WO2024055367A1

WO2024055367A1 - Vehicle route planning method and apparatus, storage medium, vehicle and terminal

Info

Publication number: WO2024055367A1
Application number: PCT/CN2022/122636
Authority: WO
Inventors: 王斌; 王睿; 刘偲; 冉旭
Original assignee: 魔门塔(苏州)科技有限公司
Priority date: 2022-09-14
Filing date: 2022-09-29
Publication date: 2024-03-21
Also published as: CN117762121A

Abstract

A vehicle route planning method and apparatus, a storage medium, a vehicle and a terminal, relating to the technical field of automatic driving, and mainly aiming to solve the problem of poor route planning efficiency of existing vehicles. The method comprises: acquiring trajectory mileage information of a vehicle in a first coordinate system (101); constructing, in a second coordinate system, a vehicle envelope model matching the trajectory mileage information, and determining an interference relationship between the vehicle and an obstacle according to the vehicle envelope model (102); and when it is determined, according to the interference relationship, that the vehicle collides with the obstacle, determining trajectory point information of the collision in the first coordinate system on the basis of the interference relationship, and performing route planning according to the trajectory point information (103).

Description

Vehicle path planning method and device, storage medium, vehicle, terminal

This application requests the priority of the Chinese patent application submitted to the State Intellectual Property Office of China on September 14, 2022, with the application number "202211119621.2" and the invention title "Vehicle path planning method and device, storage medium, vehicle, terminal" , the entire contents of which are incorporated herein by reference.

Technical field

This application relates to the field of intelligent driving technology, and in particular to a vehicle path planning method and device, storage medium, vehicle, and terminal.

Background technique

With the rapid development of intelligent driving technology, the control of vehicle driving processes is becoming more and more refined. Among them, the vehicle usually performs longitudinal planning in the Frenet coordinate system during driving to plan the path for the vehicle to travel automatically.

At present, the existing longitudinal path planning in the Frenet coordinate system is usually based on the projection of the vehicle on the reference path to plan the path in different curvature turning scenarios. However, due to the obstacles at different positions in the large curvature turning scenario, In the Frenet coordinate system, the projection distance of the vehicle is the same, so that the projection of the vehicle and the obstacle cannot effectively confirm whether a collision has occurred, which greatly reduces the accuracy of collision detection, creates a greater risk of collision, and thus reduces the path planning of the vehicle. effectiveness.

Contents of the invention

In view of this, this application provides a vehicle path planning method and device, storage medium, vehicle, and terminal, with the main purpose of solving the problem of poor path planning efficiency of existing vehicles.

According to one aspect of this application, a vehicle path planning method is provided, including:

Obtain the trajectory mileage information of the vehicle in the first coordinate system;

Construct a vehicle envelope model matching the trajectory mileage information in the second coordinate system, and determine the interference relationship between the vehicle and the obstacle based on the vehicle envelope model;

When the collision condition between the vehicle and the obstacle is determined based on the interference relationship, the trajectory point information of the collision is determined in the first coordinate system based on the interference relationship, and the path is determined based on the trajectory point information. planning.

Further, constructing a vehicle envelope model matching the trajectory mileage information in the second coordinate system includes:

Convert the trajectory mileage information in the first coordinate system into a vehicle outline model in the second coordinate system;

Determine the extension length based on the vehicle's speed influence coefficient, vehicle speed, preset speed expansion coefficient, curvature influence coefficient, trajectory curvature, and preset curvature expansion coefficient;

In the longitudinal direction of the vehicle outline model, the vehicle outline model is extended and constructed according to the extension length to obtain the vehicle envelope model.

Further, determining the extension length based on the vehicle's speed influence coefficient, vehicle speed, preset speed expansion coefficient, curvature influence coefficient, trajectory curvature, and preset curvature expansion coefficient includes:

Select the maximum speed coefficient from the dot product of the speed influence coefficient and the vehicle speed and the preset speed expansion coefficient, and select the maximum speed coefficient from the dot product of the curvature influence coefficient and the trajectory curvature, the preset curvature Select the maximum curvature coefficient from the expansion coefficient;

The extension length is obtained according to the sum operation of the maximum speed coefficient and the maximum curvature coefficient.

Further, determining the interference relationship between the vehicle and the obstacle according to the vehicle envelope model includes:

Obtain the obstacle outline information of the obstacle in the second coordinate system;

Calculate overlap information between the obstacle contour information and the vehicle envelope model, and determine an interference relationship based on the overlap information, where the interference relationship includes overlapping interference and non-overlapping interference;

After determining the interference relationship between the vehicle and the obstacle according to the vehicle envelope model, the method further includes:

If the interference relationship is overlapping interference, it is determined that the vehicle collides with the obstacle.

Further, the determination of the trajectory point information of the collision in the first coordinate system based on the interference relationship includes:

Convert the collision position of the vehicle in the second coordinate system to the first coordinate system based on the overlapping information;

The trajectory point information of the collision is generated according to the position in the first coordinate system, and the trajectory point information includes the trajectory point index and the collision trajectory mileage information.

Further, obtaining the trajectory mileage information of the vehicle in the first coordinate system includes:

Under the first coordinate system, obtain the reference trajectory of the vehicle lateral trajectory planning in the preset planning frame;

Calculate the trajectory mileage information of each trajectory point according to the reference trajectory.

Further, the path planning based on the trajectory point information includes:

Under the first coordinate system, update the path boundary used for longitudinal path planning decision-making according to the minimum collision trajectory mileage information in the trajectory point information;

Perform longitudinal path trajectory planning based on the updated path boundary.

According to another aspect of this application, a vehicle path planning device is provided, including:

The acquisition module is used to obtain the trajectory mileage information of the vehicle in the first coordinate system;

A determination module configured to construct a vehicle envelope model that matches the trajectory mileage information in a second coordinate system, and determine the interference relationship between the vehicle and obstacles based on the vehicle envelope model;

A planning module, configured to determine the trajectory point information of the collision in the first coordinate system based on the interference relationship under the condition that the vehicle and the obstacle are determined to collide according to the interference relationship, and according to the Track point information is used for path planning.

Furthermore, the determining module includes:

A conversion unit configured to convert the trajectory mileage information in the first coordinate system into a vehicle outline model in the second coordinate system;

a determination unit configured to determine the extension length based on the vehicle's speed influence coefficient, vehicle speed, preset speed expansion coefficient, curvature influence coefficient, trajectory curvature, and preset curvature expansion coefficient;

A construction unit configured to extend and construct the vehicle contour model according to the extension length in the longitudinal direction of the vehicle contour model to obtain the vehicle envelope model.

Further, the determination unit is specifically configured to select the maximum speed coefficient from the dot product of the speed influence coefficient and the vehicle speed and the preset speed expansion coefficient, and select the maximum speed coefficient from the curvature influence coefficient and the trajectory The maximum curvature coefficient is selected from the dot product value of curvature and the preset curvature expansion coefficient; and the extension length is obtained according to the sum of the maximum speed coefficient and the maximum curvature coefficient.

Further, the determination module is specifically used to obtain the obstacle outline information of the obstacle in the second coordinate system; calculate the overlap information between the obstacle outline information and the vehicle envelope model, And determine an interference relationship based on the overlapping information, where the interference relationship includes overlapping interference and non-overlapping interference;

The determination module is also configured to determine that the vehicle collides with the obstacle if the interference relationship is overlapping interference.

Further, the planning module includes:

A conversion unit configured to convert the collision position of the vehicle in the second coordinate system to the first coordinate system based on the overlapping information;

A generating unit configured to generate trajectory point information of a collision according to the position in the first coordinate system, where the trajectory point information includes a trajectory point index and collision trajectory mileage information.

Further, the acquisition module is specifically configured to obtain the reference trajectory of the vehicle transverse trajectory planning in the preset planning frame in the first coordinate system; and calculate the trajectory mileage information of each trajectory point according to the reference trajectory.

Furthermore, the planning module also includes:

An update unit configured to update the path boundary for longitudinal path planning decision-making based on the minimum collision trajectory mileage information in the trajectory point information under the first coordinate system;

A planning unit, configured to perform longitudinal path trajectory planning based on the updated path boundary.

According to one aspect of the present application, a vehicle is provided, including a path planning device for the above-mentioned vehicle.

According to one aspect of the present application, a storage medium is provided, and at least one executable instruction is stored in the storage medium. The executable instruction causes the processor to perform operations corresponding to the above-mentioned vehicle path planning method.

According to one aspect of the present application, a terminal is provided, including: a processor, a memory, a communication interface and a communication bus, and the processor, the memory and the communication interface complete communication with each other through the communication bus;

The memory is used to store at least one executable instruction, and the executable instruction causes the processor to perform operations corresponding to the vehicle path planning method.

Through the above technical solutions, the technical solutions provided by the embodiments of the present application have at least the following advantages:

The present application provides a vehicle path planning method and device, storage medium, vehicle, and terminal. Compared with the existing technology, the embodiment of the present application obtains the trajectory mileage information of the vehicle in the first coordinate system; A vehicle envelope model matching the trajectory mileage information is constructed, and an interference relationship between the vehicle and the obstacle is determined based on the vehicle envelope model; and the interference relationship between the vehicle and the obstacle is determined based on the interference relationship. Under the condition of collision with an obstacle, the trajectory point information of the collision is determined in the first coordinate system based on the interference relationship, and path planning is performed based on the trajectory point information to realize the extension in the form of constructing the vehicle extension envelope. The collision detection range of the vehicle greatly improves the accuracy of collision detection, thereby improving the effectiveness of the vehicle's path planning.

The above description is only an overview of the technical solutions of the present application. In order to have a clearer understanding of the technical means of the present application, they can be implemented according to the content of the description, and in order to make the above and other purposes, features and advantages of the present application more obvious and understandable. , the specific implementation methods of the present application are specifically listed below.

Description of drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are for the purpose of illustrating preferred embodiments only and are not to be construed as limiting the application. Also throughout the drawings, the same reference characters are used to designate the same components. In the attached picture:

Figure 1 shows a flow chart of a vehicle path planning method provided by an embodiment of the present application;

Figure 2 shows a flow chart of another vehicle path planning method provided by an embodiment of the present application;

Figure 3 shows a schematic diagram of a coordinate system transformation provided by an embodiment of the present application;

Figure 4 shows a schematic diagram of a vehicle envelope model provided by an embodiment of the present application;

Figure 5 shows a schematic diagram of an overlapping interference relationship between a vehicle and an obstacle provided by an embodiment of the present application;

Figure 6 shows a schematic diagram of a trajectory index provided by an embodiment of the present application;

Figure 7 shows a block diagram of a vehicle path planning device provided by an embodiment of the present application;

FIG8 shows a schematic diagram of the structure of a terminal provided in an embodiment of the present application.

Detailed ways

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that a thorough understanding of the disclosure will be provided, and the scope of the disclosure will be fully conveyed to those skilled in the art.

For longitudinal path planning in the Frenet coordinate system, paths in turning scenarios with different curvatures are usually planned based on the projection of the vehicle on the reference path. However, due to the large curvature turning scenario, obstacles at different positions are located in the Frenet coordinate system. The projection distance between the system and the vehicle is the same, so that the projection between the vehicle and the obstacle cannot effectively confirm whether a collision has occurred, which greatly reduces the accuracy of collision detection, creates a greater risk of collision, and thus reduces the effectiveness of the vehicle's path planning. An embodiment of the present application provides a vehicle path planning method, as shown in Figure 1. The method includes:

101. Obtain the trajectory mileage information of the vehicle in the first coordinate system.

In the embodiment of this application, when the vehicle is performing trajectory planning, the autonomous driving processor as the current execution subject can be a processor configured on the vehicle side, or a cloud server matching the vehicle, etc. At this time, the current execution subject can be based on The vehicle's reference trajectory is used to plan the vehicle's trajectory to perform automatic driving control of the vehicle based on the obtained path trajectory. The first coordinate system is a coordinate system constructed from the distance along the trajectory and the distance from the trajectory centerline, preferably the Frenrt coordinate system, that is, the trajectory mileage information in the Frenrt coordinate system is obtained. At the same time, since the mileage is used to represent the length of the vehicle's travel, at this time, the trajectory mileage information in the first coordinate system includes the path length, heading angle, and direction of the vehicle traveling at each trajectory point on the reference path in the Frenrt coordinate system. Curvature, etc.

It should be noted that vehicles are vehicles with automatic control systems in autonomous driving scenarios, including passenger cars and commercial vehicles. Common models of passenger cars include but are not limited to sedans, sports utility vehicles, multi-person commercial vehicles, etc. Common types of commercial vehicles include but are not limited to pickup trucks, minibuses, self-unloading trucks, trucks, tractors, trailers and mining vehicles. At this time, the vehicle can realize automatic driving based on the automatic control system.

102. Construct a vehicle envelope model matching the trajectory mileage information in the second coordinate system, and determine the interference relationship between the vehicle and obstacles based on the vehicle envelope model.

In the embodiment of this application, since the trajectory mileage information is in the first coordinate system, in order to build a matching vehicle envelope model, the trajectory mileage information needs to be converted to the second coordinate system, that is, the second coordinate system is used to represent The coordinate system of the vehicle's horizontal and vertical coordinate positions is preferably a Cartesian coordinate system. Specifically, the path length, heading angle, curvature, etc. in the Frenrt coordinate system can be converted into the x, y coordinates of the vehicle outline in the Cartesian coordinate system to judge the interference relationship. This application embodiment does not make it specific. limited. Among them, since the trajectory of the vehicle in the first coordinate system is composed of trajectory points, and the trajectory mileage information of the vehicle on the reference trajectory is calculated for each trajectory point, therefore, when constructing the vehicle envelope model in the second coordinate system, conversion is required. Obtain the vehicle outline model, which includes the position coordinates of the four outline corner points of the vehicle outline model, in order to construct the vehicle envelope model. Specifically, the vehicle envelope model is obtained by expanding and extending the vehicle outline model, including but not limited to the model obtained by expanding and extending the vehicle laterally and/or longitudinally, so as to determine the relationship between the vehicle and obstacles based on the vehicle envelope model. The interference relationship between them is not specifically limited in the embodiment of this application.

It should be noted that when determining the interference relationship, the contour information corresponding to all obstacles can be mapped in the second coordinate system based on the sensing device in the current execution end, such as image sensor, infrared sensor and other sensing devices. The interference relationship is determined by whether the obstacle contour information of the obstacle overlaps with the vehicle envelope model. Among them, the interference relationship is used to represent whether the normal driving between the vehicle and the obstacle is affected. The interference relationship includes overlapping interference and non-overlapping interference. Overlapping interference is the relationship between the vehicle and the obstacle that cannot drive normally due to overlap, such as a collision. , the non-overlapping interference relationship is a relationship that although there is no collision between the vehicle and the obstacle, it still affects normal driving. For example, the vehicle is too close to the obstacle and causes the driver to panic. This is not specifically limited in the embodiment of this application.

103. When it is determined that the vehicle collides with the obstacle based on the interference relationship, determine the trajectory point information of the collision in the first coordinate system based on the interference relationship, and determine the trajectory point information based on the trajectory point information. Carry out path planning.

In the embodiment of the present application, when the interference relationship is an overlapping interference relationship, it is determined that the vehicle collides with the obstacle. At this time, in order to avoid the vehicle colliding with the obstacle at the next moment, the first determination is made based on the overlapping interference relationship occurring at this time. Information about the trajectory point where the collision occurred in the coordinate system. Among them, since the interference relationship is determined in the second coordinate system, the interference relationship is converted to the first coordinate system, thereby determining the trajectory point information of the collision in the first coordinate system, and re-calculating based on this trajectory point information. route plan.

It should be noted that the path planning in the embodiment of the present application can be a longitudinal planning of the vehicle's driving trajectory, and since the trajectory point information is used to represent the information on the reference path where the vehicle collides, specifically, it can be performed through the trajectory point information. Determine the path boundary, and use this path boundary as a constraint for path planning decisions to obtain the expected driving trajectory of the vehicle, which improves the accuracy and effectiveness of driving path planning.

In another embodiment of the present application, for further definition and explanation, as shown in Figure 2, the step of constructing a vehicle envelope model matching the trajectory mileage information in the second coordinate system includes:

201. Convert the trajectory mileage information in the first coordinate system into a vehicle outline model in the second coordinate system;

202. Determine the extension length based on the vehicle's speed influence coefficient, vehicle speed, preset speed expansion coefficient, curvature influence coefficient, trajectory curvature, and preset curvature expansion coefficient;

203. In the longitudinal direction of the vehicle outline model, extend and construct the vehicle outline model according to the extension length to obtain the vehicle envelope model.

Since the second coordinate system is preferably a Cartesian coordinate system, the vehicle envelope model constructed under this coordinate system is used for collision detection. Therefore, in order to meet the needs for accurate construction of the vehicle envelope model, the first coordinate system is first The trajectory mileage information is converted into a vehicle outline model in the second coordinate system. Among them, since the first coordinate system is preferably the Frenrt coordinate system, as shown in Figure 3, in the Frenrt coordinate system, each trajectory point represents the vehicle center position of the vehicle on the path, that is, the trajectory point of the vehicle in the Frenrt coordinate system can be The position is converted to the Cartesian coordinate system, and then combined with the outline size of the vehicle, a vehicle outline model of the vehicle in the Cartesian coordinate system is obtained, which is not specifically limited in the embodiment of the present application. Since constructing the vehicle envelope model is to expand and extend the vehicle outline model, specifically, the extension length is first determined based on the vehicle's speed influence coefficient, vehicle speed, preset speed expansion coefficient, curvature influence coefficient, trajectory curvature, and preset curvature expansion coefficient. In order to extend according to the extension length based on the vehicle outline model. In the embodiment of the present application, when performing the extension construction, the vehicle outline model is extended according to the extension length in the longitudinal direction of the vehicle outline model. At this time, the longitudinal direction is the direction in which the vehicle travels. As shown in Figure 4, the vehicle outline model is obtained. Envelope model to perform collision detection based on this vehicle envelope model.

In another embodiment of the present application, for further definition and explanation, the step of determining the extension length based on the vehicle's speed influence coefficient, vehicle speed, preset speed expansion coefficient, curvature influence coefficient, trajectory curvature, and preset curvature expansion coefficient includes:

In the embodiment of the present application, in order to accurately and effectively determine the extension length to meet the collision detection requirements of the vehicle in path planning, based on the vehicle's speed influence coefficient, vehicle speed, preset speed expansion coefficient, curvature influence coefficient, trajectory curvature, When the preset curvature expansion coefficient is used to determine the extension length, specifically, the maximum speed coefficient is selected from the dot product of the speed influence coefficient and the vehicle speed, and the preset speed expansion coefficient, and the maximum speed coefficient is selected from the dot product of the curvature influence coefficient and the trajectory curvature, and the preset speed expansion coefficient. Select the largest curvature coefficient among the curvature expansion coefficients to sum up the two largest coefficients to obtain the extension length. Among them, the speed influence coefficient is the influence degree of the vehicle speed on the extension length, the curvature influence coefficient is the influence degree of the curvature of the vehicle on the path on the extension length, and the preset speed expansion coefficient is the preconfigured large expansion caused by the speed factor. value, the preset curvature expansion coefficient is the pre-configured maximum expansion value generated by the curvature factor. The trajectory curvature is the maximum curvature of the vehicle on the reference path, and the vehicle speed is the speed of the vehicle on the reference path. At this time, the speed influence coefficient, The curvature influence coefficient, the preset speed expansion coefficient, and the preset curvature expansion coefficient can be configured in advance, such as =0.5, =0.5, =1.5, =1, so that the extension length is calculated through Formula 1 and the vehicle envelope model is constructed. As shown in Figure 4, (Formula 1) is not specifically limited in the embodiment of the present application.

In another embodiment of the present application, for further definition and explanation, the step of determining the interference relationship between the vehicle and the obstacle according to the vehicle envelope model includes:

Calculate overlap information between the obstacle outline information and the vehicle envelope model, and determine an interference relationship based on the overlap information;

Correspondingly, after determining the interference relationship between the vehicle and the obstacle according to the vehicle envelope model, the method further includes:

In order to accurately perform collision detection based on the vehicle envelope model, after constructing the vehicle envelope model, obtain the obstacle contour information of all obstacles on the vehicle's reference trajectory in the second coordinate system, that is, the Cartesian coordinate system, To determine whether there is overlap based on the obstacle contour information and the vehicle envelope model. Among them, the obstacle outline information is the specific horizontal and vertical coordinates of the obstacle outline in the Cartesian coordinate system, and the overlap judgment is made with the specific horizontal and vertical coordinates of the vehicle envelope model in the Cartesian coordinate system, and the overlap information is calculated. At this time, the overlapping information between the calculated obstacle outline information and the vehicle envelope model is the information about the overlap between the obstacle outline and the vehicle envelope outline in the Cartesian coordinate system, as shown in the overlapping shaded part in Figure 5 , that is, the overlapping information consists of the intersection of two contours. When it is determined based on the intersection part that the intersection area corresponding to the overlapping information is not zero, it means that there is overlap and the interference relationship is overlapping interference, for example, a collision occurs; when there is no intersection, it is determined that the intersection area corresponding to the overlapping information is zero. , it means that there is no overlap, and the interference relationship is non-overlapping interference. For example, no collision will occur, but panic will occur. The embodiment of the present application does not make a specific limit. Furthermore, if the interference relationship is determined to be overlapping interference, it means that the contours corresponding to the vehicle and the obstacle intersect, that is, it is determined that a collision occurs between the vehicle and the obstacle.

It should be noted that in the embodiment of the present application, the case of overlapping interference can be directly processed based on the path planning method in the embodiment of the present application, and for the case of non-overlapping interference, the vehicle can be slowly controlled to pass through by decelerating. For paths with large curvatures such as curves, the driver's panic can also be alleviated by braking and then the vehicle can be re-controlled to slowly pass through the above path. This embodiment of the present application does not make a specific limitation.

In another embodiment of the present application, for further definition and explanation, the step of determining the collision trajectory point information in the first coordinate system based on the interference relationship includes:

The trajectory point information of the collision is generated according to the position in the first coordinate system.

In the embodiment of the present application, in order to further perform trajectory planning and determine the trajectory point information of the collision when the expected collision between the vehicle and the obstacle is determined based on the interference relationship, specifically, the position of the vehicle in the second coordinate system is converted based on the overlapping information. to the first coordinate system to generate collision point information based on this position. Among them, since the overlapping information is the coordinate information of the overlapping part between the outline of the obstacle and the outline of the vehicle envelope model in the Cartesian coordinate system, the position of the vehicle can be determined through the coordinate information of the overlapping part, and then this position can be converted into in Frenrt coordinate system. At this time, each position of the vehicle is represented by a trajectory point in the Frenrt coordinate system, and the frame data collected by the current execution end during collision detection usually contains multiple trajectory positions of a vehicle, so as to determine Multiple trajectory mileage information, therefore, there may be multiple locations where a collision occurs based on the overlapping information, that is, multiple trajectory points corresponding to multiple locations. Furthermore, when the trajectory point information is generated based on multiple positions in the first coordinate system, the trajectory point information includes the trajectory point index and the collision trajectory mileage information, where the trajectory point index is the trajectory point sorting information of the vehicle collision, and the collision trajectory The mileage information is the length of the driving path calculated by the vehicle at each trajectory point, which is not specifically limited in the embodiment of this application.

For example, the trajectory point information converted to the first coordinate system is shown in Figure 6. s1 and s2 are respectively the trajectory point index in the trajectory point information, that is, the trajectory point sorting information of the vehicle collision, s1=a, s2= b, a and b are collision trajectory mileage information respectively. At this time, the trajectory point index can also be represented by sorting, as the mileage information of each collision point, as the indexed trajectory point, which is not specifically limited in the embodiment of the present application.

In another embodiment of the present application, for further definition and explanation, the step of obtaining the trajectory mileage information of the vehicle in the first coordinate system includes:

Since the current execution end collects the trajectory points of the vehicle in the reference trajectory in units of frames, one collection can contain trajectory points corresponding to 8 or more frames. Therefore, the corresponding vehicle can correspond to multiple trajectory points. In order to improve the accuracy of vehicle collision detection, when obtaining the trajectory mileage information, specifically, in the first coordinate system, the reference trajectory of the vehicle's transverse trajectory planning in the preset planning frame is obtained. The transverse trajectory planning is the vehicle's trajectory on the reference path. The trajectory planning strategy is carried out in the horizontal direction. At this time, the reference trajectory is a reference path that has been planned and configured for the vehicle in advance, so that the vehicle can perform trajectory planning while driving on this reference trajectory, thereby realizing automatic driving.

It should be noted that since mileage is used to represent the length of vehicle travel, combined with each track point on the reference trajectory, the path length, heading angle, curvature and other contents of the vehicle traveling on the reference path in the Frenrt coordinate system can be calculated. For example, the path length can be calculated based on the starting point of the reference trajectory and the position of the vehicle trajectory point collected at the current moment, the heading angle can be calculated based on the vehicle's driving direction and the tangent direction of the reference trajectory, and then the curvature of the trajectory can be calculated based on the heading angle. , there is no specific limitation in the embodiments of this application.

In another embodiment of the present application, for further definition and explanation, the step of performing path planning based on the trajectory point information includes:

In the embodiment of the present application, since the trajectory point information may contain the trajectory point index of multiple trajectory points and the corresponding collision trajectory mileage information, in order to effectively perform trajectory planning based on the trajectory point information, first, in the first coordinate system, from the trajectory Select the smallest collision trajectory mileage information among multiple collision trajectory point mileage information of point information to update it as the path boundary. Among them, the path boundary in the embodiment of the present application is used for longitudinal path planning, and the path boundary is used as a constraint condition in the longitudinal path trajectory planning strategy to be optimized and solved to obtain an updated planned path. At this time, the updated path boundary s_bound is the planned path obtained by using the minimum collision trajectory mileage information as a constraint and using quadratic programming to achieve longitudinal planning of obstacles inside and outside the curve in a large curvature scene. .

The embodiment of the present application provides a vehicle path planning method. Compared with the existing technology, the embodiment of the present application obtains the trajectory mileage information of the vehicle in the first coordinate system; and constructs the trajectory in the second coordinate system. The vehicle envelope model matching the mileage information, and the interference relationship between the vehicle and the obstacle is determined based on the vehicle envelope model; under the condition of determining the collision between the vehicle and the obstacle based on the interference relationship, Based on the interference relationship, the trajectory point information of the collision is determined in the first coordinate system, and path planning is performed based on the trajectory point information, so as to extend the collision detection range of the vehicle in the form of constructing a vehicle extension envelope, which greatly The accuracy of collision detection is improved, thereby improving the effectiveness of vehicle path planning.

Further, as an implementation of the method shown in Figure 1 above, an embodiment of the present application provides a vehicle path planning device, as shown in Figure 7, the device includes:

The acquisition module 31 is used to acquire the trajectory mileage information of the vehicle in the first coordinate system;

Determination module 32, configured to construct a vehicle envelope model matching the trajectory mileage information in the second coordinate system, and determine the interference relationship between the vehicle and obstacles according to the vehicle envelope model;

The planning module 33 is configured to determine the trajectory point information of the collision in the first coordinate system based on the interference relationship when it is determined that the vehicle and the obstacle collide according to the interference relationship, and determine the collision point information according to the interference relationship. The trajectory point information is used for path planning.

Further, the determining module includes:

Further, the planning module includes:

Further, the planning module also includes:

The embodiment of the present application provides a path planning device for a vehicle. Compared with the existing technology, the embodiment of the present application obtains the trajectory mileage information of the vehicle in the first coordinate system; and constructs the trajectory corresponding to the trajectory in the second coordinate system. The vehicle envelope model matching the mileage information, and the interference relationship between the vehicle and the obstacle is determined based on the vehicle envelope model; under the condition of determining the collision between the vehicle and the obstacle based on the interference relationship, Based on the interference relationship, the trajectory point information of the collision is determined in the first coordinate system, and path planning is performed based on the trajectory point information, so as to extend the collision detection range of the vehicle in the form of constructing a vehicle extension envelope, which greatly The accuracy of collision detection is improved, thereby improving the effectiveness of vehicle path planning.

According to an embodiment of the present application, a storage medium is provided. The storage medium stores at least one executable instruction. The computer-executable instruction can execute the vehicle path planning method in any of the above method embodiments.

Figure 8 shows a schematic structural diagram of a terminal provided according to an embodiment of the present application. The specific embodiment of the present application does not limit the specific implementation of the terminal.

As shown in Figure 8, the terminal may include: a processor (processor) 402, a communication interface (Communications Interface) 404, a memory (memory) 406, and a communication bus 408.

Among them: the processor 402, the communication interface 404, and the memory 406 complete communication with each other through the communication bus 408.

Communication interface 404 is used to communicate with network elements of other devices such as clients or other servers.

The processor 402 is configured to execute the program 410. Specifically, it may execute the relevant steps in the above vehicle path planning method embodiment.

Specifically, program 410 may include program code including computer operating instructions.

The processor 402 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present application. The one or more processors included in the terminal may be the same type of processor, such as one or more CPUs; or they may be different types of processors, such as one or more CPUs and one or more ASICs.

Memory 406 is used to store programs 410. The memory 406 may include high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.

The program 410 may be specifically used to cause the processor 402 to perform the following operations:

Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the present application can be implemented using general-purpose computing devices, and they can be concentrated on a single computing device, or distributed across a network composed of multiple computing devices. , optionally, they may be implemented in program code executable by a computing device, such that they may be stored in a storage device for execution by the computing device, and in some cases, may be in a sequence different from that herein. The steps shown or described are performed either individually as individual integrated circuit modules, or as multiple modules or steps among them as a single integrated circuit module. As such, the application is not limited to any specific combination of hardware and software.

The above descriptions are only preferred embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of this application shall be included in the protection scope of this application.

Claims

A vehicle path planning method, which includes:

Obtain the trajectory mileage information of the vehicle in the first coordinate system;

Construct a vehicle envelope model matching the trajectory mileage information in the second coordinate system, and determine the interference relationship between the vehicle and the obstacle based on the vehicle envelope model;

When the collision condition between the vehicle and the obstacle is determined based on the interference relationship, the trajectory point information of the collision is determined in the first coordinate system based on the interference relationship, and the path is determined based on the trajectory point information. planning.
The method according to claim 1, wherein constructing a vehicle envelope model matching the trajectory mileage information in the second coordinate system includes:

Convert the trajectory mileage information in the first coordinate system into a vehicle outline model in the second coordinate system;

Determine the extension length based on the vehicle's speed influence coefficient, vehicle speed, preset speed expansion coefficient, curvature influence coefficient, trajectory curvature, and preset curvature expansion coefficient;

In the longitudinal direction of the vehicle outline model, the vehicle outline model is extended and constructed according to the extension length to obtain the vehicle envelope model.
The method according to claim 2, wherein determining the extension length based on the vehicle's speed influence coefficient, vehicle speed, preset speed expansion coefficient, curvature influence coefficient, trajectory curvature, and preset curvature expansion coefficient includes:

Select the maximum speed coefficient from the dot product of the speed influence coefficient and the vehicle speed and the preset speed expansion coefficient, and select the maximum speed coefficient from the dot product of the curvature influence coefficient and the trajectory curvature, the preset curvature Select the maximum curvature coefficient from the expansion coefficient;

The extension length is obtained according to the sum operation of the maximum speed coefficient and the maximum curvature coefficient.
The method according to claim 1, wherein determining the interference relationship between the vehicle and the obstacle according to the vehicle envelope model includes:

Obtain the obstacle outline information of the obstacle in the second coordinate system;

Calculate the overlap information between the obstacle contour information and the vehicle envelope model, and determine an interference relationship based on the overlap information, where the interference relationship includes overlapping interference and non-overlapping interference;

After determining the interference relationship between the vehicle and the obstacle according to the vehicle envelope model, the method further includes:

If the interference relationship is overlapping interference, it is determined that the vehicle collides with the obstacle.
The method according to claim 4, wherein determining the collision trajectory point information in the first coordinate system based on the interference relationship includes:

Convert the collision position of the vehicle in the second coordinate system to the first coordinate system based on the overlapping information;

The trajectory point information of the collision is generated according to the position in the first coordinate system, and the trajectory point information includes the trajectory point index and the collision trajectory mileage information.
The method according to any one of claims 1 to 5, wherein said obtaining the trajectory mileage information of the vehicle in the first coordinate system includes:

Under the first coordinate system, obtain the reference trajectory of the vehicle lateral trajectory planning in the preset planning frame;

Calculate the trajectory mileage information of each trajectory point according to the reference trajectory.
The method according to claim 6, wherein the path planning based on the trajectory point information includes:

Under the first coordinate system, update the path boundary used for longitudinal path planning decision-making according to the minimum collision trajectory mileage information in the trajectory point information;

Perform longitudinal path trajectory planning based on the updated path boundary.
A vehicle path planning device, which includes:

The acquisition module is used to obtain the trajectory mileage information of the vehicle in the first coordinate system;

A determination module configured to construct a vehicle envelope model that matches the trajectory mileage information in a second coordinate system, and determine the interference relationship between the vehicle and obstacles based on the vehicle envelope model;

A planning module, configured to determine the trajectory point information of the collision in the first coordinate system based on the interference relationship under the condition that the vehicle and the obstacle are determined to collide according to the interference relationship, and according to the Track point information is used for path planning.
A vehicle, which includes the vehicle path planning device according to claim 8.
A storage medium in which at least one executable instruction is stored. The executable instruction causes the processor to perform operations corresponding to the path planning method for a vehicle according to any one of claims 1-7. .
A terminal, including: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;

The memory is used to store at least one executable instruction, and the executable instruction causes the processor to perform operations corresponding to the vehicle path planning method according to any one of claims 1-7.