehicle or a fuel vehicle, and can also be a car, an SUV, a bus, a truck, etc.

[0039] The speed in the speed planning result corresponding to the previous frame of the target frame of the vehicle when determining the first path planning of the vehicle can be the speed set by the adaptive cruise control system of the vehicle.

[0040] In some embodiments, dynamic simulation is performed according to the speed planning result corresponding to the previous frame of the target frame of the vehicle, the vehicle is simulated to travel at the speed in the speed planning result corresponding to the previous frame, and the trajectory of the obstacle between the contact of the vehicle head with the obstacle and the departure of the vehicle from the obstacle is simulated. According to the trajectory of the obstacle, the first planning path of the vehicle is determined, and the step of dynamic simulation can be set according to requirements.

[0041] S102, determining a first coordinate system according to the first planning path.

[0042] Among them, the first coordinate system can be a frenet coordinate system, which is also called an SL coordinate system. The establishment of the Frenet coordinate system is based on a given reference line. The given reference line can be an arbitrary curve. It is generally defined as the center line of the lane. The lane driving direction is the horizontal direction, that is, the S axis direction, and the vertical direction perpendicular to the lane driving direction is the L axis direction. The frenet coordinate system is constructed based on the given reference line, and the frenet coordinate system is reconstructed after each first preset length of the reference line. The first preset length can be 150 meters, and the waypoint interval of the reference line must meet the second preset length to be able to construct the frenet coordinate system with this reference line. The second preset length can be 0.1 meters. The first coordinate system here is a coordinate system constructed with the first planned path as the reference line.

[0043] S103 : Determine a first speed planning result of the vehicle in the target frame according to a projection of the obstacle in the longitudinal direction of the first coordinate system.

[0044] The longitudinal direction is the L direction of the frenet coordinate system, and the first speed planning result can be overtaking, avoiding, or no speed planning result.

[0045] In some embodiments, the obstacle can be projected into the longitudinal space of the first coordinate system to obtain the longitudinal displacement-time information of the obstacle in the longitudinal space of the first coordinate system. A dynamic programming method is applied to the longitudinal displacement-time information, and the longitudinal displacement-time information is used as input to obtain the first speed planning result.

[0046] The sampling interval of the longitudinal projection may be a first preset duration, which may be 0.1 seconds. The step length of the first velocity planning result should be consistent with the step length of the dynamic simulation. If the step lengths conflict, the longer step length is used, and the step length does not exceed a second preset duration, which may be 0.2 seconds.

[0047] Dynamic programming is a method for solving dynamic programming problems. It involves finding the optimal strategy step by step from the end point to the starting point. It applies the Bellman principle and a basic recursive relation to find the optimal path from the end point back to the starting point in reverse order. This involves dividing the original problem into many simpler yet interconnected subproblems. Each subproblem is solved by leveraging the optimization result of a subsequent subproblem. The optimal solution to the final subproblem is then considered the optimal solution to the original problem.

[0048] S104: Correct the horizontal projection of the obstacle in the first coordinate system according to the first speed planning result to obtain a target projection result corresponding to the target obstacle.

[0049] The correction includes any one of adding, deleting and retaining, and the correction of the horizontal projection of the obstacle in the first coordinate system is to delete the horizontal projection of the obstacle in the first coordinate system, retain the horizontal projection of the obstacle in the first coordinate system, and add the horizontal projection of the obstacle in the first coordinate system.

[0050] In some embodiments, the lateral projection of an obstacle in the first coordinate system may be a projection of a trajectory corresponding to the obstacle in the lateral space of the first coordinate system obtained by dynamically simulating the obstacle parallel to and in front of the vehicle. The sampling interval for the lateral projection may be a first preset duration, which may be 0.1 seconds.

[0051] In some embodiments, the projection of the obstacle in the lateral direction of the first coordinate system is corrected according to whether the first speed planning result is overtaking or avoiding, to obtain a target projection result corresponding to the target obstacle.

[0052] S105 : Determine a second planned path of the vehicle in the target frame according to the target projection result.

[0053] In some implementations, a dynamic programming method is used on the target projection result to search for a rough planning path corresponding to the second planning path, and a quadratic programming method is used on the rough planning path to determine the second planning path.

[0054] Quadratic programming refers to an optimization problem with a quadratic objective function and constraints.

[0055] The general form of quadratic programming can be expressed as:

[0056]

[0057]

[0058] Where G is the Hessian matrix, τ is a finite set of indices, c, x and {a i}, are all vectors in R. If the Hessian matrix is ​​semi-positive definite, it is a convex quadratic program with a global optimal solution; if the Hessian matrix is ​​positive definite, there is a unique global optimal solution; if the Hessian matrix is ​​non-positive definite, it is a non-convex quadratic program with multiple stationary points and local minima.

[0059] S106: Determine a second coordinate system according to the second planned path.

[0060] The second coordinate system may also be a Frenet coordinate system, and the coordinate system origins of the second coordinate system and the first coordinate system are different.

[0061] In some embodiments, the second planned path is used as a reference line, and a second coordinate system is established based on the second planned path.

[0062] S107 : Determine a second speed planning result of the vehicle in the target frame according to the projection of the obstacle in the longitudinal direction of the second coordinate system.

[0063] The projection of the obstacle in the longitudinal direction of the second coordinate system may be a projection of an obstacle that interacts with the vehicle in the longitudinal space of the second coordinate system. The obstacle that interacts with the vehicle here refers to an obstacle on the second planned path.

[0064] In some embodiments, obstacles on the second planned path are projected into the longitudinal space of the second coordinate system in the first coordinate system to obtain longitudinal displacement-time information of the obstacles in the longitudinal space of the second coordinate system. Dynamic programming and quadratic programming are then applied to this longitudinal displacement-time information to obtain the second speed planning result. The sampling density of the dynamic programming method can be dynamically adjusted based on the vehicle speed, while the sampling density of the quadratic programming method is one optimization value per third of the preset length.

[0065] S108: Control the vehicle to travel according to the second speed planning result and the second planned path.

[0066] After obtaining the second speed planning result and the second planned path, the vehicle is controlled to travel on the second planned path at the speed in the second speed planning result.

[0067] In some embodiments, S107 may include: matching the second speed planning result and the second planned path to determine a corresponding driving trajectory of the vehicle; and controlling the vehicle to travel according to the driving trajectory.

[0068] The track density of the driving track is a fourth preset length, and the fourth preset length may be 0.1 meter.

[0069] In this embodiment, by performing two speed planning and two path planning within a single frame, the problem of mismatch between speed planning results and path planning results is solved, and the accuracy of the vehicle's local decision-making planning is improved. By correcting the lateral projection based on the first planned path and the first speed planning result, and then obtaining the second planned path and the second speed planning result according to the corrected lateral projection, the lateral movement, longitudinal movement, and lateral-longitudinal coupled movement of the obstacle are distinguished, achieving full coverage of static and dynamic obstacles, and improving the flexibility of the vehicle's local decision-making planning. Finally, the vehicle is controlled according to the second planned path and the second speed planning result, thereby improving driving safety.

[0070] See also Figure 3 , Figure 3A flow chart of a vehicle control method proposed in another embodiment of the present application is shown, which is used for a vehicle. The method includes:

[0071] S201 : Determine a longitudinal intersection interval corresponding to an obstacle in the longitudinal direction of an initial coordinate system based on a velocity planning result of the vehicle corresponding to a frame preceding a target frame.

[0072] The initial coordinate system may also be a Frenet coordinate system, which has a different origin from both the first coordinate system and the second coordinate system. The initial coordinate system may be constructed using the navigation line in the vehicle navigation information as a reference line, where the navigation line may be the center line of the lane. The longitudinal intersection interval corresponding to the obstacle in the longitudinal direction of the initial coordinate system is the interval where the obstacle and the vehicle overlap in the lateral direction of the initial coordinate system. One obstacle may correspond to one longitudinal intersection interval, or multiple obstacles may correspond to one longitudinal intersection interval. The predicted step length of the longitudinal intersection interval should be consistent with the step length of the first speed planning result and the step length of the dynamic simulation. If there is a step length conflict, the longer step length shall be taken, and the step length shall not exceed the second preset time length, which may be 0.2 seconds.

[0073] In some embodiments, the obstacle information belongs to the environmental information in the vehicle's perception information. The vehicle's environmental information is information in a Cartesian coordinate system. It is necessary to convert the environmental information in the Cartesian coordinate system into an initial coordinate system, namely, a Frenet coordinate system.

[0074] In some implementations, the timestamp of vehicle information collection, such as navigation information and sensor information, is also recorded. Since the timestamps of each vehicle information collection may differ, time compensation is required to ensure a more accurate trajectory. For example, if vehicle information A was collected 200ms ago and vehicle information B was collected 100ms ago, the difference in timestamps between vehicle information A and vehicle information B will affect the resulting trajectory. Time compensation can reduce or eliminate this effect.

[0075] S202: Project the trajectory of the target obstacle in the obstacles within the longitudinal intersection interval onto the lateral direction of the initial coordinate system to obtain a lateral projection result of the target obstacle.

[0076] In some embodiments, the target obstacle among the obstacles may be an obstacle among the obstacles that is parallel to the vehicle and in front of the vehicle. The trajectory of the target obstacle may be obtained through dynamic simulation, simulating the vehicle traveling at the speed in the speed planning result corresponding to the previous frame. The trajectory of the target obstacle from the time the front of the vehicle contacts the obstacle to the time the parking space leaves the target obstacle is obtained from the trajectory of the target obstacle. The trajectory of the target obstacle in the longitudinal intersection interval is projected into the lateral space of the initial coordinate system to obtain a lateral projection result of the target obstacle.

[0077] S203, determining a first planning path of the vehicle in the target frame according to the lateral projection result.

[0078] In some embodiments, determining the first planning path of the vehicle according to the lateral projection result can include: performing dynamic programming on the lateral projection result to obtain a rough planning path; determining a convex space according to the rough planning path; and performing secondary programming on the rough planning path according to the convex space to obtain the first planning path.

[0079] In some embodiments, performing dynamic programming on the lateral projection result can search for multiple rough planning paths, and a unique convex space can be determined according to the rough planning paths. The convex space can be a left direction of the obstacle or a right direction of the obstacle. After determining the direction through the obstacle, the first planning path of the vehicle in the target frame is obtained by performing secondary programming on the rough planning path according to the convex space, that is, the first planning path is determined by the secondary programming method according to the uniquely determined convex space. For a space, if the line connecting two points in the space is also in the space, the space is a convex space. The secondary programming on the rough planning path according to the convex space to obtain the first planning path reduces the complexity of determining the first planning path.

[0080] For example, the vehicle has a collision risk with the obstacle A. Through dynamic programming, multiple rough planning paths of the vehicle passing by the obstacle A can be determined. The vehicle can pass by the obstacle A from the left side of the obstacle A or from the right side of the obstacle A. According to the multiple rough planning paths, it can be determined which side the vehicle passes by the obstacle A, that is, the convex space is determined. Taking the left side as an example, after determining that the vehicle passes by the obstacle A from the left side, the optimal distance from the obstacle A can be determined by secondary programming, that is, the first planning path is determined.

[0081] S204, determining a first coordinate system according to the first planning path.

[0082] S205, determining a first speed planning result of the vehicle in the target frame according to the projection of the obstacle in the longitudinal direction of the first coordinate system.

[0083] The descriptions of S204-S205 refer to the descriptions of S102-S103 above, which will not be repeated here.

[0084] S206, obtaining a relative position relationship between the obstacle and the vehicle in the longitudinal direction of the first coordinate system.

[0085] The obstacle here can be an obstacle on the first planning path, and the relative position relationship between the obstacle and the vehicle in the longitudinal direction of the first coordinate system can be that the obstacle is in front of the vehicle or that the obstacle is behind the vehicle.

[0086] S207: Determine a projection processing result of the obstacle according to the relative position relationship and the first speed planning result.

[0087] According to the relative position relationship, whether the obstacle is in front of the vehicle or behind the vehicle, and whether the first speed planning result is overtaking, avoiding, or no speed planning result, a projection processing result of the obstacle is determined.

[0088] In some embodiments, S205 may include: when the relative position relationship is that the obstacle is in front of the vehicle, if the first speed planning result is no speed planning result or the first speed planning result is not an avoidance decision, determining that the projection processing result is to retain the obstacle's projection in the lateral direction of the first coordinate system; if the first speed planning result is an avoidance decision, determining that the projection processing result is to delete the obstacle's projection in the lateral direction of the first coordinate system; or, when the relative position relationship is that the obstacle is parallel to the vehicle, determining that the projection processing result is to retain the obstacle's projection in the lateral direction of the first coordinate system; or, when the relative position relationship is that the obstacle is behind the vehicle, if the first speed planning result is no speed planning result or the first speed planning result is not an overtaking decision, determining that the projection processing result is to add the obstacle's projection in the lateral direction of the first coordinate system; if the first speed planning result is an overtaking decision, determining that the projection processing result is to retain the obstacle's projection in the lateral direction of the first coordinate system.

[0089] In some embodiments, if the obstacle is in front of the vehicle and the speed planning result is other, the projection processing result is determined to retain the lateral projection of the obstacle in the first coordinate system; if the obstacle is behind the vehicle and the speed planning result is other, the projection processing result is to add the lateral projection of the obstacle in the first coordinate system.

[0090] S208 : Correct the horizontal projection of the obstacle in the first coordinate system according to the projection processing result to obtain a target projection result corresponding to the target obstacle.

[0091] After the projection processing result is obtained, the horizontal projection of the obstacle in the first coordinate system is corrected according to the projection processing result to obtain a target projection result corresponding to the target obstacle.

[0092] like Figure 4If the obstacle is in front of the vehicle and there is no speed planning result, the lateral projection of the obstacle in the first coordinate system is obtained as the target projection result; if the speed planning result is an avoidance decision, the lateral projection of the obstacle in the first coordinate system is deleted, and the lateral projection in the first coordinate system after deleting the projection is obtained as the target projection result; if the speed planning result is other, the lateral projection of the obstacle in the first coordinate system is obtained as the target projection result; if the obstacle is parallel to the vehicle, the lateral projection of the obstacle in the first coordinate system is obtained as the target projection result; if the obstacle is behind the vehicle and there is no speed planning result, the lateral projection in the first coordinate system after adding the projection is obtained as the target projection result; if the speed planning result is an overtaking decision, the lateral projection of the obstacle in the first coordinate system is obtained as the target projection result; if the speed planning result is other, the lateral projection of the obstacle in the first coordinate system is added, and the lateral projection in the first coordinate system after adding the projection is obtained as the target projection result.

[0093] S209: Determine a second planned path of the vehicle in the target frame according to the target projection result; and determine a second coordinate system according to the second planned path.

[0094] S210 : Determine a second speed planning result of the vehicle in the target frame according to a projection of the obstacle in the longitudinal direction of the second coordinate system.

[0095] S211 : Control the vehicle to travel according to the second speed planning result and the second planned path.

[0096] Among them, the description of S209-S211 refers to the description of S106-S108 above and will not be repeated here.

[0097] See attached Figure 5 After obtaining valid information about the vehicle, which may include perception information, prediction information, positioning information, navigation information, and vehicle motion state information, the navigation line in the vehicle's navigation information is used as a reference line to generate an initial coordinate system, and the environmental information in the perception information is converted from the Cartesian coordinate system to the initial coordinate system.

[0098] Based on the velocity planning results of the vehicle in the previous frame of the target frame, all obstacles are dynamically simulated, and the longitudinal intervals of obstacles that intersect with the vehicle in the longitudinal space are predicted. The trajectories of obstacles parallel to the vehicle and in front of the vehicle corresponding to the longitudinal intervals are projected into the lateral space to generate the first round of lateral projections.

[0099] In the generated first round of lateral projections, a first round of path planning is performed, using a dynamic programming method to search for a rough solution and generate a convex space, and then a smooth path is generated using quadratic programming as the first planning path for the first round of path planning; the generated first planning path is used as a reference line to generate a first coordinate system; in the first coordinate system, obstacles on the first planning path are projected into the longitudinal space to generate a first round of longitudinal projections; in the generated first round of longitudinal projections, a first round of speed planning is performed, using a dynamic programming method to generate a first speed planning result for the first round of speed planning for overtaking or giving way to obstacles; based on the first speed planning result, an obstacle handling area is allocated to achieve addition and deletion operations on the projection of the lateral space, and a second round of lateral projections is generated.

[0100] In the generated second round of lateral projection, a second round of path planning is performed, and dynamic programming and quadratic programming are again used to generate a smooth path as the second planned path for the second round of path planning; a second coordinate system is generated based on the second planned path, and obstacles on the second planned path are projected into the longitudinal space to generate a second round of longitudinal projection; in the generated second round of longitudinal projection, a second round of speed planning is performed, and dynamic programming and quadratic programming methods are used to generate a second speed planning result for the second round of speed planning; the second planned path and the second speed planning result are matched to complete the driving trajectory generation, and the vehicle is controlled according to the driving trajectory.

[0101] In this embodiment, by performing two speed planning and two path planning within a single frame, the problem of mismatch between speed planning results and path planning results is solved, and the accuracy of vehicle local decision planning is improved. By correcting the projection in the second direction based on the first planned path and the first speed planning result, and then obtaining the second planned path and the second speed planning result according to the corrected projection, the movement of the obstacle in the second direction, the movement in the longitudinal direction, and the coupled movement in the longitudinal and second directions are distinguished, achieving full coverage of static and dynamic obstacles, and improving the flexibility of vehicle local decision planning. Finally, the vehicle is controlled according to the second planned path and the second speed planning result, thereby improving driving safety.

[0102] See attached Figure 6 , Figure 6 The following is a block diagram of a vehicle control device according to an embodiment of the present application, which is used in a vehicle. The device 300 includes:

[0103] A first determining module 301 is configured to determine a first planned path of the vehicle in the target frame based on a speed planning result of the vehicle in the frame preceding the target frame;

[0104] A second determining module 302 is configured to determine a first coordinate system according to the first planned path;

[0105] A third determining module 303 is configured to determine a first speed planning result of the vehicle in the target frame according to a projection of the obstacle in the longitudinal direction of the first coordinate system;

[0106] A correction module 304 is configured to correct the horizontal projection of the obstacle in the first coordinate system according to the first speed planning result to obtain a target projection result corresponding to the target obstacle, wherein the correction includes any one of adding, deleting, and retaining.

[0107] The fourth determining module 305 is used to determine a second planned path of the vehicle in the target frame according to the target projection result;

[0108] A fifth determining module 306 is configured to determine a second coordinate system according to the target projection result;

[0109] a sixth determining module 307, configured to determine a second speed planning result of the vehicle in the target frame according to a projection of the obstacle in the longitudinal direction of the second coordinate system;

[0110] The control module 308 is configured to control the vehicle to travel according to the second speed planning result and the second planned path.

[0111] Optionally, the correction module 304 is further configured to obtain a relative positional relationship between the obstacle and the vehicle in the longitudinal direction of the first coordinate system; determine a projection processing result of the obstacle based on the relative positional relationship and the first speed planning result; and correct the projection of the obstacle in the lateral direction in the first coordinate system based on the projection processing result to obtain a target projection result corresponding to the target obstacle.

[0112] Optionally, the correction module 304 is further configured to, when the relative position relationship is that the obstacle is in front of the vehicle, if the first speed planning result is no speed planning result or the first speed planning result is not an avoidance decision, determine that the projection processing result is to retain the obstacle's lateral projection in the first coordinate system; if the first speed planning result is an avoidance decision, determine that the projection processing result is to delete the obstacle's lateral projection in the first coordinate system; or, when the relative position relationship is that the obstacle is parallel to the vehicle, determine that the projection processing result is to retain the obstacle's lateral projection in the first coordinate system; or, when the relative position relationship is that the obstacle is behind the vehicle, if the first speed planning result is no speed planning result or the first speed planning result is not an overtaking decision, determine that the projection processing result is to add the obstacle's lateral projection in the first coordinate system; if the first speed planning result is an overtaking decision, determine that the projection processing result is to retain the obstacle's lateral projection in the first coordinate system.

[0113] Optionally, the first determination module 301 is further used to determine the longitudinal intersection interval corresponding to the obstacle in the longitudinal direction of the initial coordinate system based on the speed planning result corresponding to the frame before the target frame of the vehicle; project the trajectory of the target obstacle in the longitudinal intersection interval to the horizontal direction of the initial coordinate system to obtain the horizontal projection result of the target obstacle; and determine the first planned path of the vehicle in the target frame based on the horizontal projection result.

[0114] Optionally, the first determination module 301 is further used to dynamically plan the lateral projection result to obtain a rough planned path; determine a convex space based on the rough planned path; and perform secondary planning on the rough planned path based on the convex space to obtain a first planned path for the vehicle in the target frame.

[0115] Optionally, the control module 308 is further configured to match the second speed planning result and the second planned path to determine a corresponding driving trajectory of the vehicle; and control the vehicle to travel according to the driving trajectory.

[0116] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0117] In addition, the functions in the various embodiments of the present application may be integrated into a single processing module, or each module may exist physically separately, or two or more modules may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or software functional modules.

[0118] On the other hand, the present application also provides a computer-readable storage medium, which stores program code. The program code can be called by a processor to execute the method described in the above method embodiment.

[0119] The computer-readable storage medium can be an electronic memory such as a flash memory, an EEPROM (Electrically Erasable Programmable Read-Only Memory), an EPROM, a hard disk, or a cluster of ROMs. Alternatively, the computer-readable storage medium includes a non-transitory computer-readable storage medium. The computer-readable storage medium has storage space for program codes for executing any of the method steps of the above-described method. These program codes can be read from or written to one or more computer program products. The program codes can be compressed, for example, in an appropriate form.

[0120] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A vehicle control method, characterized in that: The method comprises: Determining a first planned path of the vehicle in the target frame according to a speed planning result corresponding to a frame previous to the target frame; Determining a first coordinate system according to the first planned path; Determining a first speed planning result of the vehicle in the target frame according to a projection of the obstacle in the longitudinal direction of the first coordinate system; Correcting the projection of the obstacle in the lateral direction of the first coordinate system according to the first speed planning result to obtain a target projection result corresponding to the target obstacle, wherein the correction includes any one of adding, deleting, and retaining; Determining a second planned path of the vehicle under the target frame according to the target projection result; Determining a second coordinate system according to the second planned path; Determining a second speed planning result of the vehicle in the target frame according to a projection of the obstacle in the longitudinal direction of the second coordinate system; The vehicle is controlled to travel according to the second speed planning result and the second planned path.

2. The method according to claim 1, characterized in that The step of correcting the horizontal projection of the obstacle in the first coordinate system according to the first speed planning result to obtain a target projection result corresponding to the target obstacle includes: Obtaining a relative positional relationship between the obstacle and the vehicle in the longitudinal direction of the first coordinate system; Determining a projection processing result of the obstacle according to the relative position relationship and the first speed planning result; The lateral projection of the obstacle in the first coordinate system is corrected according to the projection processing result to obtain a target projection result corresponding to the target obstacle.

3. The method according to claim 2, characterized in that The determining, based on the relative position relationship and the first speed planning result, a projection processing result of the obstacle includes: In a case where the relative position relationship is that the obstacle is in front of the vehicle, if the first speed planning result is no speed planning result or the first speed planning result is not an avoidance decision, determining a projection processing result as retaining the projection of the obstacle in the lateral direction of the first coordinate system; if the first speed planning result is an avoidance decision, determining a projection processing result as deleting the projection of the obstacle in the lateral direction of the first coordinate system; or In a case where the relative position relationship is that the obstacle is parallel to the vehicle, determining the projection processing result to retain the projection of the obstacle in the lateral direction of the first coordinate system; or In a case where the relative position relationship is that the obstacle is behind the vehicle, if the first speed planning result is no speed planning result or the first speed planning result is not an overtaking decision, the projection processing result is determined to be to add a projection of the obstacle in the lateral direction of the first coordinate system; if the first speed planning result is an overtaking decision, the projection processing result is determined to be to retain the projection of the obstacle in the lateral direction of the first coordinate system.

4. The method according to claim 1, wherein Determining a first planned path of the vehicle in the target frame according to a speed planning result corresponding to a frame before the target frame includes: Determining a longitudinal intersection interval corresponding to the obstacle in the longitudinal direction of the initial coordinate system according to a velocity planning result of the vehicle corresponding to a frame preceding the target frame; Projecting the trajectory of a target obstacle among the obstacles within the longitudinal intersection interval onto the lateral direction of the initial coordinate system to obtain a lateral projection result of the target obstacle; A first planned path of the vehicle in the target frame is determined according to the lateral projection result.

5. The method according to claim 4, characterized in that Determining a first planned path of the vehicle in the target frame according to the lateral projection result includes: Performing dynamic planning on the lateral projection result to obtain a rough planning path; determining a convex space according to the rough planning path; According to the convex space, secondary planning is performed on the roughly planned path to obtain a first planned path of the vehicle in the target frame.

6. The method according to claim 1, characterized in that The controlling the vehicle to travel according to the second speed planning result and the second planned path includes: Matching the second speed planning result and the second planned path to determine a corresponding driving trajectory of the vehicle; The vehicle is controlled to travel according to the driving trajectory.

7. A vehicle control device, characterized in that: The device comprises: A first determining module is configured to determine a first planned path of the vehicle in the target frame according to a speed planning result corresponding to a frame preceding the target frame; A second determining module, configured to determine a first coordinate system according to the first planned path; a third determining module, configured to determine a first speed planning result of the vehicle in the target frame according to a projection of the obstacle in the longitudinal direction of the first coordinate system; a correction module, configured to correct the projection of the obstacle in the lateral direction of the first coordinate system according to the first speed planning result to obtain a target projection result corresponding to the target obstacle, wherein the correction includes any one of adding, deleting, and retaining; a fourth determining module, configured to determine a second planned path of the vehicle in the target frame according to the target projection result; a fifth determining module, configured to determine a second coordinate system according to the target projection result; a sixth determining module, configured to determine a second speed planning result of the vehicle in the target frame according to a projection of the obstacle in the longitudinal direction of the second coordinate system; A control module is used to control the vehicle to travel according to the second speed planning result and the second planned path.

8. A vehicle, characterized in that: The vehicle comprises: one or more processors; Memory; One or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores program codes executable by a processor, and when the program codes are executed by the processor, the processor executes the method according to any one of claims 1 to 6.

Images