CN115465270A

CN115465270A - Vehicle control system, route optimization method, apparatus, vehicle, and medium

Info

Publication number: CN115465270A
Application number: CN202211415681.9A
Authority: CN
Inventors: 廖江
Original assignee: Jidu Technology Co ltd
Current assignee: Beijing Jidu Technology Co Ltd
Priority date: 2022-11-11
Filing date: 2022-11-11
Publication date: 2022-12-13
Anticipated expiration: 2042-11-11
Also published as: CN115465270B

Abstract

The embodiment of the application provides a vehicle control system, a path optimization method, a path optimization device, a vehicle and a medium. The system comprises: the controller is used for acquiring the pose information of the target vehicle and determining the relative distance between the target vehicle and the lane center line according to the pose information; determining the command type of a vehicle driving direction control command; determining a course angle threshold value and a planned path during path planning according to the instruction type and the relative distance; and executing the vehicle driving direction control instruction based on the planned path and the heading angle threshold value. In the process of planning the path, the planned path can be optimized by using a pre-calibrated path optimization model, so that the planned path with higher accuracy and better continuity is obtained. The vehicle can realize automatic driving more accurately according to the optimized planned path.

Description

Vehicle control system, route optimization method, apparatus, vehicle, and medium

Technical Field

The present application relates to the field of vehicle control technologies, and in particular, to a vehicle control system, a path optimization method, a device, a vehicle, and a medium.

Background

With the development of vehicle technology, vehicles may be driven by vehicle assistant persons or automatically driven by vehicles, in addition to being driven by occupants themselves.

When the vehicle is in the automatic driving mode, whether the path can be accurately planned is particularly important for the automatic driving effect of the vehicle. In other words, the more accurate the path planning of the vehicle during autonomous driving, the better the stability of the autonomous driving of the vehicle. However, in practical applications, due to the complex and variable environment, it is difficult for the controller to accurately execute the driving task according to the control command during the process of controlling the vehicle to execute the driving task.

Disclosure of Invention

The embodiment of the application provides a vehicle control system, a path optimization method, a path optimization device, a vehicle and a medium, and aims to improve the success rate and continuity of path planning.

In a first aspect, an embodiment of the present application provides a vehicle control system, including:

the controller is used for acquiring the pose information of the target vehicle and determining the relative distance between the target vehicle and the lane center line according to the pose information;

determining the instruction type of the vehicle driving direction control instruction;

determining a course angle threshold value and a planned path during path planning according to the instruction type and the relative distance;

and executing the vehicle driving direction control command based on the planned path and the heading angle threshold.

When the vehicle is controlled, different path planning modes are adopted according to the instruction types of the control instructions of different vehicle driving directions. Specifically, the planned path is optimized and adjusted according to the heading angle threshold value when the path is planned, and therefore the vehicle driving direction control command is executed based on the optimized planned path.

Optionally, the controller is further configured to: determining a corresponding path optimization model according to the instruction type;

and determining a course angle threshold value corresponding to the relative distance based on the path optimization model.

When the path is planned, a proper path optimization model is selected according to specific requirements, and then the planned path is further optimized by using a course angle threshold determined by the path optimization model. Therefore, the optimized planning path has better continuity, the path planning success rate is better, and passengers in the cabin can obtain more stable and comfortable riding experience.

Optionally, the determining a path optimization model of the target vehicle in the lane comprises:

if the target vehicle does not receive the driving direction adjusting instruction, determining the path optimization model in the lane as a lane keeping model;

and if the target vehicle receives the driving direction adjusting instruction, determining that the path optimization model in the lane is a lane-changing driving model.

In practical application, corresponding path optimization models can be selected for different driving scenes. In the scheme of the application, the path planning and the optimization are realized according to the center line of the lane. In different driving scenes, the roles of the lane central lines in planning the paths are different. Therefore, a targeted path optimization model can be selected to achieve better optimization effect.

Optionally, the determining, based on the path optimization model, a heading angle threshold corresponding to the relative distance includes:

determining a planned path and a planned course angle of the target vehicle on the planned path at each moment;

and determining a course angle threshold value corresponding to the relative distance based on the corresponding relation obtained by pre-calibration in the path optimization model.

In practical applications, the path of the target vehicle in the lane is frequently corrected, planned and adjusted. Therefore, when the course angle threshold is determined, the corresponding relative distance and the planned course angle need to be determined in real time according to the actual planned path, and then an accurate course angle threshold is determined, so that the planned course angle can be optimized and adjusted by using the course angle threshold, and a more accurate path optimization and adjustment result is obtained.

Optionally, the optimizing the planned path based on the heading angle threshold includes:

and when the planned course angle is larger than the course angle threshold value, correcting the planned course angle according to a preset correction rule so as to execute the planned path based on the corrected course angle.

In practical application, when the planned course angle is larger than the course angle threshold, it indicates that the planned path of the target vehicle in the current scene is not good, which may cause poor continuity of path planning or failure of path planning, and therefore the planned path needs to be optimized. During optimization, the planned course angle can be modified according to a preset modification rule, for example, the planned course angle can be directly replaced by the course angle threshold value, so that optimization of the planned path is realized. The optimization method is simple and direct, the calculation cost is saved, and the optimization speed is higher. In addition, the course angle threshold is determined by using a pre-calibrated path optimization model instead of being artificially defined, so that the course angle threshold is more accurate and closer to the correction requirement of the planned course angle.

Optionally, the determining the relative distance of the target vehicle from the lane center line comprises:

acquiring adjacent lane marking lines on the left side and the right side of the target vehicle;

determining the lane central line based on the adjacent lane marking lines on the left side and the right side;

and determining the relative distance according to the position of the target vehicle in the lane and the position of the lane central line in the lane.

In practical application, a lane center line can be calculated based on lane marking lines on two sides of the vehicle, and when a path is planned, the path of the target vehicle can be planned based on the lane center line, so that the vehicle can run in a safe space. In addition, the adjacent lane marking lines on the two sides of the vehicle can be various marking lines, for example, marking lines which are actually planned artificially, or road teeth and the like can be used as the lane marking lines, so that lane center lines can be obtained in various scenes, and relative distances can be determined. So that the scheme of determining relative distance is applicable to various complex scenes.

Optionally, the calibrating method of the path optimization model includes:

determining at least one calibrated distance between the target vehicle and the lane center line;

executing a path planning task based on the calibration distance;

when the path planning task fails to be executed, the critical course angle between the target vehicle and the lane central line is the course angle threshold value;

and generating the path optimization model based on the corresponding relation between at least one calibration distance and the heading angle threshold value.

In practical application, the critical course angle of the course angle when the path planning succeeds and fails, namely the course angle threshold value, is determined in the path planning process, so that the problem of path planning failure can be avoided as far as possible as long as the planned course angle is ensured within the range of the heading angle threshold value, and the continuity of the planned path is better. The course angles of a plurality of calibration distances can be calibrated according to the requirement, so that a better calibration effect is obtained.

Optionally, the determining at least one calibrated distance of the target vehicle from the lane centerline comprises:

if the path optimization model to be calibrated is the lane keeping model, determining at least one calibration distance between the target vehicle and the lane center line based on a first calibration sequence;

and if the path optimization model to be calibrated is the lane-changing driving model, determining at least one calibration distance between the target vehicle and the lane center line based on a second calibration sequence.

When calibration is carried out, different calibration sequences can be adopted for different types of models for calibration, so that the models obtained by calibration are more accurate, and a better optimization effect for a specific scene can be realized.

Optionally, the generating the path optimization model based on at least one of the calibration distances and the corresponding heading angle threshold includes:

generating an initial optimization model based on at least one calibration distance and the corresponding course angle threshold;

and optimizing the initial optimization model by using a linear difference algorithm to obtain the path optimization model.

In the calibration process, the initial optimization model is optimized by using optimization processing modes such as a linear difference algorithm and the like, the obtained path optimization model has better continuity, and the processing effect obtained in the subsequent path optimization processing process is better.

In a second aspect, an embodiment of the present application provides a vehicle control method, including:

acquiring pose information of a target vehicle, and determining the relative distance between the target vehicle and the lane center line according to the pose information;

and executing the vehicle driving direction control instruction based on the planned path and the heading angle threshold value.

In a third aspect, an embodiment of the present application provides a path optimization method, including:

determining a path optimization model in response to the driving direction adjustment instruction;

determining the relative distance between the target vehicle and the center line of the lane and the current course angle;

determining a course angle threshold corresponding to the relative distance based on the path optimization model;

determining a predicted course angle of the next moment in the planned path;

and when the angle difference between the predicted course angle and the current course angle is larger than a difference threshold value, correcting the predicted course angle based on the course angle threshold value.

In a fourth aspect, an embodiment of the present application provides a vehicle control apparatus including:

the first determination module is used for acquiring pose information of the target vehicle and determining the relative distance between the target vehicle and the lane center line according to the pose information;

the second determination module is used for determining the instruction type of the vehicle driving direction control instruction;

the third determining module is used for determining a course angle threshold value and a planned path during path planning according to the instruction type and the relative distance;

and the execution module is used for executing the vehicle driving direction control instruction based on the planned path and the heading angle threshold value.

In a fifth aspect, an embodiment of the present application provides a path optimization apparatus, including:

the first determining module is used for responding to the driving direction adjusting instruction and determining a path optimization model;

the second determination module is used for determining the relative distance between the target vehicle and the center line of the lane and the current course angle;

a third determining module, configured to determine, based on the path optimization model, a heading angle threshold corresponding to the relative distance;

the fourth determining module is used for determining the predicted course angle of the next moment in the planned path;

and the replacing module is used for replacing the predicted course angle with the course angle threshold value when the angle difference between the predicted course angle and the current course angle is greater than the difference threshold value.

In a sixth aspect, an embodiment of the present application provides a vehicle, including: a vehicle body and a power source;

the vehicle body is provided with a memory and a processor;

the memory to store one or more computer instructions;

the processor is configured to execute the one or more computer instructions for performing the steps in the method of the second or third aspect.

In a seventh aspect, the present application provides a computer program product, which when executed can implement the steps in the method of the second aspect or the third aspect.

According to the method, the device and the medium for path optimization and model calibration, provided by the embodiment of the application, the center line of the lane where the current target vehicle runs can be obtained in the running process of the vehicle. Although path planning can be realized based on the center line of the lane, the obtained planned path is not ideal and sometimes cannot meet the requirements of automatic driving or auxiliary driving. Therefore, the pose information of the target vehicle can be obtained firstly, and the relative distance between the target vehicle and the lane center line can be determined according to the pose information; determining the instruction type of the vehicle driving direction control instruction; determining a course angle threshold value and a planned path during path planning according to the instruction type and the relative distance; and executing the vehicle driving direction control command based on the planned path and the heading angle threshold. By the scheme, the corresponding course angle threshold value can be determined according to the instruction type and the relative distance of the actual vehicle running direction control instruction in the process of path planning, so that the path planning process is optimized based on the course angle threshold value, and a planned path with higher accuracy and better continuity is obtained. The vehicle can more accurately realize the control of the vehicle driving direction according to the optimized planned path.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:

FIG. 1 is a schematic block diagram of a vehicle control system illustrated herein;

FIG. 2 is a schematic flow chart of a vehicle control method according to an embodiment of the present disclosure;

FIG. 3 is a schematic view of a vehicle and a lane provided by an embodiment of the present application;

fig. 4 is a schematic flowchart of a calibration method for a path optimization model according to an embodiment of the present disclosure;

FIG. 5 is a course angle trend graph obtained in the calibration process provided by the embodiment of the present application;

fig. 6 is a schematic flowchart of another path optimization method provided in the embodiment of the present application;

fig. 7 is a schematic structural diagram of a vehicle control device according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of a path optimization apparatus according to an embodiment of the present disclosure;

fig. 9 is a schematic structural diagram of a vehicle according to an embodiment of the present application.

Detailed Description

In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention.

In some of the flows described in the present specification, claims, and above-described figures, operations are included in a particular order, and may be performed out of order or in parallel as they appear herein. The sequence numbers of the operations, e.g., 101, 102, etc., are merely used to distinguish between the various operations, and the sequence numbers themselves do not represent any order of execution. Additionally, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first", "second", etc. in this document are used for distinguishing different messages, devices, modules, etc., and do not represent a sequential order, nor limit the types of "first" and "second" to be different.

In the prior art, in an automatic driving application scenario, when a vehicle performs path planning, a position of the vehicle at a next moment is determined according to a current position of the vehicle and a lane marking line. If the position difference corresponding to two adjacent moments is large, the posture of the vehicle body is adjusted suddenly, the continuity ratio of the planned path is poor, the user experience is poor, and the like. Meanwhile, if the posture of the vehicle body is adjusted excessively, the position of the next moment cannot be found accurately during path planning, and the path continuous planning fails. Therefore, a solution capable of improving the continuity and accuracy of path planning is needed.

The embodiment of the application provides a vehicle control system. Fig. 1 is a schematic structural diagram of a vehicle control system exemplified in the present application. As can be seen from fig. 1, the system comprises: controller 11, sensor 12, etc. The sensors may be used to detect pose information of the target vehicle (e.g., coordinates of the vehicle, vehicle direction, etc.), lane markings, etc.

A controller in the system is used for acquiring the pose information of the target vehicle and determining the relative distance between the target vehicle and the center line of the lane according to the pose information. Determining the instruction type of the vehicle driving direction control instruction; determining a course angle threshold value and a planned path during path planning according to the instruction type and the relative distance; and executing the vehicle driving direction control instruction based on the planned path and the heading angle threshold value.

After the pose information of the target vehicle is acquired by the sensor, the position coordinates of the target vehicle on the lane can be determined. The command type may be a driving direction adjustment command (for example, a lane change command, an overtaking command, and a side parking command), and the command may be directly generated by the controller (for example, in an automatic driving mode) or may be generated by the controller in response to an operation action or an operation command of the driver.

Fig. 2 is a schematic flowchart of a vehicle control instruction execution method according to an embodiment of the present application. As can be seen from fig. 1, the method specifically comprises the following steps:

step 201: the method comprises the steps of obtaining pose information of a target vehicle, and determining the relative distance between the target vehicle and a lane center line according to the pose information.

Step 202: the command type of the vehicle traveling direction control command is determined.

Step 203: and determining a course angle threshold value and a planned path during path planning according to the instruction type and the relative distance.

Step 204: and executing the vehicle driving direction control instruction based on the planned path and the heading angle threshold value.

In practical applications, the manner of determining the heading angle threshold includes: determining a corresponding path optimization model according to the instruction type; and determining a course angle threshold value corresponding to the relative distance based on the path optimization model.

It should be noted that the technical scheme of the application is a scheme for improving the accuracy and continuity of route planning when the controller plans the driving route in the automatic driving scene of the vehicle. The execution main body of the above steps may be a controller, or a cloud server, or the controller and the cloud server execute cooperatively. For ease of understanding, the following embodiments will be described by taking a controller as an example of the execution subject.

For ease of understanding, reference will now be made to the following description taken in conjunction with the accompanying drawings. Fig. 3 is a schematic view of a vehicle and a lane according to an embodiment of the present disclosure. As can be seen from fig. 3, the lane is a bidirectional lane, and there are lane marks on both sides of the lane where the vehicle is located, but there is no lane center line, so that the vehicle itself needs to calculate the position of the lane center line in the lane based on the recognized lane marks on both sides. In some scenarios, there is no lane marker or there is a lane marker on one side of the vehicle, and the position of the lane center line in the lane can be calculated based on curbs and the like.

In practical application, the path optimization models may be of various types, and are respectively suitable for different automatic driving scenes, for example, a lane keeping scene, an overtaking scene, an exiting high-speed scene, an approaching parking scene, and the like. And adopting different path optimization models in different scenes. The specific model determination method and the model calibration process will be described in detail in the following embodiments.

After determining the appropriate path optimization model, the heading angle threshold θ for the next time of the vehicle may be further determined based on the predicted relative distance D1 for the next time of the target vehicle. Therefore, the vehicle position and the vehicle attitude (such as the vehicle heading angle) at the next moment in the planned path of the vehicle can be more reasonable by utilizing the heading angle threshold value, so that the vehicle can smoothly and continuously move stably when walking along the planned path, and the sudden change of the heading (in other words, the steering wheel can not suddenly rotate greatly) can not occur, thereby enabling a user to obtain more stable driving experience.

In one or more embodiments of the present application, the determining a corresponding path optimization model according to an instruction type includes:

The driving direction adjustment command may be a passing command, a lane change command, a driving-away high-speed command, a side parking command, or the like. The driving direction adjustment command may be a command from an occupant (for example, a driver) or a command from a controller in the vehicle.

In practical applications, if the target vehicle does not receive the driving direction adjustment command, it is determined that the vehicle keeps the current lane running stably (for example, keeping the current lane running at a constant speed, or keeping the current lane running with the vehicle). That is to say, the lane marking lines on the two sides of the vehicle can not change in the process of keeping the vehicle stably running in the lane, and the relative distance between the vehicle and the lane marking lines is kept stable in the running process. When the route is planned, the vehicle can keep stably running in the current lane by planning the route according to the currently detectable lane marking line.

If the target vehicle receives a driving direction adjustment command (e.g., a lane change command or a passing command), it is determined that the vehicle will leave the currently driving lane. That is, during lane change of the vehicle, lane marks on two sides of the vehicle change, and during driving, a relative distance between the vehicle and the lane marks changes. When planning a path, the influence of the change of the lane marking line on the planned path needs to be eliminated.

By the scheme, different path optimization models are adopted in different driving scenes, so that the lane is more reasonably optimized and perfected, and the path optimization effect is better.

In one or more embodiments of the present application, the determining, based on the path optimization model, a heading angle threshold corresponding to the relative distance includes:

In practical application, when path planning is performed, road information (such as surrounding obstacles, vehicle speed and the like) needs to be acquired through sensors such as a camera, a millimeter wave radar and an ultrasonic radar, and various methods for realizing the path planning are available, such as a traditional algorithm (Dijkstra algorithm, a star algorithm and the like), an intelligent algorithm (PSO algorithm, a genetic algorithm, reinforcement learning and the like), and a traditional and intelligent combined algorithm. Meanwhile, the camera can be used for recognizing and extracting the lane marking lines of the collected images. The planned heading angle referred to herein can be understood as the planned heading angle of the target vehicle at the current time when the path is planned, where each time on the planned path has its corresponding position point, and the included angle between the line connecting the current position point and the next position point and the lane center line can be referred to as the planned heading angle of the target vehicle at the current time. In addition, the course angles acquired in real time by sensors such as a compass and the like comprise course angles corresponding to all relative distances.

When the path planning is carried out, information such as position coordinates, course angles and the like of each position to be driven next by the planned path can be known. Furthermore, the relative distance between the target vehicle and the lane center line can be determined according to the obtained position coordinates and the calculated position of the current lane center line in the lane. And, the planned heading angle of the vehicle as the target vehicle moves from the current location to the predicted next location may also be determined.

It should be noted that the relative distance determination method described herein may be a vertical distance from a center position of the vehicle body to a center line of the lane, or a vertical distance from a sensor (such as a camera) on the vehicle for acquiring a lane marking line to the center line of the lane. In practical application, the relative distance determining mode selected when the path optimization model is calibrated is consistent with the relative distance determining mode in the actual path optimization process.

Based on the foregoing steps, a heading angle threshold corresponding to the relative distance may be determined using the determined path optimization model, and the planned path may be further optimized based on the heading angle threshold.

The specific method for optimizing the planned path based on the course angle threshold comprises the following steps: and comparing the planned course angle with a course angle threshold value. If the planned course angle is smaller than the course angle threshold value, the planned course angle is reasonable, course angle correction is not needed, a continuous, accurate and smooth planned path can be successfully obtained, and meanwhile, the vehicle can stably run along the planned path.

And correcting the planned course angle according to a preset correction rule so as to execute the planned path based on the corrected course angle. As an optional embodiment, when the planned heading angle is greater than the heading angle threshold, replacing the planned heading angle in the planned path with the heading angle threshold to execute the planned path based on the heading angle threshold. In addition, when the planned course angle is larger than the course angle threshold, a correction coefficient can be determined according to the difference value or the proportional relation between the course angle threshold and the planned course angle, then the planned course angle is corrected by the correction coefficient, and path planning or path optimization is carried out based on the corrected course angle.

When the planned heading angle is larger than the heading angle threshold, the planned path of the current vehicle is considered to be unreasonable, and the current target vehicle may be too far away from the lane center line, or the heading angle between the current target vehicle and the lane center line is too large, which may cause the lane recognition failure, or the planned path obtained by planning may not have good continuity. Therefore, the planned course angle can be replaced by the course angle threshold value, so that the planned path has better continuity, and a more reasonable planned path is obtained.

In one or more embodiments of the present application, the determining the relative distance of the target vehicle from the lane centerline comprises: acquiring adjacent lane marking lines on the left side and the right side of the target vehicle; determining the lane central line based on the adjacent lane marking lines on the left side and the right side; and determining the relative distance according to the position of the target vehicle in the lane and the position of the lane central line in the lane.

In practical applications, the environment in which the target vehicle travels may vary widely. For example, when the vehicle runs on a highway, a standard lane marking line exists, so that when the center line of the lane is determined by the target vehicle, the center line of the lane can be easily calculated according to the adjacent lane marking lines on the left side and the right side of the vehicle.

In some driving environments, lane marking lines do not exist, for example, there are intra-district roads and intra-campus roads, and only roadside roads have green belts, curbs, etc., but there is no standard marking line artificially planned in the center of the road. Therefore, when the lane center line is determined, the curbs or the green belt can be used as the lane marking line, and the lane center line is calculated based on the curbs or the green belt.

In addition, in some driving environments, there may be no curbs, nor green belts, such as a rural trail. In this case, the lane center line of the current road may be calculated using road information provided by the navigation system.

After determining the position of the lane center line by using the above scheme, further, the position of the target vehicle in the lane (for example, the coordinates of the vehicle in the lane) may be calculated to calculate the relative distance between the target vehicle and the lane center line.

Fig. 4 is a schematic flowchart of a calibration method of a path optimization model according to an embodiment of the present disclosure. The method specifically comprises the following steps:

step 401: determining at least one calibrated distance of the target vehicle from the lane centerline.

Step 402: and executing a path planning task based on the calibration distance.

Step 403: and when the path planning task fails to be executed, the critical course angle between the target vehicle and the lane central line is the course angle threshold value.

Step 404: and generating the path optimization model based on the corresponding relation between at least one calibration distance and the heading angle threshold value.

In practical applications, a plurality of calibration distances may be defined experimentally. Adjusting the course angle at each calibration distance, for example, continuously adjusting the course angle when the relative distance is 0m, and when a certain angle of a critical course angle theta is reached ₁ When the path planning fails, the critical course angle theta can be determined ₁ As a heading angle threshold corresponding to a relative distance of 0m, or will be a ratio theta ₁ An angle of less than N degrees (N may be 1 degree) is defined as the heading angle threshold.

In the actual calibration process, calibration may be performed for various scenes, for example, calibration may be performed for different types of lane markings, calibration may be performed for different light conditions (for example, day and night), calibration may be performed for lane markings of different colors (for example, white and yellow), and calibration may be performed for lane markings of different definitions.

After the calibration for the relative distance of 0m is completed, the next position with the relative distance of 0.5 m can be selected to repeat the calibration process. Generally, the relative distance of the calibration is within 5 meters. Of course, the calibration range can be adjusted as needed.

And after the calibration work of all sampling points is finished, a complete calibration result can be obtained. Fig. 5 is a heading angle trend graph obtained in the calibration process provided in the embodiment of the present application. As can be seen in FIG. 5, the lateral coordinate is the relative distance, the longitudinal coordinate is the heading angle threshold, the upper line represents the maximum heading angle threshold, and the lower line represents the minimum heading angle threshold.

In one or more embodiments of the present application, the determining at least one calibrated distance of the target vehicle from the lane centerline comprises:

As mentioned above, the selected path optimization model is different in different scenarios. When calibrating the path optimization models of different types, different calibration parameters can be set respectively.

For example, in a nominal keeping lane model, a first nominal sequence at 0.5 meter intervals may be set as: -2, -1.5, -1, -0.5,0, +0.5, +1, +1.5, +2. And executing corresponding calibration tasks according to the first calibration sequence.

Since lane-change driving enables the vehicle to have larger course angle and transverse distance adjustment than the lane-keeping driving vehicle, when the lane-change driving model is calibrated, the set second calibration sequence can have a larger range and larger interval than the first calibration sequence. For example, a second nominal sequence at 1 meter intervals may be set as: -2, -1,0, +1, +2.

Based on the embodiment, different calibration parameters are adopted for calibrating different path optimization models, so that a more accurate path optimization model with a better optimization effect is obtained.

The calibration method of the path optimization model will be described in detail below with reference to specific embodiments.

The quadratic optimization planning algorithm is taken as an example below

s∈(smin,smax)

∈(

min,

max)

∈(

min,

max)

Wherein the content of the first and second substances,

max represents the maximum lateral velocity of the vehicle,

min represents the minimum lateral velocity;

max represents the maximum lateral acceleration of the vehicle,

min represents the minimum lateral acceleration;

the change rate of the lateral acceleration is represented, w represents an optimization coefficient, s represents the lateral distance between the vehicle and the center line of the lane, smin represents the minimum lateral distance, and smax represents the maximum lateral distance.

Specifically, s,

、

The calculation process of (2) is as follows:

wherein, θ represents course angle, K represents curvature (the curve can not form a measure of a straight line, and the curve approaches to a straight line the more the curvature approaches to 0), T represents deflection (the curve can not form a measure of a motion curve in the same plane, and the curve approaches to a motion in the same plane the more the deflection approaches to 0),

representing the heading angle in the current Cartesian coordinate system,

representing the curvature in the current Cartesian coordinate system,

representing coordinate points in the current Cartesian coordinate system,

representing coordinates of a corresponding point in a coordinate system established based on the center line of the lane,

indicating a heading angle in a coordinate system established based on the lane center line,

representing the curvature in the coordinate system established based on the lane center line,

indicating the rate of change of curvature.

The specific calibration steps are as follows:

step a, when the lane keeping model is calibrated in a scene kept running in the lane, dividing the transverse relative position of a target vehicle and the center line of the lane by taking 0.5 meter as a scale, wherein the transverse relative position is divided into-1.5, -1.0, -0.5,0, 0.5, 1.0 and 1.5.

And b, when the lane change driving model is calibrated in the scene of lane change driving, dividing the transverse relative position of the target vehicle and the center line of the lane by taking 1 meter as a scale, wherein the transverse relative position is divided into-4.0, -3.0, -2.0, -1.0,0, 1.0, 2.0,3.0 and 4.0.

C, sampling a scene when the transverse relative distance between the target vehicle and the lane center line is 0m, and calculating that when the relative distance between the target vehicle and the lane center line is 0m through the formula, a path planning algorithm (such as a Probabilistic graphical Map (PRM) algorithm, a rapid-Random extended Tree (RRT) algorithm and the like) can successfully plan a path, and the allowed maximum course angle difference and the minimum course angle difference; such as Lateral _ distance _0- (L0 _ delta _ min, L0_ delta _ max), where Lateral _ distance _0 represents a relative distance of 0 meters from the lane centerline, L0_ delta _ min represents a minimum heading angle at a relative distance of 0 meters from the lane centerline, and L0_ delta _ max represents a maximum heading angle at a relative distance of 0 meters from the lane centerline.

And d, repeating the step c, continuously sampling and calculating the allowed maximum course angle difference and the minimum course angle difference when the transverse relative distance between the target vehicle and the center line of the road is on other position scales. Such as Lateral _ distance _0.5- (L0.5 _ delta _ min, L0.5_ delta _ max), lateral _ distance _1.0- (L1.0 _ delta _ min, L1.0_ delta _ max), and so forth. Wherein, the relative distance between the Lateral _ distance _0.5 and the lane central line is 0.5 meter, the L0.5_ delta _ min represents the minimum heading angle when the relative distance between the Lateral _ distance _0.5 and the lane central line is 0.5 meter, and the L0.5_ delta _ max represents the maximum heading angle when the relative distance between the Lateral _ distance _0.5 and the lane central line is 0.5 meter. Lateral _ distance _1.0 represents a relative distance of 1.0 meter from the lane center line, L1.0_ delta _ min represents a minimum heading angle at a relative distance of 1.0 meter from the lane center line, and L1.0_ delta _ max represents a maximum heading angle at a relative distance of 1.0 meter from the lane center line.

And e, calculating the maximum course angle difference and the minimum course angle difference between the sampling points by adopting a linear interpolation method to obtain the maximum course angle difference and the minimum course angle difference. now _ delta _ max = pre _ delta _ max + (next _ delta _ max-pre _ delta _ max)/(next _ s-pre _ s) (now _ s-pre _ s); now _ delta _ min = pre _ delta _ min + (next _ delta _ min-pre _ delta _ min)/(next _ s-pre _ s) (now _ s-pre _ s). The new _ delta _ max represents the current maximum heading angle, the pre _ delta _ max represents the maximum heading angle of the previous sampling point, the next _ delta _ max represents the maximum heading angle of the next sampling point, the next _ s represents the distance between the next sampling point and the center line of the lane, and the pre _ s represents the distance between the previous sampling point and the center line of the lane. now _ delta _ min represents the current minimum heading angle, pre _ delta _ min represents the previous sample point minimum heading angle, next _ delta _ min represents the next sample point minimum heading angle, next _ s represents the distance from the next sample point to the lane centerline, and pre _ s represents the distance from the previous sample point to the lane centerline.

As shown in fig. 5, it can be seen that each sampling point in the calibrated graph is isolated, and if the path optimization is performed based on each actually calibrated point, the obtained optimization result is not good. Therefore, further optimization processing of the obtained model is required. Specifically, an initial optimization model is generated based on at least one calibration distance and the corresponding heading angle threshold value; and optimizing the initial optimization model by using a linear difference algorithm to obtain the path optimization model.

Based on the same idea, the embodiment of the present application further provides a path optimization method, for example, fig. 6 is a schematic flow diagram of the path optimization method provided in the embodiment of the present application. As can be seen from fig. 6, the method specifically comprises the following steps:

step 601: in response to the driving direction adjustment instruction, a path optimization model is determined.

Step 602: and determining the relative distance between the target vehicle and the center line of the lane and the current heading angle.

Step 603: and determining a course angle threshold value corresponding to the relative distance based on the path optimization model.

Step 604: a predicted heading angle for a next time in the planned path is determined.

Step 605: and when the angle difference between the predicted course angle and the current course angle is larger than a difference threshold value, correcting the predicted course angle based on the course angle threshold value.

When the vehicle has a lane change requirement, the vehicle is generally required to be adjusted with a larger heading angle and a larger transverse distance. However, in the prior art, the vehicle may have a large abrupt change in direction due to an excessively large adjustment of the heading angle, and the passenger may feel a significant sway in terms of riding feeling. The movement is not smooth, and the riding experience of the passengers is not good.

In the scheme of the application, in the course of changing the lane, the sudden change of the course angle or the overlarge adjustment of the course angle is avoided by limiting the course angle threshold. So that the heading angle in the planned path is gradually adjusted. The course angle adjustment can cause the vehicle to gradually get away from the center line of the lane in the running process of the target vehicle, the farther the target vehicle gets away from the center line, the larger the difference of the heading angle is, but the change process of the course angle is slowly progressive.

Therefore, the relative distance and the current course angle of the target vehicle at the current moment can be acquired in real time. And when the path planning is carried out, the corresponding predicted course angle at the next moment can be known. If the angle difference between the current heading angle and the predicted heading angle is too large (for example, when the angle difference is larger than the difference threshold), the difference between the heading angles of two adjacent vehicles is large, and obvious heading angle adjustment may occur in the running process of the target vehicle.

When the vehicle travels between two lane centerlines, lane centerline replacement is performed. After the replacement of the lane center line is completed, the vehicle is shown to drive into another lane, and path planning is carried out based on the new lane center line, and at the moment, the path optimization model can be continuously utilized to carry out optimization adjustment on the planned path, so that the vehicle is enabled to approach the new center line stably.

Through the scheme, when the target vehicle has a large course angle adjustment requirement, such as lane changing, side parking and the like, the planned path can be optimized by utilizing the course angle threshold value in the scheme, so that the optimized planned path has better continuity, smooth lane changing is realized in the driving process, and a user obtains better and more stable lane changing driving experience.

Based on the same idea, the embodiment of the application further provides a path optimization device. Fig. 7 is a schematic structural diagram of a path optimization apparatus according to an embodiment of the present application. As can be seen from fig. 7, the apparatus comprises:

the first determining module 701 is configured to acquire pose information of a target vehicle, and determine a relative distance between the target vehicle and a lane center line according to the pose information.

A second determining module 702 is configured to determine a command type of the vehicle driving direction control command.

A third determining module 703, configured to determine, according to the instruction type and the relative distance, a heading angle threshold and a planned path during path planning.

And an executing module 704, configured to execute the vehicle driving direction control instruction based on the planned path and the heading angle threshold.

A second determining module 702, configured to determine that the path optimization model in a lane is a lane keeping model if the target vehicle does not receive a driving direction adjustment instruction;

A third determining module 703, configured to determine a planned path and a planned heading angle of the target vehicle on the planned path at each time;

determining the relative distance between the target vehicle and the lane central line on the planned path at each moment;

A third determining module 703, configured to replace the planned heading angle in the planned route with the heading angle threshold when the planned heading angle is greater than the heading angle threshold, so as to execute the planned route based on the heading angle threshold.

A first determining module 701, configured to obtain lane identification lines adjacent to left and right sides of the target vehicle;

Optionally, the system further comprises a calibration module 705 for determining at least one calibration distance between the target vehicle and the lane center line;

executing a path planning task based on the calibration distance;

when the path planning task fails to be executed, a course angle threshold value is set between the target vehicle and the lane central line;

and generating the path optimization model based on at least one calibration distance and the corresponding course angle threshold value.

A calibration module 705, configured to determine at least one calibration distance between the target vehicle and the lane center line based on a first calibration sequence if the path optimization model to be calibrated is the lane keeping model;

A calibration module 705, configured to generate an initial optimization model based on at least one of the calibration distances and the corresponding heading angle threshold;

Based on the same idea, the embodiment of the present application further provides another path optimization device. Fig. 8 is a schematic structural diagram of another path optimization device according to an embodiment of the present application. As can be seen from fig. 8, the apparatus comprises:

a first determination module 801 for determining a path optimization model in response to a driving direction adjustment instruction.

A second determining module 802 for determining a relative distance of the target vehicle from a lane centerline and a current heading angle.

A third determining module 803, configured to determine, based on the path optimization model, a heading angle threshold corresponding to the relative distance.

A fourth determining module 804, configured to determine a predicted heading angle at a next time in the planned path.

And the replacing module 805 is configured to correct the predicted course angle based on the course angle threshold when the angle difference between the predicted course angle and the current course angle is greater than the difference threshold.

Fig. 9 is a schematic structural diagram of a vehicle according to an embodiment of the present application, where as shown in fig. 9, a vehicle device is disposed on the vehicle, and the vehicle device includes: a memory 901 and a controller 902.

A memory 901 for storing a computer program and may be configured to store other various data to support operations on the vehicular apparatus. Examples of such data include instructions for any application or method operating on the vehicle device, contact data, phone book data, messages, pictures, videos, and so forth.

The Memory 901 may be implemented by any type of volatile or nonvolatile Memory device or combination thereof, such as Static Random-Access Memory (SRAM), electrically Erasable Programmable Read-Only Memory (EEPROM), erasable Programmable Read-Only Memory (EPROM), programmable Read-Only Memory (PROM), read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk or optical disk.

The vehicle apparatus further includes: a display device 903. A controller 902, coupled to the memory 901, for executing a computer program in the memory 901 to:

acquiring pose information of a target vehicle, and determining the relative distance between the target vehicle and a lane center line according to the pose information;

The controller 902 is configured to determine that the path optimization model in the lane is a lane keeping model if the target vehicle does not receive the driving direction adjustment instruction;

The controller 902 is configured to determine a planned path and a planned heading angle of the target vehicle on the planned path at each time;

The controller 902 is configured to modify the planned heading angle according to a preset modification rule when the planned heading angle is greater than the heading angle threshold, so as to execute the planned path based on the modified heading angle.

The controller 902 is configured to obtain lane identification lines adjacent to left and right sides of the target vehicle;

determining the relative distance according to the position of the target vehicle in the lane and the position of the lane center line in the lane.

Controller 902 is configured to determine at least one calibrated distance of the target vehicle from the lane centerline;

executing a path planning task based on the calibration distance;

The controller 902 is configured to determine at least one calibration distance between the target vehicle and the lane center line based on a first calibration sequence if the path optimization model to be calibrated is the lane keeping model;

The controller 902 is configured to generate an initial optimization model based on at least one of the calibration distances and the corresponding heading angle threshold;

The display device 903 in fig. 9 described above includes a screen, which may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

The audio component 904 of fig. 9 above may be configured to output and/or input audio signals. For example, the audio component includes a Microphone (MIC) configured to receive an external audio signal when the device in which the audio component is located is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal may further be stored in a memory or transmitted via a communication component. In some embodiments, the audio assembly further comprises a speaker for outputting audio signals.

Further, as shown in fig. 9, the vehicular apparatus further includes: communication components 905, power components 906, and the like. Only some of the components are schematically shown in fig. 9, and it is not intended that the vehicle apparatus includes only the components shown in fig. 3.

The communications component 905 of fig. 9 is configured to facilitate communications between the device in which the communications component resides and other devices in a wired or wireless manner. The device in which the communication component is located may access a wireless network based on a communication standard, such as WiFi,2G, 3G, 4G, or 5G, or a combination thereof. In one exemplary embodiment, the Communication component may be implemented based on Near Field Communication (NFC) technology, radio Frequency Identification (RFID) technology, infrared Data Association (IrDA) technology, ultra Wide Band (UWB) technology, bluetooth technology, and other technologies.

The power supply 906 provides power to various components of the device in which the power supply is located. The power components may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device in which the power component is located.

Accordingly, the present application further provides a computer program product, and the computer program product can implement the steps in the method embodiment of fig. 2 when being executed.

In the embodiment of the application, the center line of the lane where the current target vehicle runs can be acquired in the running process of the vehicle. Although path planning can be realized based on the center line of the lane, the obtained planned path is not ideal and sometimes cannot meet the requirement of automatic driving. Therefore, the planned path can be optimized by using the pre-calibrated path optimization model. Specifically, after acquiring the lane center line, determining the relative distance between the target vehicle and the lane center line; and then, searching a path optimization parameter corresponding to the relative distance based on the path optimization model so as to optimize the planned path based on the path optimization parameter. By the scheme, the planned path can be optimized by using the pre-calibrated path optimization model in the path planning process, so that the more accurate and continuous planned path is obtained. The vehicle can realize automatic driving more accurately according to the optimized planned path.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory. The memory may include forms of volatile memory in a computer readable medium, random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A vehicle control system, characterized in that the system comprises a controller;

2. The system of claim 1, wherein the controller is further configured to:

determining a corresponding path optimization model according to the instruction type;

3. The system of claim 2, wherein the controller is further configured to: if the target vehicle does not receive the driving direction adjusting instruction, determining the path optimization model in the lane as a lane keeping model;

4. The system of claim 3, wherein the controller is further configured to calibrate the path optimization model, comprising:

executing a path planning task based on the calibration distance;

5. The system of claim 4, wherein the controller is further configured to:

6. The system of claim 5, wherein the controller is further configured to:

7. The system of claim 1, wherein the controller is further configured to:

8. The system of claim 4, wherein the controller is further configured to:

9. The system of claim 4, wherein the controller is further configured to:

generating an initial optimization model based on at least one calibration distance and the corresponding course angle threshold value;

10. A vehicle control method, characterized by comprising:

11. A method for path optimization, the method comprising:

determining a predicted course angle of the next moment in the planned path;

12. A vehicle control apparatus, characterized by comprising:

and the execution module is used for executing the vehicle driving direction control instruction based on the planned path and the course angle threshold value.

13. A path optimization device, characterized in that the device comprises:

the first determination module is used for responding to the driving direction adjusting instruction and determining a path optimization model;

the second determining module is used for determining the relative distance between the target vehicle and the center line of the lane and the current course angle;

and the replacing module is used for correcting the predicted course angle based on the course angle threshold when the angle difference between the predicted course angle and the current course angle is greater than the difference threshold.

14. A vehicle, characterized by comprising: a vehicle body and a steer-by-wire system;

the memory and the processor are arranged on the vehicle body;

the memory to store one or more computer instructions;

the processor is configured to execute the one or more computer instructions for performing the steps in the method of claim 10 or performing the steps in the method of claim 11.

15. A computer program product enabling the implementation of the steps of the method according to claim 10 or the implementation of the steps of the method according to claim 11 when being executed.