WO2022148172A1

WO2022148172A1 - Lane line planning method and related apparatus

Info

Publication number: WO2022148172A1
Application number: PCT/CN2021/133214
Authority: WO
Inventors: 刘大伟; 周旺
Original assignee: 华为技术有限公司
Priority date: 2021-01-08
Filing date: 2021-11-25
Publication date: 2022-07-14
Also published as: CN114754780A

Abstract

A lane line planning method, a lane line planning apparatus, a high-precision map, an intelligent vehicle, a lane line planning device, and a computer readable storage medium. The method comprises: obtaining information of a first intersection, the information of the first intersection comprising information of a first reference point, information of a second reference point, and information of an obstacle of the first intersection (S301); determining a target projection point, wherein the target projection point is a projection point of the obstacle on a first depth and/or a second depth, the first depth is the depth of a first lane line extending to the first intersection, and the second depth is the depth of a second lane line extending to the first intersection (S302); and determining a lane line according to the first reference point, the second reference point and the target projection point (S303). According to the method, lane lines avoiding obstacles can be automatically planned, and the planning efficiency and accuracy are improved.

Description

Lane line planning method and related device

This application claims the priority of the Chinese patent application with the application number 202110026340.1 and the application name "lane planning method and related device" filed with the China Patent Office on January 8, 2021, the entire contents of which are incorporated into this application by reference .

technical field

The present application relates to the field of unmanned driving technology, and in particular, to a lane line planning method and related devices.

Background technique

With the maturity of artificial intelligence technology, autonomous driving technology has also developed rapidly. High-precision maps play a vital role in scenarios such as map search, automatic navigation, and autonomous driving. High-precision maps have relatively high requirements on the richness and accuracy of information, and can provide more detailed road information. It can provide geographic coordinate information of each lane on a road, and the accuracy can reach centimeter level. High-precision maps can also record rich road sign information such as crosswalks, overpasses, and traffic lights. In the intersection area, the high-precision map will also generate many lane-level virtual lane lines according to the actual road scene, providing accurate and smooth navigation information for cars driving at the intersection. Therefore, in the process of autonomous driving, the autonomous vehicle can drive on a lane-level path that is pre-planned on a high-precision map.

The mapping process of the high-precision map is usually driven by a technician to collect the vehicle, collect the environmental information of the area that the vehicle passes through, and fuse the various information obtained to generate an electronic map. Then cartographers will use various map labeling software to label the obtained electronic map automatically or manually to label various traffic information, such as lane lines, road signs, road signs and other traffic information.

For the lane lines in the intersections in the high-precision map, there are currently two labeling methods: manual labeling and automatic labeling. Among them: Manual labeling: It is labelled by the cartographer according to the obtained point cloud map, but the manually labelled lane lines are not only time-consuming It is laborious, and it is not easy to ensure the aesthetics of the lane lines. Automatic labeling: Automatic labeling is performed based on the obtained intersection information, but this method often does not consider the clearness of obstacles in the intersection, resulting in low labeling accuracy.

Whether it is manual labeling or automatic labeling, it is impossible to take into account the labeling efficiency and labeling accuracy of high-precision maps.

SUMMARY OF THE INVENTION

The embodiments of the present application improve a lane line planning method and a related device, which can automatically plan a lane line that avoids obstacles, thereby improving planning efficiency and accuracy.

In a first aspect, an embodiment of the present application provides a method for lane line planning, which may include: acquiring information of a first intersection, where the information of the first intersection includes information of a first reference point, information of a second reference point, and information of a first intersection. The information of obstacles at the intersection; the first intersection is the intersection where the lane line needs to be planned, the first reference point is the point on the first lane line, the second reference point is the point on the second lane line, and the first intersection The connected lane lines are the first lane line and the second lane line, the second lane line connects the first lane line through the lane line that needs to be planned at the first intersection, and the obstacle is the object in the first intersection that hinders the planned lane line; determine the target Projection point, where the target projection point is the projection point of the obstacle to the first depth and/or the second depth, the first depth is the depth of the first lane line extending to the first intersection, and the second depth is the second lane The depth of the line extending to the first intersection; the lane line is determined according to the first reference point, the second reference point and the target projection point.

With the method provided in the first aspect, the obstacles at the intersection are considered when planning the lane line at the intersection, so that the target projection point can be determined, and then the target projection point can be determined according to the first reference point, the second reference point and the target projection point. Lane lines can be determined. Because of the existence of the target projection point, it can be ensured that the generated lane line will not be pressed against obstacles, and no manual adjustment is required, which can improve the efficiency and accuracy of planning lane lines.

In a possible implementation manner, the method may further include: determining a planning area, and marking objects in the planning area as obstacles.

In the embodiment of the present application, only the part of the object close to the intersection may obstruct the planned lane line. Therefore, objects that may obstruct the planned lane line can be marked as obstacles through the planning area, so that the planned lane line will not be pressed against the obstacle. 's accuracy.

In a possible implementation manner, the method may further include: determining the planning area according to the first reference point, the second reference point, and an intersection point, where the intersection point is a point where the first depth and the second depth meet.

In this embodiment of the present application, since the first reference point, the second reference point and the intersection point are points required for planning lane lines, the planning area determined by the first reference point, the second reference point and the intersection point can quickly And accurately identify objects that obstruct the planned lane lines.

In a possible implementation manner, the method may further include: projecting N position points of the obstacle to the first depth to obtain N first projection points, where N is greater than or equal to 1; Project to the second depth to obtain N second projection points; select the target projection point from the N first projection points and the N second projection points, where the distance from the N first projection points to the first reference point maximum, and the first projection point whose distance to the corresponding point on the obstacle is less than or equal to the first threshold belongs to the target projection point; among the N second projection points, the distance to the second reference point is the largest, and the distance to the obstacle is the largest. The second projected point whose distance between the corresponding points on the 2 is less than or equal to the second threshold belongs to the target projected point.

In this embodiment of the present application, a target projection point that satisfies the preset requirements is selected from the N first projection points and/or the N second projection points according to a given preset condition, because the first threshold value in the preset condition is And the existence of the second threshold can improve the accuracy that the lane line drawn by the determined target projection will not overwhelm the obstacle, and also ensure that the vehicle can smoothly drive out of the intersection through the planned lane line.

In a possible implementation manner, the target projection point includes a first projection point, and the method may further include: determining a first line segment according to the first reference point and the first projection point; according to the first projection point and the second reference point and the intersection point to determine the first curve, and the intersection point is the point where the first depth and the second depth meet; the right-turn lane line is determined by the first line segment and the first curve.

In this embodiment of the present application, the lane line is composed of a first line segment and a first curve. The first line segment is the longest distance that can avoid obstacles at the entrance and can guarantee a right turn, so the first line segment can pass through the first line. In the case of completely avoiding the obstacle, the segment will go out of the intersection by the first curve.

In a possible implementation manner, the target projection point includes a second projection point, and the method may further include: determining a second curve according to the first reference point, the second projection point and an intersection point, where the intersection point is the first depth and the second depth The intersection point; the second straight line is determined according to the second projection point and the second reference point; the right-turn lane line is determined by the second curve and the second straight line.

In the embodiment of the present application, the lane line is composed of a second line segment and a second curve, and the second line segment is the longest distance that can avoid obstacles at the exit from the intersection and can guarantee the completion of a right turn. When reaching the obstacle, pass the second line segment to avoid pressing the obstacle.

In a possible implementation manner, the target projection point includes a first projection point and a second projection point, and the method may further include: determining a third line segment according to the first reference point and the first projection point; according to the first projection point, The second projection point and the intersection point determine the third curve, and the intersection point is the point where the first depth meets the second depth; the fourth line segment is determined according to the second projection point and the first reference point; the third line segment, the third curve and the fourth The line segment determines the right-turn lane line.

In the embodiment of the present application, the lane line is composed of a third line segment, a third curve and a fourth line segment, and the third line segment is the longest distance to avoid obstacles at the entrance to the intersection, which can ensure that the obstacles are completely avoided. Go down and turn right. The fourth line segment is the longest distance to avoid obstacles at the exit and can guarantee to complete a right turn. It can ensure that the fourth line segment is used to avoid hitting obstacles when turning right. thing.

In a possible implementation manner, the method may further include: both the first threshold value and the second threshold value are reference values obtained by training according to sample data, and the sample data is historical driving data of the driving trajectory to avoid obstacles.

In the embodiment of the present application, the first threshold value and the second threshold value obtained by training the sample data are more in line with the actual situation and have higher reliability.

In a second aspect, an embodiment of the present application provides a lane line planning device, the device may include: an acquisition unit configured to acquire information of a first intersection, where the information of the first intersection includes information of a first reference point, a second reference Point information and information of obstacles at the first intersection; wherein, the first intersection is the intersection where the lane line needs to be planned, the first reference point is the point on the first lane line, and the second reference point is the second lane line. Point, the lane lines connected to the first intersection are the first lane line and the second lane line, the second lane line is connected to the first lane line through the lane line of the first intersection, and the obstacles are the obstacles in the first intersection that obstruct the planned lane line. Object; a determining unit for determining a target projection point, wherein the target projection point is the projection point of the obstacle to the first depth and/or the second depth, and the first depth is the extension of the first lane line to the first intersection. depth, the second depth is the depth of the second lane line extending to the first intersection; the planning unit is used to determine the lane line according to the first reference point, the second reference point and the target projection point.

In a possible implementation manner of the second aspect, the determining unit is further configured to: determine a planning area, and mark objects in the planning area as obstacles.

In a possible implementation manner of the second aspect, the determining unit is specifically configured to: determine the planning area according to the first reference point, the second reference point, and an intersection point, where the intersection point is a point where the first depth and the second depth intersect.

In a possible implementation of the second aspect, the determining unit is specifically configured to: project the N position points of the obstacle to the first depth to obtain N first projection points, where N is greater than or equal to 1; N position points are projected to the second depth, and N second projection points are obtained; the target projection point is selected from the N first projection points and the N second projection points, wherein, among the N first projection points to the first The distance to the reference point is the largest, and the first projection point whose distance to the corresponding point on the obstacle is less than or equal to the first threshold belongs to the target projection point; the distance to the second reference point is the largest among the N second projection points, and , the second projection point whose distance to the corresponding point on the obstacle is less than or equal to the second threshold belongs to the target projection point.

In a possible implementation of the second aspect, the target projection point is the first projection point, the lane line is the right-turn lane line, and the planning unit is specifically configured to: determine the first line according to the first reference point and the first projection point The first curve is determined according to the first projection point, the second reference point and the intersection point, and the intersection point is the point where the first depth and the second depth meet; the right-turn lane line is determined by the first line segment and the first curve.

In a possible implementation of the second aspect, the target projection point is the second projection point, the lane line is the right-turn lane line, and the planning unit is specifically configured to: determine the first reference point, the second projection point, and the intersection point. Two curves, the intersection point is the point where the first depth meets the second depth; the second straight line is determined according to the second projection point and the second reference point; the right-turn lane line is determined by the second curve and the second straight line.

In a possible implementation of the second aspect, the target projection point includes a first projection point and a second projection point, the lane line is a right-turn lane line, and the planning unit is specifically configured to: according to the first reference point and the first projection point to determine the third line segment; determine the third curve according to the first projection point, the second projection point and the intersection point, the intersection point is the point where the first depth and the second depth meet; determine the fourth line segment according to the second projection point and the first reference point ; Determine the right-turn lane line by the third line segment, the third curve and the fourth line segment.

In a third aspect, an embodiment of the present application provides a high-precision map, and the high-precision map includes the method described in the first aspect or any possible implementation manner of the first aspect according to the first reference point and the second reference point. and the lane line determined by the target projection point.

In a fourth aspect, an embodiment of the present application provides an intelligent vehicle, the intelligent vehicle includes at least one processor and at least one memory, and the at least one processor is configured to call a computer program stored in the at least one memory, so that the intelligent vehicle executes the first aspect or the method described in any one possible implementation manner of the first aspect.

In a fifth aspect, an embodiment of the present application provides a lane line planning device, the lane line planning device includes at least one processor and at least one memory, and the at least one processor is configured to call a computer program stored in the at least one memory, so that the apparatus executes The method described in the first aspect or any possible implementation manner of the first aspect.

In a sixth aspect, embodiments of the present application provide a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program runs on one or more processors, the first aspect or the first aspect is executed. The method described in any of the possible embodiments of the aspect.

In a seventh aspect, an embodiment of the present application provides a computer program product. When the computer program product runs on one or more processors, the first aspect or any possible implementation manner of the first aspect is executed. method.

Description of drawings

The accompanying drawings used in the embodiments of the present application will be introduced below.

1 is a schematic diagram of a scene for drawing lane lines provided by the prior art;

2A is a schematic structural diagram of a lane line planning system provided by an embodiment of the present application;

2B is a schematic structural diagram of another lane planning system provided by an embodiment of the present application;

FIG. 2C is a functional block diagram of an intelligent vehicle 003 provided by an embodiment of the present application;

3A is a schematic flowchart of a method for drawing lane lines according to an embodiment of the present application;

3B is a schematic diagram of intersection information provided by an embodiment of the present application;

3C is a schematic diagram of determining a target projection point provided by an embodiment of the present application;

4 is a schematic diagram of another scene for drawing lane lines provided by an embodiment of the present application;

5 is a schematic diagram of another scene for drawing lane lines provided by an embodiment of the present application;

6 is a schematic diagram of another scene for drawing lane lines provided by an embodiment of the present application;

7 is a schematic structural diagram of a lane line planning device provided by an embodiment of the present application;

FIG. 8 is a schematic structural diagram of a lane line planning device provided by an embodiment of the present application.

Detailed ways

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

First, the related technologies involved in the embodiments of the present application are explained so as to be understood by those skilled in the art.

1. High-precision map

A high-resolution map, also known as a high-resolution map (HD Map, High Definition Map), is a map specially designed for unmanned driving. Unlike traditional navigation maps, high-precision maps can provide lane-level navigation information in addition to road-level navigation information. Both in the richness of the information and the accuracy of the information, it is far higher than the traditional navigation map.

For example, lane-level navigation information can include high-precision coordinates, as well as accurate road shape, slope, curvature, heading, elevation, roll, and other data for each lane.

2. Vector data

Vector data is in Cartesian coordinates, using x and y coordinates to represent the position and shape of map graphics or geographic entities. Generally, the spatial position of geographic entities is expressed as accurately as possible by recording coordinates. Also, vector data can be internal data stored in a vector structure in a computer, which is a direct product of a tracking digitizer. In the vector data structure, point data can be described directly by coordinate values; line data can be described by evenly or unevenly spaced sequential coordinate chains; surface data (or polygon data) can be described by boundary lines.

At present, the method for planning lane lines at intersections may include the following steps:

S1. Determine the information of the first reference point, where the first reference point is a point on the first lane.

Please refer to FIG. 1 . FIG. 1 is a schematic diagram of a scene for drawing lane lines provided by the prior art. FIG. 1 takes drawing a lane line for a right turn as an example for description. It can be seen from (1) of FIG. 1 that the first reference point is the first reference point 101A. Optionally, the first reference point 101A is a point on the first lane line 104A, and the first reference point 101A may specifically be the first lane line 104A (or an extension of the first lane line 104A) on an area close to the intersection 106 The intersection 106 is the intersection where lane lines need to be marked, the lanes connected to the intersection 106 are the first lane 102 and the second lane 103 , and the first lane line 104A may be the lane edge line of the first lane 102 .

S2. Determine the information of the second reference point, where the second reference point is a point on the second lane.

Please refer to ( 1 ) of FIG. 1 , it can be seen from ( 1 ) of FIG. 1 that the second reference point is the second reference point 101B. Optionally, the second reference point 101B is a point on the second lane line 105A, and the second reference point 101B may specifically be the second lane line 105A (or an extension of the second lane line 105A) on an area close to the intersection 106 The second lane line 105A may be the lane edge line of the second lane 103 .

S3. Determine the intersection point, which is the point where the first lane line extends toward the intersection and the second lane line extends toward the intersection.

Referring to (1) of FIG. 1 , it can be seen from (1) of FIG. 1 that the intersection is the intersection 101C. The intersection point 101C is the point where the extension of the first lane line 104A toward the intersection meets the extension of the second lane line 105A toward the intersection.

S4, generating a right-turn lane line according to the first reference point, the second reference point and the intersection point.

As can be seen from (2) of FIG. 1 , the edge lane line of the right-turn lane line 107 generated according to the first reference point 101A, the intersection point 101C and the second reference point 101B intersects the obstacle 108 in the intersection 106, that is, the obstacle Object 108 may appear in the area covered by right-turn lane line 107 .

It can be seen that the lane lines drawn without obstacle avoidance processing may press on the obstacles in the intersection, and manual adjustment is still required, which is inefficient and prone to errors.

In order to facilitate understanding of the embodiments of the present application, the following first describes the structure of one of the lane line planning systems on which the embodiments of the present application are based. Please refer to FIG. 2A. FIG. 2A is a schematic structural diagram of a lane line planning system provided by an embodiment of the present application. The system includes a collection device 001 and a drawing device 002, wherein the collection device 001 and the drawing device 002 can communicate through a network to The collected raw data for drawing lane lines is sent to the drawing device 002, and the drawing device 002 completes the drawing of the lane lines.

The collection device 001 may be an electronic device with specific data collection capability and data transceiver capability. For example, the acquisition device 001 may be an acquisition vehicle equipped with one or more sensors such as lidar, camera, Global Navigation Satellite System (GNSS), Inertial Measurement Unit (IMU), etc. The collecting vehicle can collect the intersection information of the lane lines to be marked in the high-precision map, that is, before drawing the high-precision map, the information required for drawing the high-precision map can be collected by collecting vehicles driving on each road. Among them, lidar is mainly used to collect point cloud data, because lidar can accurately reflect position information, so the width of the road, the height of signal lights and some other information can be obtained through lidar; the camera is mainly used to collect road signs, Lane lines and other information; GNSS is mainly used to record the coordinates of the current collection point; IMU is mainly used to record the angle and acceleration information of the collection vehicle, and is used to correct the position and angle of the collection vehicle.

Alternatively, the collection device 001 may also be a roadside unit installed at an intersection, and the roadside unit may acquire intersection information within the coverage area, and monitor multiple smart vehicles within the coverage area. The roadside unit can collect the intersection information of the lanes to be planned in automatic driving, that is, the roadside unit can monitor the dynamics in the intersection at any time, and can send the information of the intersection to the intelligent vehicles that need to pass the intersection. It should be noted that the intersection information may be acquired by one roadside unit, or the intersection information may be acquired by the cooperation of multiple roadside units, so as to obtain the information of all roads connected to the intersection. Among them, the roadside unit may be composed of a high-gain directional beam control read-write antenna and a radio frequency controller. The high-gain directional beam control read-write antenna is a microwave transceiver module, responsible for signal and data transmission/reception, modulation/demodulation, encoding/decoding, encryption/decryption; the radio frequency controller is used to control the transmission and reception of data and the processing of the upper computer. A module for sending and receiving information.

The intersection information of the lane lines to be marked in the high-precision map can be collected through the collection device 001, such as road-level data at the intersection (that is, the data of each road connected to the intersection), lane-level data at the intersection (that is, the data of each road connected to the intersection). data for each lane connected to the intersection), information on obstacles within the intersection. Road-level can also be called non-high-precision vector road network data, which is used to describe specific roads from road-level accuracy. The road-level data is the road network data collected according to the road granularity, that is, a lane containing multiple lanes will only have one vector data with the unit of link (link) as the unit. Vector data includes a series of location coordinate points, usually a series of location coordinate points on the road centerline; road-level data also includes road grade, traffic capacity, number of lanes, road category, driving mode, road bandwidth, and so on. Lane-level data can be called high-precision vector road network data, which are used to describe specific roads from lane line accuracy. Specifically, lane-level data is road network data collected according to the granularity of lane lines, which may include, but is not limited to, lane edge line information of any road (including vector data of the location of the lane edge line), lane boundary line information (including lane edge line information) vector data of the location of the dividing line), etc. The obstacle can be an object that hinders driving in the intersection, the information of the obstacle can be vector data of the location of the obstacle, and the obstacle includes but is not limited to at least one of the following: curbs, trees, street lights, and so on.

The drawing apparatus 002 may be an electronic device with data processing capability and data transceiving capability, may be a physical device such as a host, rack server, blade server, etc., or may be a virtual device such as a virtual machine, a container, and the like. The drawing device 002 can obtain the intersection information of the lane line to be marked in the high-precision map, and then obtain the information of the first reference point, the information of the second reference point and the information of the obstacles of the first intersection from the intersection information; An intersection is an intersection where lane lines need to be planned, the first reference point is a point on the first lane line, the second reference point is a point on the second lane line, and the second lane line is connecting the first lane through the lane line inside the intersection The lane line of the line, the obstacle is the object that obstructs the planned lane line in the first intersection; and then the target projection point is determined, and the target projection point is the projection point of the obstacle to the first depth and/or the second depth. A depth is the depth of the first reference point extending to the first intersection, and the second depth is the depth of the second reference point extending to the first intersection. Finally, the drawing device 002 is based on the first reference point, the second reference point and the The target projection points are used as control points to determine the lane lines.

In a possible implementation manner, the drawing device 002 projects the N position points of the obstacle to the first depth to obtain N first projection points; the drawing device 002 projects the N position points of the obstacle to the second depth , to obtain N second projection points; then the drawing device 002 selects the target projection point from the N first projection points and the N second projection points, that is, the distance from the N first projection points to the first reference point The distance is the largest, and the first projection point whose distance to the corresponding point on the obstacle is less than or equal to the first threshold belongs to the target projection point; or, the distance from the N second projection points to the second reference point is the largest, and, The second projected point whose distance to the corresponding point on the obstacle is less than or equal to the second threshold belongs to the target projected point. The first threshold and the second threshold are values obtained through machine learning training according to the distance between the obstacle at the intersection and the lane line.

It should be noted that, when the collecting device 001 is collecting vehicles, the collected intersection information may be the intersection information of the lane lines to be marked in the high-precision map, and the drawing device 001 may be a device that generates a high-precision map. After the drawing device 001 generates the high-precision map, the above-mentioned high-precision map can be sent to the intelligent vehicle 003, and the intelligent vehicle 003 can complete the driving according to the high-precision map.

When the collection device 001 is a roadside unit installed at the intersection, the collected intersection information may be the information of the intersection of the lane line to be planned in automatic driving. Please refer to FIG. 2B , which is another kind of intersection provided by the embodiment of the present application. Schematic diagram of the architecture of the lane line planning system. As can be seen from FIG. 2B , the drawing device 001 can be an intelligent vehicle 003 driving at an intersection. When the intelligent vehicle 003 receives the information of the intersection sent by the roadside unit, it can plan a lane to avoid obstacles according to the information of the intersection. Wire.

It should be noted that the lane lines may include straight lane lines, left-turn lane lines, or right-turn lane lines, which are not limited in this embodiment of the present application.

It should be noted that a Bezier curve can be used to draw a lane line, and a spline curve can also be used to accurately draw a lane line, and the embodiment of the present application does not impose any limitation on a tool for drawing a lane line.

Based on the above system architecture for drawing lane lines, an embodiment of the present application provides an intelligent vehicle 003 applied to the above system architecture for drawing lane lines. Referring to FIG. 2C , FIG. 2C is a functional block diagram of an intelligent vehicle 003 provided by an embodiment of the present application. In one embodiment, the intelligent vehicle 003 may be configured in a fully or partially autonomous driving mode. For example, the intelligent vehicle 003 can control itself while in an autonomous driving mode, and can determine the current state of the vehicle and its surroundings through human manipulation, determine the possible behavior of at least one other vehicle in the surrounding environment, and determine the other The intelligent vehicle 003 is controlled based on the determined information with a confidence level corresponding to the likelihood that the vehicle will perform the possible behavior. When the intelligent vehicle 003 is in an autonomous driving mode, the intelligent vehicle 003 can be set to operate without human interaction.

Intelligent vehicle 003 may include various subsystems, such as travel system 202 , sensing system 204 , control system 206 , one or more peripherals 208 and power supply 210 , computer system 212 , and user interface 216 . Alternatively, the intelligent vehicle 003 may include more or fewer subsystems, and each subsystem may include multiple elements. Additionally, each of the subsystems and elements of the intelligent vehicle 003 may be interconnected by wire or wirelessly.

The travel system 202 may include components that provide powered motion for the intelligent vehicle 003 . In one embodiment, travel system 202 may include engine 218 , energy source 219 , transmission 220 , and wheels/tires 221 . Engine 218 may be an internal combustion engine, an electric motor, an air compression engine, or other types of engine combinations, such as a hybrid engine consisting of an air oil engine and an electric motor, a hybrid engine consisting of an internal combustion engine and an air compression engine. Engine 218 converts energy source 219 into mechanical energy.

Examples of energy sources 219 include gasoline, diesel, other petroleum-based fuels, propane, other compressed gas-based fuels, ethanol, solar panels, batteries, and other sources of electricity. The energy source 219 may also provide energy to other systems of the intelligent vehicle 003 .

Transmission 220 may transmit mechanical power from engine 218 to wheels 221 . Transmission 220 may include a gearbox, a differential, and a driveshaft. In one embodiment, transmission 220 may also include other devices, such as clutches. Among other things, the drive shafts may include one or more axles that may be coupled to one or more wheels 221 .

The sensing system 204 may include several sensors that sense information about the environment surrounding the intelligent vehicle 003 . For example, the sensing system 204 may include a global positioning system 222 (the positioning system may be a GPS system, a Beidou system or other positioning systems), an inertial measurement unit (IMU) 224, a radar 226, a laser rangefinder 228 and camera 230. The sensing system 204 may also include sensors that monitor the internal systems of the smart vehicle 003 (eg, an in-vehicle air quality monitor, a fuel gauge, an oil temperature gauge, etc.). Sensor data from one or more of these sensors can be used to detect objects and their corresponding characteristics (position, shape, orientation, velocity, etc.). This detection and identification is a critical function for the safe operation of the autonomous intelligent vehicle 003 .

The global positioning system 222 may be used to estimate the geographic location of the intelligent vehicle 003 . The IMU 224 is used to sense position and orientation changes of the intelligent vehicle 003 based on inertial acceleration. In one embodiment, the IMU 224 may be a combination of an accelerometer and a gyroscope. For example: IMU 224 may be used to measure the curvature of smart vehicle 003.

Radar 226 may utilize radio signals to sense objects within the surrounding environment of intelligent vehicle 003 . In some embodiments, in addition to sensing objects, radar 226 may be used to sense the speed and/or heading of objects.

The laser rangefinder 228 may utilize laser light to sense objects in the environment in which the intelligent vehicle 003 is located. In some embodiments, the laser rangefinder 228 may include one or more laser sources, laser scanners, and one or more detectors, among other system components.

Camera 230 may be used to capture multiple images of the surrounding environment of intelligent vehicle 003 . Camera 230 may be a still camera or a video camera.

The control system 206 controls the operation of the intelligent vehicle 003 and its components. Control system 206 may include various elements including steering system 232 , throttle 234 , braking unit 236 , sensors 238 , computer vision system 240 , route control system 242 , and obstacle avoidance system 244 .

Steering system 232 is operable to adjust the heading of intelligent vehicle 003 . For example, in one embodiment it may be a steering wheel system.

The throttle 234 is used to control the operating speed of the engine 218 and thus the speed of the intelligent vehicle 003 .

The braking unit 236 is used to control the deceleration of the intelligent vehicle 003 . The braking unit 236 may use friction to slow the wheels 221 . In other embodiments, the braking unit 236 may convert the kinetic energy of the wheels 221 into electrical current. The braking unit 236 may also take other forms to slow down the wheels 221 to control the speed of the smart vehicle 003 .

Computer vision system 240 is operable to process and analyze images captured by camera 230 in order to identify objects and/or features in the environment surrounding intelligent vehicle 003 . The objects and/or features may include traffic signals, road boundaries and obstacles. Computer vision system 240 may use object recognition algorithms, Structure from Motion (SFM) algorithms, video tracking, and other computer vision techniques. In some embodiments, computer vision system 240 may be used to map the environment, track objects, estimate the speed of objects, and the like.

The route control system 242 is used to determine the travel route of the intelligent vehicle 003 . In some embodiments, the route control system 242 may combine data from the sensors 238 , the global positioning system 222 , and one or more predetermined maps to determine a driving route for the intelligent vehicle 003 .

The obstacle avoidance system 244 is used to identify, evaluate and avoid or otherwise overcome potential obstacles in the environment of the intelligent vehicle 003 .

Of course, in one example, the control system 206 may additionally or alternatively include components other than those shown and described. Alternatively, some of the components shown above may be reduced.

The intelligent vehicle 003 interacts with external sensors, other vehicles, other computer systems, or the user through peripheral devices 208 . Peripherals 208 may include a wireless communication system 246 , an onboard computer 248 , a microphone 250 and/or a speaker 252 .

In some embodiments, peripherals 208 provide a means for a user of intelligent vehicle 003 to interact with user interface 216 . For example, the onboard computer 248 may provide information to the user of the smart vehicle 003 . User interface 216 may also operate on-board computer 248 to receive user input. The onboard computer 248 can be operated via a touch screen. In other cases, peripherals 208 may provide a means for intelligent vehicle 003 to communicate with other devices located within the vehicle. For example, microphone 250 may receive audio (eg, voice commands or other audio input) from a user of intelligent vehicle 003 . Similarly, speaker 252 may output audio to the user of smart vehicle 003 .

Wireless communication system 246 may wirelessly communicate with one or more devices, either directly or via a communication network. For example, wireless communication system 246 may use 3G cellular communications, such as CDMA, EVDO, GSM/GPRS, or 4G cellular communications, such as LTE. Or 5G cellular communications. The wireless communication system 246 may communicate with a wireless local area network (WLAN) using WiFi. In some embodiments, the wireless communication system 246 may communicate directly with the device using an infrared link, Bluetooth, or ZigBee. Other wireless protocols, such as various vehicle communication systems, for example, wireless communication system 246 may include one or more dedicated short range communications (DSRC) devices, which may include a combination of vehicle and/or roadside stations. public and/or private data communications between them.

Power supply 210 may provide power to various components of intelligent vehicle 003 . In one embodiment, the power source 210 may be a rechargeable lithium-ion or lead-acid battery. One or more battery packs of such batteries may be configured as a power source to provide power to various components of the intelligent vehicle 003 . In some embodiments, power source 210 and energy source 219 may be implemented together, such as in some all-electric vehicles.

Some or all of the functions of intelligent vehicle 003 are controlled by computer system 212 . Computer system 212 may include at least one processor 213 that executes instructions 215 stored in a non-transitory computer-readable medium such as memory 214 . Computer system 212 may also be multiple computing devices that control individual components or subsystems of intelligent vehicle 003 in a distributed fashion.

The processor 213 may be any conventional processor, such as a commercially available CPU. Alternatively, the processor may be a dedicated device such as an ASIC or other hardware-based processor. Although FIG. 2C functionally illustrates a processor, memory, and other elements of the computer in the same block, one of ordinary skill in the art will understand that the processor, computer, or memory may actually include storage that may or may not be Multiple processors, computers, or memories within the same physical enclosure. For example, the memory may be a hard drive or other storage medium located within an enclosure other than a computer. Thus, reference to a processor or computer will be understood to include reference to a collection of processors or computers or memories that may or may not operate in parallel. Rather than using a single processor to perform the steps described herein, some components such as the steering and deceleration components may each have their own processor that only performs computations related to component-specific functions .

In various aspects described herein, a processor may be located remotely from the vehicle and in wireless communication with the vehicle. In other aspects, some of the processes described herein are performed on a processor disposed within the vehicle while others are performed by a remote processor, including taking steps necessary to perform a single maneuver.

In some embodiments, memory 214 may include instructions 215 (eg, program logic) executable by processor 213 to perform various functions of intelligent vehicle 003, including those described above. Memory 214 may also contain additional instructions, including sending data to, receiving data from, interacting with and/or controlling one or more of travel system 202 , sensing system 204 , control system 206 and peripherals 208 instruction.

In addition to instructions 215, memory 214 may store data such as road maps, route information, vehicle location, direction, speed, and other such vehicle data, among other information. Such information may be used by intelligent vehicle 003 and computer system 212 during operation of intelligent vehicle 003 in autonomous, semi-autonomous, and/or manual modes.

User interface 216 for providing information to or receiving information from a user of intelligent vehicle 003 . Optionally, user interface 216 may include one or more input/output devices within the set of peripheral devices 208 , such as wireless communication system 246 , onboard computer 248 , microphone 250 and speaker 252 .

Computer system 212 may control functions of intelligent vehicle 003 based on input received from various subsystems (eg, wireless communication system 246 , travel system 202 , sensing system 204 , and control system 206 ) and from user interface 216 . For example, the computer system 212 may utilize input from the wireless communication system 246 to plan lane lines at intersections that need to be passed in autonomous driving by which obstacles at the intersection can be avoided. In some embodiments, computer system 212 is operable to provide control over many aspects of intelligent vehicle 003 and its subsystems.

Optionally, computer system 212 may also receive information from, or transfer information to, other computer systems. For example, the computer system 212 may transfer sensor data collected from the sensor system 204 of the smart vehicle 003 to another computer system remotely, and have the data processed by the other computer system, such as by another computer system. The data collected by each sensor in the sensor system 204 is fused, and then the data or analysis result obtained after fusion is returned to the computer system 212 . Optionally, data from computer system 212 may be transmitted via a network to a cloud-side computer system for further processing. Networks and intermediate nodes may include various configurations and protocols, including the Internet, the World Wide Web, Intranets, Virtual Private Networks, Wide Area Networks, Local Area Networks, private networks using one or more of the company's proprietary communication protocols, Ethernet, WiFi and HTTP, and various combinations of the foregoing. Such communications may be by any device capable of transferring data to and from other computers, such as modems and wireless interfaces.

As mentioned above, in some possible embodiments, the remote computer system that interacts with the computer system 212 in the intelligent vehicle 003 may include a server with multiple computers, such as a load balancing server farm, in order to receive, from the computer system 212 , The purpose of processing and transmitting data, which exchanges information with different nodes of the network. The server may have processors, memory, instructions and data, and the like. For example, in some embodiments of the present application, the data of the server may include providing weather-related information. For example, the server may receive, monitor, store, update, and transmit various information related to the weather. This information may include, for example, precipitation, cloud, and/or temperature information in the form of reports, radar information, forecasts, and the like. The data of the server can also include high-precision map data, traffic information of the road ahead (such as real-time traffic congestion and traffic accidents, etc.), and the server can send the high-precision map data and traffic information to the computer system 212 , so that it can assist the intelligent vehicle 003 to better perform automatic driving and ensure driving safety.

Optionally, one or more of these components described above may be installed or associated with the intelligent vehicle 003 separately. For example, memory 214 may exist partially or completely separate from intelligent vehicle 003 . The above-described components may be communicatively coupled together in a wired and/or wireless manner.

Optionally, the above component is just an example. In practical applications, components in each of the above modules may be added or deleted according to actual needs, and FIG. 2C should not be construed as a limitation on the embodiments of the present application.

A self-driving car traveling on a road, such as Smart Vehicle 003 above, can recognize objects within its surroundings to determine adjustments to its current speed. The objects may be other vehicles, traffic control equipment, or other types of objects. In some examples, each identified object may be considered independently, and based on the object's respective characteristics, such as its current speed, acceleration, distance from the vehicle, etc., may be used to determine the speed at which the autonomous vehicle is to adjust.

Optionally, the autonomous vehicle intelligent vehicle 003 or a computing device associated with the autonomous vehicle 003 (eg, computer system 212, computer vision system 240, memory 214 of FIG. 2C ) may be based on the characteristics of the identified objects and the surrounding environment. state (eg, traffic, rain, ice on the road, etc.) to predict the behavior of the identified object. Optionally, each identified object is dependent on the behavior of the other, so it is also possible to predict the behavior of a single identified object by considering all identified objects together. The intelligent vehicle 003 is able to adjust its speed based on the predicted behavior of the identified object. In other words, the self-driving car can determine what steady state the vehicle will need to adjust to (eg, accelerate, decelerate, or stop) based on the predicted behavior of the object. In this process, other factors may also be considered to determine the speed of the intelligent vehicle 003, such as the lateral position of the intelligent vehicle 003 in the road on which it is traveling, the curvature of the road, the proximity of static and dynamic objects, and the like.

In addition to providing instructions to adjust the speed of the self-driving car, the computing device may also provide instructions to modify the steering angle of the intelligent vehicle 003 so that the self-driving car follows a given trajectory and/or maintains contact with objects in the vicinity of the self-driving car ( For example, safe lateral and longitudinal distances for cars in adjacent lanes on the road.

The above-mentioned intelligent vehicles 003 can be cars, trucks, motorcycles, buses, boats, airplanes, helicopters, lawn mowers, recreational vehicles, playground vehicles, construction equipment, trams, golf carts, trains, and trolleys, etc., The embodiments of the present application are not particularly limited.

It can be understood that the function diagram of the smart vehicle 003 in FIG. 2C is only an exemplary implementation in the embodiments of the present application, and the smart vehicle 003 in the embodiments of the present application includes but is not limited to the above structures.

Please refer to FIG. 3A . FIG. 3A is a schematic flowchart of a method for drawing lane lines provided by an embodiment of the present application. The method can be applied to the system architecture described in FIG. 2A or FIG. 2B , and can be specifically applied to the above-mentioned FIG. 2A in the drawing device 002. 3A as an example to illustrate, the method includes but is not limited to the following steps:

Step S301: Obtain the information of the first intersection.

Specifically, the first intersection is the intersection where lane lines need to be planned. When the collection device 001 shown in FIG. 2A is collecting vehicles, the information of the intersection collected by the collection device 001 is the information of the intersection that needs to be marked with lane lines in the high-precision map. (Including the information of the first intersection), and then the collection device 001 sends the information of the intersection to the drawing device 002, so that the drawing device 002 can obtain the information of the first intersection. When the collecting device 001 shown in FIG. 2A is a roadside unit, the drawing device 002 may be an intelligent vehicle 003 . Please refer to FIG. 2B , the information of the intersection collected by the collection device 001 is the information of the intersection of the lane line to be planned in the automatic driving (including the information of the first intersection), and then the collection device 001 sends the information of the above intersection to the intelligent vehicle 003, so that the intelligent vehicle 003 can obtain the information of the first intersection.

The information of the first intersection includes information of the first reference point, information of the second reference point, and information of obstacles at the first intersection. The first reference point is a point on the first lane line, the second reference point is a point on the second lane line, the lane lines connected to the first intersection are the first lane line and the second lane line, and the second lane line The line connects the first lane line through the lane line of the first intersection, and the obstacle is the object that hinders the driving near the first intersection. Referring to FIG. 3B , FIG. 3B is a schematic diagram of intersection information provided by an embodiment of the present application. FIG. 3B illustrates an intersection as an example, in which:

The intersection is represented as the area where the roads meet. Optionally, it can be seen from FIG. 3B that the intersection 300 can be the stop line on the first lane 301, the stop line on the second lane 302, the stop line on the third lane 303 and The rectangular area enclosed by the stop line on the fourth lane 304 or the area around the rectangle. The first lane 301 , the second lane 302 , the third lane 303 and the fourth lane 304 are two-way lanes, which are formed by two traffic lanes in opposite directions. It can be understood that the intersection not only includes the intersection 300 shown in FIG. 3B where four roads intersect (eg, an intersection, an X-shaped intersection), but also includes, but is not limited to, an intersection where two roads intersect, and an intersection where three roads intersect (eg, an intersection, an X-shaped intersection). , T-junction, Y-junction). It should be noted that, in a roundabout section (for example, a roundabout), each group of two adjacent roads may be defined to form an intersection with the roundabout. Wherein, the intersection 300 is an intersection where a lane line needs to be planned, the lane line is used to indicate the driving route in the intersection area, and is a virtual curve connecting the first lane line and the second lane line. Generally speaking, one end of the lane line at the intersection is connected to the end point of the exit lane, and the other end is connected to the start point of the lane entering the lane.

The first lane line may represent the incoming lane line outside the intersection. It can be understood that the intersection information obtained by the drawing device 002 includes the driving direction and lane line corresponding to the lane. The driving direction mentioned here refers to the direction in which the vehicle in the lane can drive in the lane. From another perspective, the driving direction actually indicates how the vehicle can drive in the lane, such as straight, Turn left. As can be seen from FIG. 3B , the driving directions corresponding to the first lane 301 , the second lane 302 , the third lane 303 and the fourth lane 304 respectively may include one or more of the following: going straight, turning left or turning right. Thus, the first lane marking 301A may be the lane marking of a right-turn lane on the first lane 301, or the first lane marking 301A may be the lane marking of a straight-going lane on the second lane 302, or the first lane marking 301A may be the third lane marking The lane markings of the right-turn lane on lane 303 , or the first lane marking 301A may be the lane markings of the through lane on the fourth lane 304 .

The second lane line may represent the outgoing lane line outside the intersection. It can be understood that the second lane line is a lane line having a corresponding relationship with the first lane line, that is, the lane line connected to the first lane line through the planned lane line at the intersection 300 is the second lane line. As can be seen from FIG. 3B , if the first lane line 301A is the lane line of the right-turn lane on the first lane 301 , the second lane line 301B may be the lane line on the second lane, that is, the second lane line 301B In order to connect the lane line of the first lane line 301A through the right-turn lane line of the intersection 300; if the first lane line 301A is the lane line of the straight lane on the first lane 301, the second lane 301B can be the third lane 303. The lane line, that is, the second lane line 301B is a lane line connecting the first lane line 301A through the straight lane line of the intersection 300 .

The first reference point is a point on the first lane line or an extension line of the first lane line, and may specifically be a point where the first lane line is close to the intersection. For example, the first reference point may be a point at the intersection of the first lane line and the stop line, or a point where the first lane line is close to the stop line, or the intersection of the extension of the first lane line and the intersection. point. As can be seen from FIG. 3B , the first reference point 302A may be a point on the first lane line 301A of the first lane 301 , or a point on the first lane line 301A of the second lane 302 , or a third lane 303 A point on the first lane line 301A of , or a point on the first lane line 301A of the fourth lane 304 .

The second reference point is a point at the second lane line or an extension line of the second lane line, and may specifically be a point where the second lane line is close to the intersection. For example, the second reference point may be a point at the intersection of the second lane line and the stop line, or a point where the second lane line is close to the stop line, or the intersection of the extension of the second lane line and the intersection. point. Since the second lane line is a lane line having a corresponding relationship with the first lane line, the second reference point is a point having a corresponding relationship with the first reference point. As can be seen from FIG. 3B , if the planned lane line is a right-turn lane line, the first reference point 302A is a point on the lane line of the right-turn lane of the first lane 301 , and the second reference point 302B may be the second lane The point on the second lane line 301B of 302, that is, one end of the planned right-turn lane line at the intersection is connected to the end point of the first lane line 301A of the first lane 301 is the first reference point 302A, and the other end is connected to the second lane. The end point of the second lane line 301B is the second reference point 302B; if the planned lane line is a straight lane line, the first reference point 302A is a point on the lane line of the straight lane of the first lane 301, and the second reference point 302B It can be a point on the lane line of the third lane 303, that is, one end of the planned straight lane line at the intersection is connected to the end point of the first lane line 301A of the first lane 301 as the first reference point 302A, and the other end is connected to the third lane. The end point of the second lane line 301B of 303 is the second reference point 302B; if the planned lane line is a left-turn lane line, then the first reference point 302A is a point on the lane line of the left-turn lane of the first lane 301, then The second reference point 302B may be a point on the second lane line 301B of the fourth lane 304 .

Obstacles can be objects in the intersection area that may hinder travel, such as trees, curbs, traffic signs placed on the ground, and so on. It can be seen from FIG. 3B that the obstacle 305 is a tree near the curb at the intersection. The obstacle information collected by the collecting device 001 may be the vector data of the obstacle, that is, it includes one or more coordinate points that can describe the obstacle, and the shape and position of the obstacle can be inferred from the one or more coordinate points.

Step S302: Determine the target projection point.

Specifically, the target projection point is the projection point of the obstacle to the first depth and/or the second depth, wherein the first depth is the depth of the first reference point extending to the intersection, and the second depth is the second reference point extending to the intersection. The depth of the extension at the intersection.

In a possible implementation manner, before determining the target projection point, the drawing apparatus 002 may determine a planning area, and mark objects in the planning area as obstacles. It is understandable that the obtained obstacle information is vector data that can represent the shape, size and specific location of the obstacle, and the obstacle that affects the drawing of the right-turn lane line may be a certain part of the obstacle, such as the one near the intersection. In this part, objects located within the planning area (including the side boundary of the right-turn area) are regarded as obstacles, which can improve the accuracy that the planned lane lines will not overwhelm obstacles. Optionally, the drawing apparatus 002 may determine the planning area according to the first reference point, the second reference point and the intersection point, and mark objects in the planning area as obstacles. Wherein, the intersection point is the point where the first depth and the second depth meet. In this embodiment of the present application, since the first reference point, the second reference point and the intersection point are points required for planning lane lines, the planning area determined by the first reference point, the second reference point and the intersection point can quickly And accurately identify objects that obstruct the planned lane lines.

In a possible implementation manner, the drawing device 002 projects the N position points of the obstacle to the first depth to obtain N first projection points, and selects the first reference point from the N first projection points. The distance is the largest, and the first projection point whose distance to the corresponding point on the obstacle is less than or equal to the first threshold belongs to the target projection point; by projecting the N position points of the obstacle to the second depth, N second projection points can be obtained. For the projection point, the specific largest one to the first reference point is selected from the N Nth projection points, and the second projection point whose distance to the corresponding point on the obstacle is less than or equal to the second threshold belongs to the target projection point. It can be understood that the target projection point includes one or more of the following situations: the target projection point is the first projection point, the target projection point is the second projection point, and the target projection point includes the first projection point and the second projection point. In this embodiment of the present application, a target projection point that satisfies the preset requirements is selected from the N first projection points and/or the N second projection points according to a given preset condition, because the first threshold value in the preset condition is And the existence of the second threshold can improve the accuracy that the lane line drawn by the determined target projection will not overwhelm the obstacle, and also ensure that the vehicle can smoothly drive out of the intersection through the planned lane line.

The first threshold and the second threshold are empirical values that can meet the needs obtained through machine learning training according to the distance between the obstacles at the intersection and the lane line. That is, through the collected data of a large number of intersections, the distance relationship between the obstacles at the intersection and the lane line is analyzed, or the distance required for the vehicle to turn at the intersection is analyzed, and the value obtained by training. The target projection point determined by the first threshold and/or the second threshold can satisfy that the planned lane line will not press against obstacles, and can also ensure that the vehicle turns right or left through the planned lane line. Wherein, the first threshold and the second threshold may be equal or unequal.

For example, please refer to FIG. 3C , which is a schematic diagram of determining a target projection point according to an embodiment of the present application. 3C is described by taking the drawing of a right-turn lane line as an example. As can be seen from FIG. 3C , the first reference point 302A is a point on the first lane line 301A of the first lane 301 , and the second reference point 302B is a point on the second lane line 301B of the second lane 302 . The first depth 303A is the depth that the first reference point 302A extends to the intersection 300 , that is, the extension of the first lane line 301A along the intersection 300 ; the second depth 303B is the depth that the second reference point 302B extends to the intersection 300 , that is, the second lane line 301B is along the extension line of the intersection 300 . The intersection point of the first depth 303A and the second depth 303B is the intersection point 300B, and the intersection point 300B is a control point required when drawing a lane line.

The planning area can be determined according to the first reference point 302A, the second reference point 302B and the intersection point 300B. The overlapping part of the obstacle 305 and the planning area can be considered as an obstacle that will affect the drawing of the lane line. By obtaining the obstacle in the overlapping part information to determine the target projection point. It can be seen from FIG. 3C that the point 30A represents any point on the obstacle 305 in the right turn area, that is, the point 30A includes N position points of the obstacle, and N is greater than or equal to 1. From point 30A as a starting point, draw a vertical line to the first depth 303A to obtain point 30B, and draw a vertical line through point 30A to the second depth 303B to obtain point 30C. It can be understood that since the point 30A includes N position points, the point 30B includes N projection points, and the point 30C also includes N projection points. Then select the projection point with the farthest distance from the first reference point 302A from the point 30B, and the distance from the point 30B to the corresponding point on the obstacle is less than or equal to the first threshold; select the point 30C from the first reference point 302B The distance is the farthest, and the distance from the point 30C to the corresponding point on the obstacle is less than or equal to the projected point of the second threshold. It should be noted that the point corresponding to the point 30B to the obstacle and the point corresponding to the point 30C to the obstacle may be the same point or different points.

It should be noted that, if the lane line is a straight lane line or a left-turn lane line, the planning area may be determined according to the method of the above-mentioned right-turn lane line, which will not be repeated here.

Step S303: Determine the lane line according to the first reference point, the second reference point and the target projection point.

Specifically, because the first projection point and/or the second projection point satisfying the preset condition is the target projection point, the target projection point includes one or more of the following situations: Case 1, the target projection point includes the first projection point ; Case 2, the target projection point includes the second projection point; Case 3, the target projection point includes the first projection point and the second projection point.

When the target projection point is the first projection point, the drawing device 002 may determine the lane line according to the first reference point, the second reference point and the first projection point. The lane line may be composed of a first line segment and a first curve, the first line segment is determined by a first reference point and a first projection point, and the first curve is determined by the first projection point, the intersection point and the second reference point. The intersection point is the point where the first depth and the second depth meet. In this embodiment of the present application, the lane line is composed of a first line segment and a first curve. The first line segment is the longest distance that can avoid obstacles at the entrance and can guarantee a right turn, so the first line segment can pass through the first line. In the case of completely avoiding the obstacle, the segment will go out of the intersection by the first curve.

When the target projection point is the second projection point, the drawing device 002 may determine the lane line according to the first reference point, the second reference point and the second projection point. The lane line may be composed of a second line segment and a second curve, the second line segment is determined by a second reference point and a second projection point, and the second curve is determined by the second projection point, the intersection point and the first reference point. Wherein, the intersection point is the point where the first depth and the second depth meet. In the embodiment of the present application, the lane line is composed of a second line segment and a second curve, and the second line segment is the longest distance that can avoid obstacles at the exit from the intersection and can guarantee the completion of a right turn. When reaching the obstacle, pass the second line segment to avoid pressing the obstacle.

When the target projection point includes the first projection point and the second projection point, the drawing device 002 may determine the lane line according to the first reference point, the second reference point, the first projection point and the second projection point. The lane line may be composed of a third line segment, a fourth line segment and a third curve, the third line segment is determined by the first reference point and the first projection point, and the third curve is determined by the first projection point, the intersection point and the second projection point ; The fourth line segment is determined by the second projection point and the second reference point. Wherein, the intersection point is the point where the first depth and the second depth meet. In the embodiment of the present application, the lane line is composed of a third line segment, a third curve and a fourth line segment, and the third line segment is the longest distance to avoid obstacles at the entrance to the intersection, which can ensure that the obstacles are completely avoided. Go down and turn right. The fourth line segment is the longest distance to avoid obstacles at the exit and can guarantee to complete a right turn. It can ensure that the fourth line segment is used to avoid hitting obstacles when turning right. thing.

After the first reference point, the second reference point, the intersection point and the target projection point are determined, the lane line can be planned according to the Bezier curve or the spline curve. It should be noted that, the embodiments of the present application do not impose any limitations on tools for planning lane lines.

With the method provided by the embodiment of the present application, the obstacles at the intersection are considered when planning the lane line at the intersection, so that the target projection point can be determined, and then the target projection point can be determined according to the first reference point, the second reference point and the target projection. Points define lane lines. Because of the existence of the target projection point, it can be ensured that the generated lane line will not be pressed against obstacles, and no manual adjustment is required, which can improve the efficiency and accuracy of planning lane lines.

Referring to FIG. 4 , FIG. 4 is a schematic diagram of another scene for drawing lane lines provided by an embodiment of the present application. FIG. 4 is an example of drawing a right-turn lane. It can be seen from FIG. 4 that the information of the first intersection 004 acquired by the drawing device 002 includes the information of the first reference point 401A, the information of the second reference point 401B and obstacles Object 400 information. Wherein, the information of the obstacles in the right turn area determined by the first reference point 401A, the second reference point 401B and the intersection point 401C includes the point 400A, the point 400B and the point 400C. The intersection point 401C is the point where the first depth 402A and the second depth 402B meet, the first depth 402A is the depth where the first reference point 401A extends to the first intersection 004, and the second depth 402B is the second reference point 401B to the first intersection Depth of extension at 004.

Please refer to (1) of FIG. 4 , the drawing device 002 draws a vertical line from the point 400A to the first depth 402A to obtain the projection point of the point 400A at the first depth 402A as the point 4001A; similarly, the projection point of the point 400B at the first depth 402A can be obtained. The projected point is point 4001B, and the projected point of point 400C at the first depth 402A is 4001C. The projected point obtained by the drawing device 002 passing the point 400A, the point 400B and the point 400C to the second depth 402B by drawing a vertical line is the point 4002A. Next, the drawing device 002 selects the maximum distance from the point 4001A, the point 4001B and the point 4001C to the first reference point 401A, and the point whose distance to the corresponding point on the obstacle 400 is less than or equal to the first threshold is the target projection point . Because, the distance determined by point 400A and point 4001A, the distance determined by point 400B and point 4001B, and the distance determined by point 400C and point 4001C are all less than or equal to the first threshold, but point 4001C is the farthest distance from the first reference point 401A , so point 4001C is selected as the target projection point at the first depth. However, the distance determined by point 4002A and point 400A, the distance determined by point 4002A and point 400B, and the distance determined by point 4002A and point 400C are all greater than the second threshold, so there is no target projection that meets the preset conditions at the second depth. point.

Please refer to (2) of FIG. 4 , after determining the target projection point of point 4001C, use Bezier curve or spline curve to determine the first line segment 403 determined by the first reference point 401A and point 4001C, and the first line segment 403 determined by point 4001C, The first curve 404 defined by the intersection point 400C and the second reference point 401B constitutes a right-turn lane line. It can be seen from (2) of FIG. 4 that the right-turn lane line drawn by the above method will not press against the obstacle 400 .

It can be understood that the lane in which the vehicle travels is composed of two lane lines. When one of the lane lines is obtained, the other lane line can be determined through the corresponding relationship. In practical applications, the complete lane can be quickly determined and improved. efficiency.

Referring to FIG. 5 , FIG. 5 is a schematic diagram of another scene for drawing lane lines according to an embodiment of the present application. FIG. 5 is an example of drawing a right-turn lane. It can be seen from FIG. 5 that the information of the first intersection 005 acquired by the drawing device 002 includes the information of the first reference point 501A, the information of the second reference point 501B and obstacles Item 500 information. The information of obstacles in the right turn area determined by the first reference point 501A, the second reference point 501B and the intersection point 501C includes points 500A, 500B and 500C. The intersection point 501C is the point where the first depth 502A and the second depth 502B meet, the first depth 502A is the depth where the first reference point 501A extends to the first intersection 005, and the second depth 502B is the second reference point 501B to the first intersection Depth of extension at 005.

Please refer to (1) of FIG. 5 , the drawing device 002 draws a vertical line from the point 500A to the second depth 502B to obtain the projection point of the point 500A at the second depth 502B as the point 5001A; similarly, the projection point of the point 500B at the second depth 502B can be obtained. The projected point is point 5001B, and the projected point of point 500C at the second depth 502B is 5001C. The drawing device 002 draws a vertical line from the point 500A and the point 500B to the first depth 502A to obtain a projected point as point 5002A, and draws a vertical line from the point 500C to the first depth 502A to obtain a projected point as 5002B. Next, the drawing device 002 selects the maximum distance from the point 5001A, the point 5001B and the point 5001C to the second reference point 501B, and the point whose distance to the corresponding point on the obstacle 500 is less than or equal to the second threshold is the target projection point . The drawing device 002 selects the point with the largest distance from the point 5002A and the point 5002B to the first reference point 501A, and the point whose distance to the corresponding point on the obstacle 500 is less than or equal to the first threshold is the target projection point. Because, the distance determined by point 500A and point 5001A, the distance determined by point 500B and point 5001B, and the distance determined by point 500C and point 5001C are all less than or equal to the first threshold, but point 5001C is the farthest distance from the second reference point 501B , so point 5001C is selected as the target projection point on the second depth 502B. However, the distance determined by point 5002A and point 500A, the distance determined by point 5002A and point 500B, and the distance determined by point 5002B and point 500C are all greater than the first threshold, so there is no target projection that meets the preset conditions at the first depth. point.

Please refer to (2) of FIG. 5 , after the target projection point of point 5001C is determined, the second curve 503 determined by the first reference point 501A, the intersection point 501C and the point 5001C through a Bezier curve or a spline curve, and a second curve 503 determined by the point The second line segment 504 determined by 5001C and the second reference point 501B constitutes a right-turn lane line. It can be seen from (2) of FIG. 5 that the right-turn lane line drawn by the above method will not press against the obstacle 500 .

Referring to FIG. 6 , FIG. 6 is a schematic diagram of another scene for drawing lane lines provided by an embodiment of the present application. FIG. 6 illustrates by drawing a right-turn lane as an example. It can be seen from FIG. 6 that the information of the first intersection 006 acquired by the drawing device 002 includes the information of the first reference point 601A, the information of the second reference point 601B and obstacles Object 600 information. The information of obstacles in the right turn area determined by the first reference point 601A, the second reference point 601B and the intersection point 601C includes points 600A, 600B, 600C, 600D and 600E. The intersection point 601C is the point where the first depth 602A and the second depth 602B meet, the first depth 602A is the depth where the first reference point 601A extends to the first intersection 006, and the second depth 602B is the second reference point 601B to the first intersection Depth of extension at 006.

Please refer to (1) of FIG. 6 , the drawing device 002 draws a vertical line from the point 600A to the first depth 602A to obtain the projection point of the point 600A at the first depth 602A as the point 6001A; similarly, the projection point of the point 600B at the first depth 602A can be obtained. The projected point is point 6001B, and the projected point of point 600C at the first depth 602A is 6001C. In the same way, the corresponding projection points of the point 600A, the point 600B, and the point 600C on the second depth 602B can be obtained. Similarly, the drawing device 002 draws a vertical line to the second depth 602B through the points 600D and 600E, respectively, to obtain the corresponding projection points as the point 6001D and the point 6001E; similarly, the projections of the points 600D and 600E at the first depth 602A can be obtained. point. Next, the drawing device 002 selects the largest distance to the first reference point 601A from the points 6001A, 6001B, 6001C and other projection points to the first depth 602A, and the distance to the corresponding point on the obstacle 600 is less than The point equal to the first threshold is the target projection point. The drawing device 002 selects the point with the largest distance to the second reference point 601B from the point 6001B, the point 6001E and other projection points to the second depth 602B, and the distance to the corresponding point on the obstacle 600 is less than or equal to the second threshold value Projection point for the target. It can be seen from (1) of FIG. 6 that the point 6001C and the point 6001D are target projection points that can satisfy the preset conditions.

Please refer to (2) of FIG. 6 , after the point 6001C and the point 6001D are determined as the target projection points, the third line segment 603 determined by the first reference point 601A and the point 6001C through the Bezier curve or the spline curve, to The third curve 604 determined by the point 6001C, the intersection point 601C and the point 6001D, and the fourth line segment 605 determined by the point 6001D and the second reference point 601B constitute a right-turn lane line. It can be seen from (2) of FIG. 6 that the right-turn lane line drawn by the above method will not press against the obstacle 600 .

It should be noted that the planning of the straight lane line or the left turn lane line can be derived and planned according to the method of planning the right turn lane line in the embodiment shown in FIG. 4 , FIG. 5 or FIG. Or an example of left-turn lane markings.

The methods of the embodiments of the present application are described in detail above, and the apparatuses of the embodiments of the present application are provided below.

Please refer to FIG. 7. FIG. 7 is a schematic structural diagram of a lane planning apparatus provided by an embodiment of the present application. The lane planning apparatus 700 may be a node, or may be a device in a node, such as a chip or an integrated circuit, etc. The lane line planning apparatus 700 may include an acquisition unit 701, a determination unit 702 and a planning unit 703, wherein the detailed description of each unit is as follows.

The obtaining unit 701 is configured to obtain the information of the first intersection, the information of the first intersection includes the information of the first reference point, the information of the second reference point and the information of the obstacles of the first intersection; wherein, the first intersection needs to be planned For the intersection of the lane line, the first reference point is the point on the first lane line, the second reference point is the point on the second lane line, and the lane lines connected to the first intersection are the first lane line and the second lane line, The second lane line is connected to the first lane line through the lane line of the first intersection, and the obstacle is the object in the first intersection that obstructs the planned lane line;

A determination unit 702, configured to determine a target projection point, wherein the target projection point is the projection point of the obstacle to the first depth and/or the second depth, and the first depth is the depth extending from the first lane line to the first intersection , the second depth is the depth of the second lane line extending to the first intersection;

The planning unit 703 is configured to determine the lane line according to the first reference point, the second reference point and the target projection point.

It can be seen that, because the obstacles at the intersection are considered when planning the lane line at the intersection, the target projection point can be determined, and then the lane line can be determined according to the first reference point, the second reference point and the target projection point. . Because of the existence of the target projection point, it can ensure that the generated lane line will not be pressed against obstacles, and no manual adjustment is required, which can improve the efficiency and accuracy of planning lane lines.

In a possible implementation manner, the determining unit 702 is further configured to:

Determine the planning area and mark objects in the planning area as obstacles.

In the embodiment of the present application, only the part of the object close to the intersection may hinder the drawing of the lane line, so the object that may hinder the planning of the lane line may be marked as an obstacle through the planning area.

In a possible implementation manner, the determining unit 702 is specifically configured to:

The planning area is determined according to the first reference point, the second reference point and the intersection point, where the intersection point is a point where the first depth and the second depth meet.

In this embodiment of the present application, since the first reference point, the second reference point and the intersection point are points needed to plan lane lines, the planning area determined by the first reference point, the second reference point and the intersection point can be more Accurately find objects that obstruct the planned lane lines.

Project the N position points of the obstacle to the first depth to obtain N first projection points, where N is greater than or equal to 1;

Project the N position points of the obstacle to the second depth to obtain N second projection points;

The target projection point is selected from the N first projection points and the N second projection points, where,

Among the N first projection points, the distance to the first reference point is the largest, and the first projection point whose distance to the corresponding point on the obstacle is less than or equal to the first threshold belongs to the target projection point;

Among the N second projection points, the distance to the second reference point is the largest, and the second projection point whose distance to the corresponding point on the obstacle is less than or equal to the second threshold belongs to the target projection point.

In this embodiment of the present application, a target projection point that satisfies the preset requirements is selected from the N first projection points and/or the N second projection points according to a given preset condition, because the first threshold value in the preset condition is And the existence of the second threshold can improve the possibility that the lane line drawn by the determined target projection will not overwhelm the obstacle, and also ensure that the vehicle can smoothly exit the intersection through the planned lane line.

In a possible implementation manner, the target projection point includes the first projection point, and the planning unit 703 is specifically configured to:

determining the first line segment according to the first reference point and the first projection point;

Determine the first curve according to the first projection point, the second reference point and the intersection point, where the intersection point is a point where the first depth and the second depth meet;

The right-turn lane line is determined by the first line segment and the first curve.

In a possible implementation manner, the target projection point includes the second projection point, and the planning unit 703 is specifically configured to:

Determine the second curve according to the first reference point, the second projection point and the intersection point, where the intersection point is the point where the first depth and the second depth meet;

determining a second straight line according to the second projection point and the second reference point;

The right-turn lane line is determined by the second curve and the second straight line.

In a possible implementation manner, the target projection point includes a first projection point and a second projection point, and the planning unit 703 is specifically configured to:

determining a third line segment according to the first reference point and the first projection point;

Determine the third curve according to the first projection point, the second projection point and the intersection point, where the intersection point is the point where the first depth and the second depth meet;

determining a fourth line segment according to the second projection point and the first reference point;

The right-turn lane line is determined by the third line segment, the third curve, and the fourth line segment.

In a possible implementation manner, the first threshold and the second threshold are both reference values obtained by training according to sample data, and the sample data is historical driving data of the driving trajectory to avoid obstacles.

It should be noted that, the implementation of each unit may also correspond to the corresponding description of an embodiment shown in FIG. 3A .

Referring to FIG. 8 , FIG. 8 is a schematic structural diagram of a lane planning device provided by an embodiment of the present application. The lane planning device 800 may be a node or a device in a node, such as a chip or an integrated circuit. The apparatus 80 may include at least one memory 801 and at least one processor 802 . Optionally, a bus 803 may also be included. Further optionally, a communication interface 804 may also be included, wherein the memory 801 , the processor 802 and the communication interface 804 are connected through a bus 803 .

Among them, the memory 801 is used to provide a storage space, and data such as an operating system and a computer program can be stored in the storage space. The memory 801 may be random access memory (RAM), read-only memory (ROM), erasable programmable read only memory (EPROM), or portable read-only memory One or more combinations of memory (compact disc read-only memory, CD-ROM), etc.

The processor 802 is a module that performs arithmetic operations and/or logical operations, and can specifically be a central processing unit (central processing unit, CPU), a graphics processing unit (graphics processing unit, GPU), a microprocessor (microprocessor unit, MPU), One or more of processing modules such as Application Specific Integrated Circuit (ASIC), Field Programmable Gate Array (FPGA), and Complex Programmable Logic Device (CPLD) The combination.

The communication interface 804 is used to receive and/or send data to the outside, and may be a wired link interface such as an Ethernet cable, or a wireless link (Wi-Fi, Bluetooth, general wireless transmission, etc.) interface. Optionally, the communication interface 804 may further include a transmitter (eg, a radio frequency transmitter, an antenna, etc.), or a receiver, etc., coupled with the interface.

The processor 802 in the lane line planning device 800 is configured to read the computer program stored in the memory 801, to perform the following operations:

Obtain the information of the first intersection, and the information of the first intersection includes the information of the first reference point, the information of the second reference point and the information of the obstacles of the first intersection; wherein, the first intersection is the intersection where lane lines need to be planned, and the first intersection is the intersection where lane lines need to be planned. The first reference point is the point on the first lane line, the second reference point is the point on the second lane line, the lane lines connected to the first intersection are the first lane line and the second lane line, and the second lane line passes through the The lane line of an intersection is connected to the first lane line, and the obstacle is the object in the first intersection that obstructs the planned lane line; determine the target projection point, wherein the target projection point is the obstacle to the first depth and/or the second depth. Projection point, the first depth is the depth of the extension of the first lane line to the first intersection, and the second depth is the depth of the extension of the second lane line to the first intersection; according to the first reference point, the second reference point and the target projection Click to define the lane line.

It can be seen that because the obstacles at the intersection are considered when planning the lane line at the intersection, the target projection point can be determined, and then the lane line can be determined according to the first reference point, the second reference point and the target projection point. . Because of the existence of the target projection point, it can be ensured that the generated lane line will not be pressed against obstacles, and no manual adjustment is required, which can improve the efficiency and accuracy of planning lane lines.

In a possible implementation, the processor 802 is further configured to:

Determine the planning area and mark objects in the planning area as obstacles.

In a possible implementation manner, the processor 802 is specifically configured to:

In a possible implementation manner, the target projection point includes the first projection point, and the processor 802 is specifically configured to:

In a possible implementation manner, the target projection point includes the second projection point, and the processor 802 is specifically configured to:

In a possible implementation manner, the target projection point includes a first projection point and a second projection point, and the processor 802 is specifically configured to:

It should be noted that, the implementation of each operation may also correspond to the corresponding description with reference to the method embodiment shown in FIG. 3A .

An embodiment of the present application further provides a chip system, the chip system includes at least one processor, a memory and an interface circuit, the memory, the transceiver and the at least one processor are interconnected through a line, and the at least one memory A computer program is stored in the computer; when the computer program is executed by the processor, the method flow shown in FIG. 3A is realized.

Embodiments of the present application further provide a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed on one or more processors, the method flow shown in FIG. 3A is implemented.

The embodiment of the present application further provides a computer program product, when the computer program product is executed on one or more processors, the method flow shown in FIG. 3A is implemented.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented, and the process can be completed by a computer program or computer program-related hardware, and the computer program can be stored in a computer-readable storage medium. During execution, the processes of the foregoing method embodiments may be included. The aforementioned storage medium includes various media that can store computer program codes, such as ROM or random access memory RAM, magnetic disk or optical disk.

Claims

A lane line planning method, comprising:

Obtain the information of the first intersection, where the information of the first intersection includes the information of the first reference point, the information of the second reference point and the information of the obstacles of the first intersection; wherein, the first intersection needs to be planned The intersection of the lane line, the first reference point is the point on the first lane line, the second reference point is the point on the second lane line, and the lane line connected to the first intersection is the first lane line a lane line and the second lane line, the second lane line is connected to the first lane line through the lane line of the first intersection, and the obstacle is a lane line that obstructs the planning in the first intersection the object;

Determining a target projection point, wherein the target projection point is a projection point of the obstacle to a first depth and/or a second depth, and the first depth is the direction from the first lane line to the first intersection The depth extending at the intersection, and the second depth is the depth extending from the second lane line to the first intersection;

The lane line is determined according to the first reference point, the second reference point and the target projection point.
The method according to claim 1, wherein before the determining the target projection point and after the acquiring the information of the first intersection, the method further comprises:

A planning area is determined, and objects in the planning area are marked as the obstacles.
The method according to claim 2, wherein the determining a planning area comprises:

A planning area is determined according to the first reference point, the second reference point, and an intersection point, where the intersection point is a point where the first depth and the second depth meet.
The method according to any one of claims 1-3, wherein the determining the target projection point comprises:

Projecting the N position points of the obstacle to the first depth to obtain N first projection points, where N is greater than or equal to 1;

Projecting the N position points of the obstacle to the second depth to obtain N second projection points;

The target projection point is selected from the N first projection points and the N second projection points, wherein,

Among the N first projection points, the distance to the first reference point is the largest, and the first projection point whose distance to the corresponding point on the obstacle is less than or equal to the first threshold belongs to the target projection point;

Among the N second projection points, the distance to the second reference point is the largest, and the second projection point whose distance to the corresponding point on the obstacle is less than or equal to the second threshold belongs to the target projection point.
The method according to claim 4, wherein the target projection point comprises the first projection point, and the lane is determined according to the first reference point, the second reference point and the target projection point line, including:

determining a first line segment according to the first reference point and the first projection point;

determining a first curve according to the first projection point, the second reference point, and an intersection point, where the intersection point is a point where the first depth meets the second depth;

The right-turn lane line is determined from the first line segment and the first curve.
The method according to claim 4, wherein the target projection point comprises the second projection point, and the lane is determined according to the first reference point, the second reference point and the target projection point line, including:

determining a second curve according to the first reference point, the second projection point, and an intersection point, where the intersection point is a point where the first depth meets the second depth;

determining a second straight line according to the second projection point and the second reference point;

The right-turn lane line is determined from the second curve and the second straight line.
The method according to claim 4, wherein the target projection point comprises the first projection point and the second projection point, and the target projection point is based on the first reference point, the second reference point and the The target projection point determines the lane line, including:

determining a third line segment according to the first reference point and the first projection point;

determining a third curve according to the first projection point, the second projection point and an intersection point, where the intersection point is a point where the first depth and the second depth intersect;

determining a fourth line segment according to the second projection point and the first reference point;

The right-turn lane line is determined from the third line segment, the third curve, and the fourth line segment.
The method according to any one of claims 4-7, wherein the first threshold value and the second threshold value are both reference values obtained by training according to sample data, and the sample data is a driving track to avoid The historical driving data of the obstacle is described.
A lane line planning device, characterized in that it includes:

an obtaining unit, configured to obtain information of a first intersection, where the information of the first intersection includes information of a first reference point, information of a second reference point, and information of obstacles at the first intersection; wherein the first intersection An intersection is an intersection where lane lines need to be planned, the first reference point is a point on the first lane line, the second reference point is a point on the second lane line, and the lane line connected to the first intersection are the first lane line and the second lane line, the second lane line is connected to the first lane line through the lane line of the first intersection, and the obstacle is the first road Objects in the mouth that obstruct the planned lane lines;

A determination unit for determining a target projection point, wherein the target projection point is a projection point of the obstacle to a first depth and/or a second depth, and the first depth is the direction of the first lane line the depth extending from the first intersection, and the second depth is the depth extending from the second lane line to the first intersection;

A planning unit, configured to determine the lane line according to the first reference point, the second reference point and the target projection point.
The device according to claim 9, wherein the determining unit is further configured to:

A planning area is determined, and objects in the planning area are marked as the obstacles.
The device according to claim 10, wherein the determining unit is specifically configured to:

A planning area is determined according to the first reference point, the second reference point, and an intersection point, where the intersection point is a point where the first depth and the second depth meet.
The device according to any one of claims 9-11, wherein the determining unit is specifically configured to:

Projecting the N position points of the obstacle to the first depth to obtain N first projection points, where N is greater than or equal to 1;

Projecting the N position points of the obstacle to the second depth to obtain N second projection points;

The target projection point is selected from the N first projection points and the N second projection points, wherein,

The distance to the first reference point in the N first projection points is the largest, and the first projection point whose distance to the corresponding point on the obstacle is less than or equal to the first threshold value belongs to the target projection point;

Among the N second projection points, the distance to the second reference point is the largest, and the second projection point whose distance to the corresponding point on the obstacle is less than or equal to the second threshold belongs to the target projection point.
The device according to claim 12, wherein the target projection point comprises the first projection point, and the planning unit is specifically configured to:

determining a first line segment according to the first reference point and the first projection point;

determining a first curve according to the first projection point, the second reference point, and an intersection point, where the intersection point is a point where the first depth meets the second depth;

The right-turn lane line is determined from the first line segment and the first curve.
The device according to claim 12, wherein the target projection point comprises the second projection point, and the planning unit is specifically configured to:

determining a second curve according to the first reference point, the second projection point, and an intersection point, where the intersection point is a point where the first depth meets the second depth;

determining a second straight line according to the second projection point and the second reference point;

The right-turn lane line is determined from the second curve and the second straight line.
The device according to claim 12, wherein the target projection point includes the first projection point and the second projection point, the lane line is a right-turn lane line, and the planning unit is specifically configured to :

determining a third line segment according to the first reference point and the first projection point;

determining a third curve according to the first projection point, the second projection point and an intersection point, where the intersection point is a point where the first depth and the second depth intersect;

determining a fourth line segment according to the second projection point and the first reference point;

The right-turn lane line is determined from the third line segment, the third curve, and the fourth line segment.
A high-precision map, characterized in that the high-precision map includes the first reference point, the second reference point and the target projection point in the method according to any one of claims 1-8 The identified lane lines.
An intelligent vehicle, characterized in that the intelligent vehicle includes at least one processor and at least one memory, and the at least one processor is configured to call a computer program stored in the at least one memory, so that the intelligent vehicle executes the following steps: The method of any one of claims 1-8.
A lane line planning device, characterized in that the lane line planning device includes at least one processor and at least one memory, and the at least one processor is configured to call a computer program stored in the at least one memory, so that the The apparatus performs the method of any of claims 1-8.
A computer-readable storage medium, characterized in that, a computer program is stored in the computer-readable storage medium, and when the computer program is executed on one or more processors, it executes any one of claims 1-8. one of the methods described.