CN117400945B

CN117400945B - Vehicle control method and device based on monocular vision information

Info

Publication number: CN117400945B
Application number: CN202311726627.0A
Authority: CN
Inventors: 叶家盛; 黎润东; 伊海霞; 张恩硕; 关方明
Original assignee: GAC Aion New Energy Automobile Co Ltd
Current assignee: GAC Aion New Energy Automobile Co Ltd
Priority date: 2023-12-15
Filing date: 2023-12-15
Publication date: 2024-02-23
Anticipated expiration: 2043-12-15
Also published as: CN117400945A

Abstract

A vehicle control method and device based on monocular vision information comprises the following steps: monocular visual information is acquired through a monocular camera; carrying out path planning according to a quintic polynomial planning algorithm, a path planning preset value and monocular vision information to obtain a planned path set; screening a target planning path according to the planning longitudinal distance gradient and the limiting condition; calculating position course angle information of a planning point of a vehicle coordinate system and a transverse position coordinate and a longitudinal position coordinate under a world coordinate system according to a real-time course angle of a target (calculated according to a course angle and a course angle difference value of a target vehicle) and a target planning path; calculating the front wheel corner of the vehicle according to the position course angle information of the planning point and the horizontal and vertical position coordinates; and tracking control operation is carried out on the target vehicle according to the front wheel corner of the vehicle. Therefore, the method and the device can plan the real-time path and control the corresponding vehicle based on the monocular camera, thereby being beneficial to improving the overall efficiency of planning control and enhancing the safety of the operation process.

Description

Vehicle control method and device based on monocular vision information

Technical Field

The application relates to the technical field of whole vehicle control, in particular to a vehicle control method and device based on monocular vision information.

Background

Currently, prior art vehicles are route planned by a route planning module. The driving path planning is divided into global planning and local planning, and the existing path planning control method is generally combined with real-time path planning realized by a high-precision map and GPS positioning and performs corresponding control. However, in practice, the existing method is found to depend on a high-precision map and a GPS positioning technology, so that the method is difficult to realize in an area which is not covered by traffic infrastructure and low-delay communication, and the GPS positioning is low in accuracy, large in error and high in delay, so that a larger error occurs in path planning control.

Disclosure of Invention

An object of the embodiment of the application is to provide a vehicle control method and device based on monocular vision information, which can plan a real-time path and control a corresponding vehicle based on a monocular camera, and has the advantages of high accuracy, small error and small delay, thereby being beneficial to improving the overall efficiency of planning control and enhancing the safety of an operation process.

The first aspect of the application provides a vehicle control method based on monocular vision information, which comprises the following steps:

monocular visual information is acquired through a monocular camera on a target vehicle;

carrying out path planning according to a preset quintic polynomial planning algorithm, a preset path planning preset value and the monocular vision information to obtain a planned path set;

performing path screening on the planned path set based on a preset planned longitudinal distance gradient and a preset limiting condition to obtain a target planned path;

acquiring a course angle of the target vehicle under a vehicle coordinate system, a course angle difference value of a front and rear moment lane line relative to the vehicle coordinate system and a real-time vehicle speed of the target vehicle;

calculating a real-time heading angle of the target according to the heading angle of the target vehicle and the heading angle difference value;

calculating position course angle information of a planning point based on the vehicle coordinate system and a transverse and longitudinal position coordinate of the target vehicle under a world coordinate system according to the target real-time course angle and the target planning path;

calculating the front wheel corner of the vehicle according to the position course angle information of the planning point and the transverse and longitudinal position coordinates;

and carrying out tracking control operation on the target vehicle according to the front wheel corner of the bicycle.

Further, the monocular visual information at least includes a lane line, a front obstacle, vehicle information of the target vehicle, a heading angle of the target vehicle under a vehicle-by-vehicle coordinate system, a real-time curvature value of the lane line, a curvature change rate of the lane line, a lateral deviation of the lane line from the target vehicle, and a lane line strength.

Further, the path planning preset value comprises a preset longitudinal distance lower limit threshold value, a longitudinal distance upper limit threshold value, a distance interval value and a longitudinal distance planning value.

Further, after calculating the target real-time heading angle according to the heading angle of the target vehicle and the heading angle difference value, the vehicle control method further includes:

and carrying out correction calculation on the target real-time course angle according to the real-time curvature value of the lane line to obtain a corrected target real-time course angle.

Further, the calculating, according to the target real-time heading angle and the target planned path, the heading angle information of the planned point position based on the vehicle coordinate system and the horizontal and vertical position coordinates of the target vehicle in the world coordinate system includes:

calculating the transverse and longitudinal position coordinates of the target vehicle under a world coordinate system through a preset vehicle kinematic model and the target real-time course angle;

and calculating the position course angle information of the planning point based on the vehicle coordinate system according to the fifth-order polynomial planning algorithm and the target planning path.

Further, the calculating the front wheel corner of the target vehicle according to the planned point position course angle information and the transverse and longitudinal position coordinates comprises the following steps:

according to the position course angle information of the planning points and the transverse and longitudinal position coordinates, calculating the transverse deviation between the target vehicle and the target planning path, the relative course angle of the target vehicle and the target planning path, the curvature of each path point of the target planning path and the curvature change rate of each path point of the target planning path;

and calculating the front wheel corner of the target vehicle according to the curvature of each path point of the target planning path, the real-time vehicle speed, the transverse deviation and the relative course angle.

A second aspect of the present application provides a vehicle control device based on monocular visual information, the vehicle control device based on monocular visual information including:

the acquisition unit is used for acquiring monocular visual information through a monocular camera on the target vehicle;

the path planning unit is used for carrying out path planning according to a preset penta polynomial planning algorithm, a preset path planning preset value and the monocular vision information to obtain a planned path set;

the path screening unit is used for screening the paths of the planned path set based on a preset planned longitudinal distance gradient and a preset limiting condition to obtain a target planned path;

the system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring a course angle of the target vehicle under a self-vehicle coordinate system, a course angle difference value of a front and rear time lane line relative to the self-vehicle coordinate system and a real-time vehicle speed of the target vehicle;

the first calculation unit is used for calculating a target real-time course angle according to the course angle of the target vehicle and the course angle difference value;

the second calculation unit is used for calculating position course angle information of a planning point based on the vehicle coordinate system and the transverse and longitudinal position coordinates of the target vehicle under the world coordinate system according to the target real-time course angle and the target planning path;

a third calculation unit for calculating the front wheel corner of the target vehicle according to the position course angle information of the planning point and the transverse and longitudinal position coordinates;

and the control unit is used for carrying out tracking control operation on the target vehicle according to the front wheel corner of the bicycle.

Further, the first calculation unit is further configured to perform correction calculation on the target real-time heading angle according to the real-time curvature value of the lane line, so as to obtain a corrected target real-time heading angle.

Further, the second calculating unit is specifically configured to calculate, through a preset vehicle kinematic model and the target real-time heading angle, a horizontal-vertical position coordinate of the target vehicle in a world coordinate system;

the second calculation unit is specifically configured to calculate, according to the fifth order polynomial planning algorithm and the target planning path, position and heading angle information of a planned point based on a vehicle coordinate system.

Further, the third calculation unit is specifically configured to calculate, according to the planned point position and heading angle information and the horizontal and vertical position coordinates, a lateral deviation between the target vehicle and the target planned path, a relative heading angle between the target vehicle and the target planned path, a curvature of each path point of the target planned path, and a curvature change rate of each path point of the target planned path;

the third calculation unit is specifically further configured to calculate a front wheel corner of the target vehicle according to the curvature of each path point of the target planned path, the real-time vehicle speed, the lateral deviation, and the relative heading angle.

A third aspect of the present application provides an electronic device comprising a memory for storing a computer program and a processor that runs the computer program to cause the electronic device to execute the method of monocular vision information-based vehicle control of any one of the first aspect of the present application.

A fourth aspect of the present application provides a computer readable storage medium storing computer program instructions which, when read and executed by a processor, perform the method of vehicle control based on monocular visual information as set forth in any one of the first aspects of the present application.

The beneficial effects of this application are: the method and the device can carry out real-time path planning and corresponding vehicle control based on the monocular camera, have high accuracy and small error and delay, thereby being beneficial to improving the overall efficiency of planning control and enhancing the safety of the operation process.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a schematic flow chart of a vehicle control method based on monocular visual information according to an embodiment of the present application;

fig. 2 is a schematic flow chart of another vehicle control method based on monocular visual information according to an embodiment of the present application;

fig. 3 is a schematic structural diagram of a vehicle control device based on monocular visual information according to an embodiment of the present application;

fig. 4 is a schematic structural diagram of another vehicle control device based on monocular visual information according to an embodiment of the present application;

fig. 5 is an exemplary schematic diagram of a coordinate system conversion process applied by a vehicle control method based on monocular vision information according to an embodiment of the present application;

FIG. 6 is an overall framework diagram of a classical MPC model provided in an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.

It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.

Example 1

Referring to fig. 1, fig. 1 is a flow chart of a vehicle control method based on monocular vision information according to the present embodiment. The vehicle control method based on the monocular vision information comprises the following steps:

s101, monocular visual information is collected through a monocular camera on a target vehicle.

In this embodiment, the monocular visual information includes at least a lane line, a front obstacle, vehicle information of the target vehicle, a heading angle of the target vehicle in the own vehicle coordinate system, a real-time curvature value of the lane line, a curvature change rate of the lane line, a lateral deviation of the lane line from the target vehicle, and a lane line strength.

S102, path planning is carried out according to a preset quintic polynomial planning algorithm, a preset path planning preset value and monocular vision information, and a planned path set is obtained.

In this embodiment, the path planning preset value includes a preset longitudinal distance lower limit threshold, a longitudinal distance upper limit threshold, a distance interval value, and a longitudinal distance planning value.

And S103, carrying out path screening on the planned path set based on a preset planned longitudinal distance gradient and a preset limiting condition to obtain a target planned path.

In the present embodiment, the restriction conditions include at least an acceleration restriction condition and a lateral acceleration.

S104, acquiring a course angle of the target vehicle under the own vehicle coordinate system, a course angle difference value of a front and rear time lane line relative to the own vehicle coordinate system and a real-time vehicle speed of the target vehicle.

S105, calculating the real-time heading angle of the target according to the heading angle and the heading angle difference value of the target vehicle.

S106, calculating position course angle information of a planning point based on a vehicle coordinate system and the transverse and longitudinal position coordinates of the target vehicle under a world coordinate system according to the target real-time course angle and the target planning path.

And S107, calculating the front wheel corner of the vehicle according to the position course angle information of the planning point and the transverse and longitudinal position coordinates.

S108, tracking control operation is carried out on the target vehicle according to the front wheel rotation angle of the vehicle.

In the embodiment, the method can obtain real-time position information and course angle information of the vehicle under a world coordinate system through visual information acquired by the monocular camera. The method adopts a solution of firstly planning a polynomial of the next five times of a vehicle coordinate system and then carrying out subsequent coordinate system conversion work when facing the problem.

In this embodiment, the execution subject of the method may be a computing device such as a computer or a server, which is not limited in this embodiment.

In this embodiment, the execution body of the method may be an intelligent device such as a smart phone or a tablet computer, which is not limited in this embodiment.

Therefore, by implementing the vehicle control method based on monocular vision information described in the embodiment, the compatibility of a single camera scheme can be improved, so that enterprises can consider the software design of the related functions of vehicle planning control under the single camera scheme; meanwhile, under the condition that sensors such as a radar and the like are damaged or misplaced, the single camera is used for independently supporting the continuous operation of the planning control function, the overall efficiency of the planning control is improved, and the safety of the operation process is enhanced; finally, when satellite signals are interfered or shielded in a specific environment, the positioning of the vehicle position information can be completed through the camera, so that the loophole of the vehicle positioning mode is filled to a certain extent, and the approximate position information of the vehicle can be obtained through the camera even if the satellite positioning is invalid.

Example 2

Referring to fig. 2, fig. 2 is a flow chart of a vehicle control method based on monocular visual information according to the present embodiment. The vehicle control method based on the monocular vision information comprises the following steps:

s201, monocular visual information is collected through a monocular camera on a target vehicle.

In this embodiment, the monocular visual information includes at least a lane line, a front obstacle, vehicle information of the target vehicle, a heading angle of the target vehicle in the own vehicle coordinate system, a real-time curvature value of the lane line, a curvature change rate of the lane line, a lateral deviation of the lane line from the target vehicle, and a lane line strength. Wherein, the information needs to be updated in real time so as to improve the accuracy of calculating the position information of the vehicle.

In this embodiment, the method may capture information of the lane line (including information of the lane line based on heading angle in the vehicle's own coordinate system, curvature of the lane line, curvature change rate, lateral deviation from the vehicle, strength of the lane line, etc.), information of the obstacle ahead, information of the vehicle, etc. by a single smart camera disposed behind the vehicle windshield.

In this embodiment, the method can capture the dynamic change of the lane line in real time by switching the lateral deviation. At present, when a vehicle performs lane change and other lane crossing operations, the change of a reference lane line can cause the jump of curvature, course angle and other information to cause larger errors in subsequent calculation; based on the method, the reference lane line can be kept when the lane line crossing action is carried out, so that the reference lane line before and after the lane line crossing is ensured to be unchanged and the numerical value is ensured not to jump.

S202, acquiring a path planning preset value.

In this embodiment, the path planning preset values include a preset longitudinal distance lower limit threshold, a longitudinal distance upper limit threshold, a distance interval value, and a longitudinal distance planning value.

S203, planning the driving path according to a preset penta polynomial planning algorithm, monocular vision information and a path planning preset value to obtain a planned path set.

S204, carrying out path screening on the planned path set based on a preset planned longitudinal distance gradient and a preset limiting condition to obtain a target planned path.

In this embodiment, the method may plan a feasible path that meets the kinematic constraint and the comfort principle by using a fifth-order polynomial, and the own vehicle performs the control tracking operation according to the path.

In this embodiment, the method is different from the ordinary quintic polynomial programming in performing path screening based on time gradient in that: the method carries out path screening based on planning longitudinal distance gradient, and the planning duration is fixed at a reasonable time; meanwhile, in the planning process, a lower limit threshold value, an upper limit threshold value and a proper distance interval value of the longitudinal distance can be set, and then a gradually-increased longitudinal distance planning value is input for path planning. In addition, the planning result can be judged according to limiting conditions such as acceleration, transverse acceleration and the like, so that a path meeting the setting requirement is screened out and then is output to a subsequent coordinate system conversion flow.

S205, acquiring a course angle of the target vehicle under the own vehicle coordinate system, a course angle difference value of a front and rear time lane line relative to the own vehicle coordinate system and a real-time vehicle speed of the target vehicle.

S206, calculating the real-time course angle of the target according to the course angle and the course angle difference value of the target vehicle.

S207, correcting and calculating the target real-time course angle according to the real-time curvature value of the lane line to obtain the corrected target real-time course angle.

S208, calculating the transverse and longitudinal position coordinates of the target vehicle under the world coordinate system through a preset vehicle kinematic model and the target real-time course angle.

S209, calculating the position course angle information of the planning point based on the vehicle coordinate system according to the fifth-order polynomial planning algorithm and the target planning path.

S210, calculating the transverse deviation between the target vehicle and the target planning path, the relative course angle of the target vehicle and the target planning path, the curvature of each path point of the target planning path and the curvature change rate of each path point of the target planning path according to the position course angle information of the planning point and the transverse and longitudinal position coordinates.

S211, calculating the front wheel corner of the target vehicle according to the curvature, the real-time vehicle speed, the transverse deviation and the relative course angle of each path point of the target planning path.

At present, the general method is that the course angle based on the camera sensing module is output to the course angle calculation module of the own vehicle, and then the course angle information of the own vehicle under the real-time world coordinate system is calculated by the course angle calculation module of the own vehicle based on the course angle difference value of the lane line relative to the own vehicle coordinate system at the front and rear moments. The calculation process can generate a larger error in a curve scene, because the course angle of the lane line changes caused by a large part of lane line curvature changes besides the change value relative to the vehicle in the curve driving process.

Based on the above, the application provides a method for performing course angle correction calculation by utilizing a real-time curvature value of a lane line acquired by a camera in a self-vehicle course angle calculation module, and the error of course angle calculation is reduced to an acceptable range. Specifically, the method can firstly obtain the course angle of the own vehicle under the world coordinate system, then calculate the horizontal and vertical position coordinates under the vehicle world coordinate system through the vehicle kinematics model, simultaneously access the planned point position course angle information based on the own vehicle coordinate system of the penta polynomial programming, and uniformly convert the information into the world coordinate system according to the geometric relationship of the two-dimensional coordinate system in the coordinate system conversion module, thereby outputting the horizontal deviation between the own vehicle and the planned path, the relative course angle between the own vehicle and the planned path, and the curvature and curvature change rate of each path point of the planned path. Wherein, the information can be used in the follow-up control tracking module.

Referring to fig. 5, fig. 5 shows an exemplary schematic diagram of a coordinate system conversion process in the present application.

S212, tracking control operation is carried out on the target vehicle according to the front wheel rotation angle of the vehicle.

In this embodiment, the method may be implemented based on a classical MPC model. The implementation principle of the MPC model is as follows: and controlling the transverse error and the course angle deviation to be attached to a specified path for tracking control. Specifically, the model needs to input a path curvature, a vehicle speed, a vehicle-to-path lateral deviation and a vehicle-to-path relative course angle, output a corresponding vehicle front wheel corner, and then complete tracking control operation of the vehicle by controlling the vehicle front wheel corner and the vehicle corresponding speed.

Referring to fig. 6, fig. 6 shows an overall frame diagram of one of the above models.

Example 3

Referring to fig. 3, fig. 3 is a schematic structural diagram of a vehicle control device based on monocular visual information according to the present embodiment. As shown in fig. 3, the vehicle control apparatus based on monocular visual information includes:

an acquisition unit 310 for acquiring monocular visual information through a monocular camera on a target vehicle;

the path planning unit 320 is configured to perform path planning according to a preset quintic polynomial planning algorithm, a preset path planning preset value and monocular vision information, so as to obtain a planned path set;

the path screening unit 330 is configured to perform path screening on the planned path set based on a preset planned longitudinal distance gradient and a preset constraint condition, so as to obtain a target planned path;

an acquiring unit 340, configured to acquire a heading angle of the target vehicle in the own vehicle coordinate system, a heading angle difference value of a lane line at front and rear moments relative to the own vehicle coordinate system, and a real-time vehicle speed of the target vehicle;

a first calculating unit 350, configured to calculate a real-time heading angle of the target according to the heading angle and the heading angle difference value of the target vehicle;

a second calculating unit 360, configured to calculate, according to the real-time heading angle of the target and the planned path of the target, heading angle information of the planned point based on the own vehicle coordinate system and the horizontal and vertical position coordinates of the target vehicle in the world coordinate system;

a third calculation unit 370 for calculating a bicycle front wheel corner of the target vehicle according to the planned point heading angle information and the horizontal-vertical position coordinates;

and a control unit 380 for performing a tracking control operation on the target vehicle according to the front wheel rotation angle of the vehicle.

In this embodiment, the explanation of the vehicle control device based on monocular vision information may refer to the description in embodiment 1 or embodiment 2, and a detailed description is not repeated in this embodiment.

Therefore, by implementing the vehicle control device based on monocular vision information described in the embodiment, the compatibility of a single camera scheme can be improved, so that enterprises can consider the software design of the related functions of vehicle planning control under the single camera scheme; meanwhile, under the condition that sensors such as a radar and the like are damaged or misplaced, the single camera is used for independently supporting the continuous operation of the planning control function, the overall efficiency of the planning control is improved, and the safety of the operation process is enhanced; finally, when satellite signals are interfered or shielded in a specific environment, the positioning of the vehicle position information can be completed through the camera, so that the loophole of the vehicle positioning mode is filled to a certain extent, and the approximate position information of the vehicle can be obtained through the camera even if the satellite positioning is invalid.

Example 4

Referring to fig. 4, fig. 4 is a schematic structural diagram of a vehicle control device based on monocular visual information according to the present embodiment. As shown in fig. 4, the vehicle control apparatus based on monocular visual information includes:

As an optional implementation manner, the first calculating unit 350 is further configured to perform correction calculation on the target real-time heading angle according to the real-time curvature value of the lane line, so as to obtain a corrected target real-time heading angle.

As an optional implementation manner, the second calculating unit 360 is specifically configured to calculate, through a preset vehicle kinematic model and a target real-time heading angle, a horizontal-vertical position coordinate of the target vehicle in a world coordinate system;

the second calculating unit 360 is specifically further configured to calculate the position and heading angle information of the planned point based on the vehicle coordinate system according to the fifth order polynomial planning algorithm and the target planned path.

As an optional implementation manner, the third calculating unit 370 is specifically configured to calculate, according to the course angle information of the planned point location and the coordinates of the lateral deviation between the target vehicle and the target planned path, the relative course angle between the target vehicle and the target planned path, the curvature of each path point of the target planned path, and the curvature change rate of each path point of the target planned path;

the third calculation unit 370 is specifically further configured to calculate the front wheel corner of the target vehicle according to the curvature, the real-time vehicle speed, the lateral deviation, and the relative heading angle of each path point of the target planned path.

An embodiment of the present application provides an electronic device, including a memory and a processor, where the memory is configured to store a computer program, and the processor is configured to execute the computer program to cause the electronic device to execute a vehicle control method based on monocular visual information in embodiment 1 or embodiment 2 of the present application.

The present embodiment provides a computer-readable storage medium storing computer program instructions that, when read and executed by a processor, perform the vehicle control method based on monocular visual information in embodiment 1 or embodiment 2 of the present application.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other manners as well. The apparatus embodiments described above are merely illustrative, for example, flow diagrams and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

In addition, the functional modules in the embodiments of the present application may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single part.

The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

The foregoing is merely exemplary embodiments of the present application and is not intended to limit the scope of the present application, and various modifications and variations may be suggested to one skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application. It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.

The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

Claims

1. A vehicle control method based on monocular visual information, comprising:

2. The monocular vision information-based vehicle control method according to claim 1, wherein the monocular vision information includes at least a lane line, a front obstacle, vehicle information of the target vehicle, a heading angle of the target vehicle in a vehicle coordinate system, a real-time curvature value of the lane line, a curvature change rate of the lane line, a lateral deviation of the lane line from the target vehicle, and a lane line pixel intensity.

3. The monocular vision information-based vehicle control method according to claim 1, wherein the path planning preset values include a preset longitudinal distance lower limit threshold, a longitudinal distance upper limit threshold, a distance interval value, and a longitudinal distance planning value.

4. The monocular vision information-based vehicle control method according to claim 1, wherein after calculating a target real-time heading angle from a heading angle of the target vehicle and the heading angle difference value, the vehicle control method further comprises:

5. The monocular vision information-based vehicle control method according to claim 1, wherein the calculating of planned point position heading angle information based on the own vehicle coordinate system and the horizontal-vertical position coordinates of the target vehicle in the world coordinate system from the target real-time heading angle and the target planned path includes:

6. The monocular vision information-based vehicle control method according to claim 1, wherein the calculating the own front wheel turning angle of the target vehicle from the planned point position heading angle information and the abscissa and ordinate includes:

7. A vehicle control device based on monocular visual information, characterized in that the vehicle control device based on monocular visual information includes:

8. The monocular vision information-based vehicle control apparatus according to claim 7, wherein the path planning preset values include a preset longitudinal distance lower limit threshold, a longitudinal distance upper limit threshold, a distance interval value, and a longitudinal distance planning value.

9. An electronic device comprising a memory for storing a computer program and a processor that runs the computer program to cause the electronic device to execute the monocular vision information-based vehicle control method according to any one of claims 1 to 6.

10. A readable storage medium, wherein computer program instructions are stored in the readable storage medium, which when read and executed by a processor, perform the monocular vision information-based vehicle control method of any one of claims 1 to 6.