Lane line planning method and related device

Abstract

The embodiment of the present application provides a lane line planning method and related devices, the method comprising: obtaining information of a first intersection, the information of the first intersection including information of a first reference point, information of a second reference point and information of obstacles at the first intersection; determining a target projection point, the target projection point being a projection point of an obstacle to a first depth and / or a second depth, the first depth being the depth of the first lane line extending to the first intersection, and the second depth being the depth of the second lane line extending to the first intersection; determining a lane line according to the first reference point, the second reference point and the target projection point. By adopting the embodiment of the present application, a lane line that avoids obstacles can be automatically planned, thereby improving the efficiency and accuracy of planning.

Description

Technical Field

[0001] The present application relates to the field of unmanned driving technology, and in particular to a lane line planning method and related devices. Background Art

[0002] With the maturity of artificial intelligence technology, autonomous driving technology has also developed rapidly. High-precision maps play a vital role in map search, automatic navigation, and autonomous driving. High-precision maps have high requirements for information richness and accuracy, and can provide more road details. It can provide geographic coordinate information for each lane on a road, and the accuracy can reach the centimeter level. High-precision maps can also record rich road sign information such as crosswalks, overpasses, traffic lights, etc. At intersections, high-precision maps will also generate many lane-level virtual lane lines based on actual road scenes, providing accurate and smooth navigation information for cars driving at intersections. Therefore, during the autonomous driving process, the autonomous driving vehicle can drive on a lane-level path that is pre-planned on the high-precision map.

[0003] The process of making high-precision maps is usually carried out by technicians driving a collection vehicle to obtain environmental information of the area passed by, and then integrating the various information obtained to generate an electronic map. Then the cartographers will use various map annotation software to automatically or manually annotate the obtained electronic map to mark various traffic information, such as lane lines, road signs, road markings and other traffic information.

[0004] There are currently two methods for marking lane lines at intersections in high-precision maps: manual marking and automatic marking. Manual marking is done by cartographers based on the acquired point cloud map. However, manually marked lane lines are not only time-consuming and laborious, but also difficult to ensure the beauty of the lane lines. Automatic marking is automated based on the acquired intersection information. However, this method often does not consider the presence of obstacles at the intersection, resulting in low marking accuracy.

[0005] Neither manual nor automatic labeling can guarantee both labeling efficiency and accuracy of high-precision maps. Summary of the invention

[0006] The embodiments of the present application provide a lane line planning method and related devices, which can automatically plan lane lines that avoid obstacles, thereby improving planning efficiency and accuracy.

[0007] In a first aspect, an embodiment of the present application provides a method for lane line planning, which may include: obtaining information of a first intersection, the information of the first intersection including information of a first reference point, information of a second reference point and information of an obstacle at the first intersection; wherein the first 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, the lane lines connected to the first intersection 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 an object in the first intersection that hinders the planning of the lane line; 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, the first depth is the depth of the first lane line extending to the first intersection, and the second depth is the depth of the second lane line extending to the first intersection; determining the lane line according to the first reference point, the second reference point and the target projection point.

[0008] According to the method provided in the first aspect, when planning the lane line at the intersection, the obstacles at the intersection are taken into consideration, so that 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 press the obstacle, and no manual adjustment is required, which can improve the efficiency and accuracy of planning the lane line.

[0009] In a possible implementation manner, the method may further include: determining a planning area, and marking objects in the planning area as obstacles.

[0010] In an embodiment of the present application, only the part of the object close to the intersection may hinder the planned lane line, so the objects that may hinder the planned lane line can be marked as obstacles through the planning area, thereby improving the accuracy of the planned lane line not pressing the obstacle.

[0011] In a possible implementation, the method may further include: determining a 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.

[0012] In an embodiment of the present application, because the first reference point, the second reference point and the intersection are the points needed to plan the lane lines, the planning area determined by the first reference point, the second reference point and the intersection can quickly and accurately determine objects that hinder the planned lane lines.

[0013] In a possible implementation, the method may further include: projecting N position points of the obstacle to a 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 a second depth to obtain N second projection points; selecting a target projection point from the N first projection points and the N second projection points, wherein the first projection point whose distance to the first reference point is the largest among the N first projection points, and whose distance to the corresponding point on the obstacle is less than or equal to the first threshold belongs to the target projection point; and the second projection point whose distance to the second reference point is the largest among the N second projection points, and whose distance to the corresponding point on the obstacle is less than or equal to the second threshold belongs to the target projection point.

[0014] In an embodiment of the present application, through given preset conditions, a target projection point that meets the preset requirements is selected from N first projection points and / or N second projection points. Because of the existence of the first threshold and the second threshold in the preset conditions, the accuracy of the lane line drawn by the determined target projection will not press onto obstacles can be improved, and it is also ensured that the vehicle can smoothly exit the intersection through the planned lane line.

[0015] In a possible implementation, the target projection point includes a first projection point, and the method may further include: determining a first line segment based on the first reference point and the first projection point; determining a first curve based on the first projection point, the second reference point and the intersection point, the intersection point being the point where the first depth and the second depth meet; determining a right-turn lane line by the first line segment and the first curve.

[0016] In an 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 when entering the intersection and ensure the completion of the right turn. Therefore, the first line segment can be used to completely avoid obstacles and the first curve can be used to exit the intersection.

[0017] In one possible implementation, the target projection point includes a second projection point, and the method may further include: determining a second curve based on the first reference point, the second projection point and the intersection point, the intersection point being the point where the first depth and the second depth intersect; determining a second straight line based on the second projection point and the second reference point; and determining a right-turn lane line by the second curve and the second straight line.

[0018] In an embodiment of the present application, the lane line is composed of a second line segment and a second curve. The second line segment is the longest distance to avoid obstacles when leaving the intersection and to ensure completion of the right turn. The second line segment can be used to avoid hitting the obstacle when the vehicle is about to hit the obstacle during the right turn.

[0019] In a possible implementation, 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 based on the first reference point and the first projection point; determining a third curve based on the first projection point, the second projection point and the intersection point, the intersection point being the point where the first depth and the second depth meet; determining a fourth line segment based on the second projection point and the second reference point; and determining the right-turn lane line by the third line segment, the third curve and the fourth line segment.

[0020] 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. The third line segment is the longest distance to avoid obstacles when entering the intersection, which can ensure that the right turn can be made while completely avoiding obstacles. The fourth line segment is the longest distance to avoid obstacles when leaving the intersection and ensure that the right turn is completed. It can be ensured that the fourth line segment can be used to avoid hitting the obstacle when turning right and is about to hit the obstacle.

[0021] In a possible implementation, the method may further include: the first threshold and the second threshold are both reference values ​​obtained through training based on sample data, and the sample data is historical driving data of a driving trajectory avoiding obstacles.

[0022] 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 a higher credibility.

[0023] In a second aspect, an embodiment of the present application provides a lane line planning device, which may include: an acquisition unit, used to acquire information of a first intersection, the information of the first intersection includes information of a first reference point, information of a second reference point and information of an obstacle at the first intersection; wherein the first 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, the lane lines connected to the first intersection are the first lane line and the second lane line, the second lane line connects the first lane line through the lane line of the first intersection, and the obstacle is an object in the first intersection that hinders the planning of the lane line; a determination unit, used to determine 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, the first depth is the depth of the first lane line extending to the first intersection, and the second depth is the depth of the second lane line extending to the first intersection; a planning unit, used to determine the lane line based on the first reference point, the second reference point and the target projection point.

[0024] In a possible implementation manner of the second aspect, the determination unit is further configured to: determine a planning area, and mark objects in the planning area as obstacles.

[0025] In a possible implementation of the second aspect, the determining unit is specifically configured to: determine the planned 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.

[0026] In a possible implementation of the second aspect, the determination unit is specifically used to: project N position points of the obstacle to a 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 a second depth to obtain N second projection points; select a target projection point from the N first projection points and the N second projection points, wherein the first projection point whose distance to the first reference point is the largest among the N first projection points, and 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 second projection point whose distance to the second reference point is the largest among the N second projection points, and whose distance to the corresponding point on the obstacle is less than or equal to the second threshold belongs to the target projection point.

[0027] In a possible implementation of the second aspect, the target projection point is a first projection point, the lane line is a right-turn lane line, and the planning unit is specifically used to: determine a first line segment based on the first reference point and the first projection point; determine a first curve based on the first projection point, the second reference point and the intersection point, the intersection point being the point where the first depth and the second depth meet; determine the right-turn lane line by the first line segment and the first curve.

[0028] 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 used to: determine the second curve based on the first reference point, the second projection point and the intersection point, the intersection point being the point where the first depth and the second depth intersect; determine the second straight line based on the second projection point and the second reference point; and determine the right-turn lane line by the second curve and the second straight line.

[0029] 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 used to: determine a third line segment based on the first reference point and the first projection point; determine a third curve based on the first projection point, the second projection point and the intersection point, the intersection point being the point where the first depth and the second depth meet; determine a fourth line segment based on the second projection point and the second reference point; and determine the right-turn lane line by the third line segment, the third curve and the fourth line segment.

[0030] In a third aspect, an embodiment of the present application provides a high-precision map, which includes lane lines determined based on the first reference point, the second reference point and the target projection point in the method described in the first aspect or any possible implementation scheme of the first aspect.

[0031] In a fourth aspect, an embodiment of the present application provides an intelligent vehicle, which includes at least one processor and at least one memory, and the at least one processor is used to call a computer program stored in the at least one memory so that the intelligent vehicle executes the method described in the first aspect or any possible implementation method of the first aspect.

[0032] In the fifth aspect, an embodiment of the present application provides a lane line planning device, which includes at least one processor and at least one memory, and the at least one processor is used to call a computer program stored in the at least one memory so that the device executes the method described in the first aspect or any possible implementation method of the first aspect.

[0033] In a sixth aspect, an embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer program runs on one or more processors, the method described in the first aspect or any possible implementation of the first aspect is executed.

[0034] In a seventh aspect, an embodiment of the present application provides a computer program product, which, when running on one or more processors, executes the method described in the first aspect or any possible implementation of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The following is an introduction to the drawings used in the embodiments of the present application.

[0036] Figure 1 It is a scene schematic diagram of drawing lane lines provided by the prior art;

[0037] Figure 2A It is a structural schematic diagram of a lane line planning system provided in an embodiment of the present application;

[0038] Figure 2B It is a schematic diagram of the architecture of another lane planning system provided in an embodiment of the present application;

[0039] Figure 2C It is a functional block diagram of a smart vehicle 003 provided in an embodiment of the present application;

[0040] Figure 3A This is a schematic diagram of a method for drawing lane lines provided in an embodiment of the present application;

[0041] Figure 3B is a schematic diagram of intersection information provided by an embodiment of the present application;

[0042] Figure 3C is a schematic diagram of determining a target projection point provided by an embodiment of the present application;

[0043] Figure 4 This is another schematic diagram of a scene for drawing lane lines provided in an embodiment of the present application;

[0044] Figure 5 This is another schematic diagram of a scene for drawing lane lines provided in an embodiment of the present application;

[0045] Figure 6 This is another schematic diagram of a scene for drawing lane lines provided in an embodiment of the present application;

[0046] Figure 7 It is a structural schematic diagram of a lane line planning device provided in an embodiment of the present application;

[0047] Figure 8 It is a structural schematic diagram of a lane line planning device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] The embodiments of the present application are described below in conjunction with the drawings in the embodiments of the present application.

[0049] First, the relevant technologies involved in the embodiments of the present application are explained so that those skilled in the art can understand.

[0050] 1. High-precision maps

[0051] High-precision maps, also known as high-resolution maps (HD Maps), are maps specifically designed for autonomous driving. Unlike traditional navigation maps, high-precision maps can provide not only road-level navigation information, but also lane-level navigation information. Both the richness and accuracy of information are far superior to traditional navigation maps.

[0052] 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.

[0053] 2. Vector Data

[0054] Vector data is data that uses x and y coordinates to represent the position and shape of map graphics or geographic entities in rectangular coordinates. Generally, the spatial position of geographic entities is expressed as accurately as possible by recording coordinates. In addition, vector data can also be internal data stored in a vector structure in a computer, which is a direct product of a tracking digitizer. In a vector data structure, point data can be directly described by coordinate values; line data can be described by a sequence of coordinate chains with uniform or uneven intervals; and surface data (or polygonal data) can be described by boundary lines.

[0055] At present, the method for lane line planning at an intersection may include the following steps:

[0056] S1. Determine information of a first reference point, where the first reference point is a point on a first lane.

[0057] See also Figure 1 , Figure 1 It is a scene diagram of drawing lane lines provided by the prior art. Figure 1 Take drawing the right turn lane line as an example. Figure 1 As can be seen from (1), 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 can specifically be a point on the first lane line 104A (or an extension of the first lane line 104A) in an area close to the intersection 106; the intersection 106 is an intersection where lane lines need to be marked, and the lanes connected to the intersection 106 are the first lane 102 and the second lane 103, and the first lane line 104A can be a lane edge line of the first lane 102.

[0058] S2. Determine information of a second reference point, where the second reference point is a point on the second lane.

[0059] See also Figure 1 (1), from Figure 1 As can be seen from (1), 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. Specifically, the second reference point 101B may be a point on the second lane line 105A (or an extension of the second lane line 105A) in an area close to the intersection 106. The second lane line 105A may be a lane edge line of the second lane 103.

[0060] S3. Determine an intersection point, where the intersection point is a point where the first lane line extends toward the intersection and intersects with the second lane line extends toward the intersection.

[0061] See also Figure 1 (1), from Figure 1 As can be seen from (1), the intersection is the intersection 101C. The intersection 101C is the point where the extension line of the first lane line 104A to the intersection and the extension line of the second lane line 105A to the intersection meet.

[0062] S4, generating a right turn lane line according to the first reference point, the second reference point and the intersection point.

[0063] from Figure 1 As can be seen from (2), 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 with the obstacle 108 in the intersection 106, that is, the obstacle 108 may appear in the area covered by the right-turn lane line 107.

[0064] It can be seen that lane lines drawn without obstacle avoidance may press on obstacles in the intersection and still require manual adjustment, which is inefficient and prone to errors.

[0065] 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 based on the embodiments of the present application. Figure 2A , Figure 2A It is a structural diagram of a lane line planning system provided in 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 send the collected raw data for drawing lane lines to the drawing device 002, and the drawing device 002 completes the drawing of the lane lines.

[0066] The acquisition device 001 can be an electronic device with specific data acquisition capabilities and data transmission and reception capabilities. For example, the acquisition device 001 can be a collection vehicle equipped with one or more sensors such as a laser radar, a camera, a global navigation satellite system (GNSS), an inertial measurement unit (IMU), etc. The collection 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 the collection vehicles traveling on various roads. Among them, the laser radar is mainly used to collect point cloud data. Because the laser radar can accurately reflect the location information, the width of the road surface, the height of the traffic light and some other information can be obtained through the laser radar; the camera is mainly used to collect road signs, lane lines and other information; the GNSS is mainly used to record the coordinates of the current collection point; the 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.

[0067] Alternatively, the acquisition device 001 can also be a roadside unit installed at an intersection. The roadside unit can obtain intersection information within the coverage area and monitor multiple intelligent vehicles within the coverage area. The roadside unit can collect intersection information of lane lines to be planned in automatic driving, that is, the roadside unit can monitor the dynamics in the intersection at any time, and can send intersection information to intelligent vehicles that need to pass through the intersection. It should be noted that the intersection information can be obtained by one roadside unit, or by multiple roadside units working together to obtain intersection information, so as to obtain information on all roads connected to the intersection. Among them, the roadside unit can be composed of a high-gain directional beam-controlled read-write antenna and a radio frequency controller. The high-gain directional beam-controlled read-write antenna is a microwave transceiver module responsible for sending / receiving, modulating / demodulating, encoding / decoding, encrypting / decrypting signals and data; the radio frequency controller is a module that controls the transmission and reception of data and processes the transmission and reception of information to the upper computer.

[0068] The acquisition device 001 can be used to acquire the intersection information of the lane lines to be marked in the high-precision map, such as the road-level data at the intersection (that is, the data of each road connected to the intersection), the lane-level data at the intersection (that is, the data of each lane connected to the intersection), and the information of obstacles in the intersection. The road level can also be called non-high-precision vector road network data, which is used to describe specific roads from the road level accuracy. Road-level data is road network data collected at the road granularity, that is, a lane containing multiple lanes will only have one vector data in units of road segments (link). Vector data includes a series of position coordinate points, usually a series of position coordinate points on the center line of the road; road-level data also includes road grade, capacity, number of lanes, road category, driving mode, road bandwidth, etc. Lane-level data can be called high-precision vector road network data, which is used to describe specific roads from the lane line accuracy. Specifically, lane-level data is road network data collected at the lane line granularity, and may include but is not limited to lane edge line information (including vector data of the location of lane edge lines) and lane dividing line information (including vector data of the location of lane dividing lines) of any road. Obstacles may be objects that hinder driving at intersections, and obstacle information may be vector data of the location of obstacles. Obstacles include but are not limited to at least one of the following: curbs, trees, street lights, etc.

[0069] The drawing device 002 may be an electronic device with data processing capability and data transceiving capability, and may be a physical device such as a host, a rack server, a blade server, etc., or a virtual device such as a virtual machine, a container, etc. The drawing device 002 may 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 obstacle at the first intersection from the intersection information; wherein the first intersection is an intersection where a lane line needs 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, the second lane line is a lane line connected to the first lane line through the lane line in the intersection, and the obstacle is an object in the first intersection that hinders the planning of the lane line; then determine the target projection point, 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 reference point extending to the first intersection, and the second depth is the depth of the second reference point extending to the first intersection, and finally the drawing device 002 determines the lane line according to the first reference point, the second reference point, and the target projection point as control points.

[0070] In a possible implementation, the drawing device 002 projects the N position points of the obstacle to a first depth to obtain N first projection points; the drawing device 002 projects the N position points of the obstacle to a second depth to obtain N second projection points; then the drawing device 002 selects a target projection point from the N first projection points and the N second projection points, that is, the first projection point with the largest distance to the first reference point among the N first projection points, and the distance to the corresponding point on the obstacle is less than or equal to the first threshold value belongs to the target projection point; or the second projection point with the largest distance to the second reference point among the N second projection points, and the distance to the corresponding point on the obstacle is less than or equal to the second threshold value belongs to the target projection point. The first threshold value and the second threshold value are values ​​obtained through machine learning training according to the distance between the obstacle and the lane line at the intersection.

[0071] It should be noted that when the collection device 001 is a collection vehicle, the collected intersection information can be the intersection information of the lane lines to be marked in the high-precision map, and the drawing device 001 can be a device for generating high-precision maps. After the drawing device 001 generates a high-precision map, the high-precision map can be sent to the intelligent vehicle 003, and the intelligent vehicle 003 can complete driving according to the high-precision map.

[0072] When the collection device 001 is a roadside unit installed at an intersection, the collected intersection information may be information of the intersection where lane lines are to be planned in the autonomous driving. Figure 2B , Figure 2B Schematic diagram of another lane planning system provided by an embodiment of the present application. Figure 2B It can be seen that the drawing device 001 may be an intelligent vehicle 003 traveling at an intersection. When the intelligent vehicle 003 receives the intersection information sent by the roadside unit, it may plan a lane line to avoid obstacles according to the intersection information.

[0073] It should be noted that the lane markings may include straight lane markings, left-turn lane markings or right-turn lane markings, and the embodiments of the present application do not impose any limitations thereon.

[0074] It should be noted that Bezier curves can be used to draw lane lines, and spline curves can also be used to draw lane lines. The embodiment of the present application does not impose any restrictions on the tools for drawing lane lines.

[0075] Based on the above lane line drawing system architecture, the present application embodiment provides an intelligent vehicle 003 applied in the above lane line drawing system architecture. Figure 2C , Figure 2C003 is a functional block diagram of a smart vehicle 003 provided in an embodiment of the present application. In one embodiment, the smart vehicle 003 can be configured to be in a fully or partially autonomous driving mode. For example, the smart vehicle 003 can control itself while in the autonomous driving mode, and can determine the current state of the vehicle and its surrounding environment through human operation, determine the possible behavior of at least one other vehicle in the surrounding environment, and determine the confidence level corresponding to the possibility of the other vehicle performing the possible behavior, and control the smart vehicle 003 based on the determined information. When the smart vehicle 003 is in the autonomous driving mode, the smart vehicle 003 can be set to operate without human interaction.

[0076] The smart vehicle 003 may include various subsystems, such as a travel system 202, a sensor system 204, a control system 206, one or more peripheral devices 208, and a power supply 210, a computer system 212, and a user interface 216. Optionally, the smart vehicle 003 may include more or fewer subsystems, and each subsystem may include multiple elements. In addition, each subsystem and element of the smart vehicle 003 may be interconnected by wire or wirelessly.

[0077] The travel system 202 may include components that provide powered movement for the smart vehicle 003. In one embodiment, the travel system 202 may include an engine 218, an energy source 219, a transmission 220, and wheels / tires 221. The engine 218 may be an internal combustion engine, an electric motor, an air compression engine, or a combination of other types of engines, such as a hybrid engine consisting of a gas-oil engine and an electric motor, or a hybrid engine consisting of an internal combustion engine and an air compression engine. The engine 218 converts the energy source 219 into mechanical energy.

[0078] Examples of energy source 219 include gasoline, diesel, other petroleum-based fuels, propane, other compressed gas-based fuels, ethanol, solar panels, batteries, and other sources of electricity. Energy source 219 can also provide energy for other systems of smart vehicle 003.

[0079] The transmission 220 can transmit mechanical power from the engine 218 to the wheels 221. The transmission 220 may include a gearbox, a differential, and a drive shaft. In one embodiment, the transmission 220 may also include other devices, such as a clutch. Among them, the drive shaft may include one or more shafts that can be coupled to one or more wheels 221.

[0080] The sensing system 204 may include several sensors that sense information about the environment around the smart vehicle 003. For example, the sensing system 204 may include a global positioning system 222 (the positioning system may be a GPS system, or a Beidou system or other positioning systems), an inertial measurement unit (IMU) 224, a radar 226, a laser rangefinder 228, and a camera 230. The sensing system 204 may also include sensors of the internal systems of the monitored smart vehicle 003 (e.g., an in-vehicle air quality monitor, a fuel gauge, an oil temperature gauge, etc.). Sensor data from one or more of these sensors may be used to detect objects and their corresponding characteristics (position, shape, direction, speed, etc.). Such detection and recognition are key functions for the safe operation of the autonomous smart vehicle 003.

[0081] The global positioning system 222 can be used to estimate the geographic location of the smart vehicle 003. The IMU 224 is used to sense the position and orientation changes of the smart vehicle 003 based on inertial acceleration. In one embodiment, the IMU 224 can be a combination of an accelerometer and a gyroscope. For example, the IMU 224 can be used to measure the curvature of the smart vehicle 003.

[0082] Radar 226 can use radio signals to sense objects in the surrounding environment of smart vehicle 003. In some embodiments, in addition to sensing objects, radar 226 can also be used to sense the speed and / or heading of the object.

[0083] The laser rangefinder 228 can use lasers to sense objects in the environment in which the smart vehicle 003 is located. In some embodiments, the laser rangefinder 228 can include one or more laser sources, a laser scanner, and one or more detectors, among other system components.

[0084] The camera 230 may be used to capture multiple images of the surrounding environment of the smart vehicle 003. The camera 230 may be a still camera or a video camera.

[0085] The control system 206 controls the operation of the intelligent vehicle 003 and its components. The control system 206 may include various elements, including a steering system 232 , a throttle 234 , a brake unit 236 , a sensor 238 , a computer vision system 240 , a path control system 242 , and an obstacle avoidance system 244 .

[0086] The steering system 232 is operable to adjust the forward direction of the intelligent vehicle 003. For example, in one embodiment, it can be a steering wheel system.

[0087] The throttle 234 is used to control the operating speed of the engine 218 and thus control the speed of the intelligent vehicle 003 .

[0088] The brake unit 236 is used to control the deceleration of the smart vehicle 003. The brake unit 236 can use friction to slow down the wheel 221. In other embodiments, the brake unit 236 can convert the kinetic energy of the wheel 221 into electric current. The brake unit 236 can also take other forms to slow down the rotation speed of the wheel 221 to control the speed of the smart vehicle 003.

[0089] Computer vision system 240 can be operated to process and analyze the images captured by camera 230 in order to identify objects and / or features in the surrounding environment of intelligent vehicle 003. The objects and / or features may include traffic signals, road boundaries and obstacles. Computer vision system 240 can use object recognition algorithms, Structure from Motion (SFM) algorithms, video tracking and other computer vision technologies. In some embodiments, computer vision system 240 can be used to map the environment, track objects, estimate the speed of objects, etc.

[0090] The route control system 242 is used to determine the driving route of the smart vehicle 003. In some embodiments, the route control system 242 can combine data from the sensor 238, the global positioning system 222 and one or more predetermined maps to determine the driving route for the smart vehicle 003.

[0091] The obstacle avoidance system 244 is used to identify, evaluate, and avoid or otherwise negotiate potential obstacles in the environment of the smart vehicle 003 .

[0092] Of course, in one example, the control system 206 may include additional or alternative components other than those shown and described, or may also reduce some of the components shown above.

[0093] The smart vehicle 003 interacts with external sensors, other vehicles, other computer systems, or users through the peripheral device 208. The peripheral device 208 may include a wireless communication system 246, an onboard computer 248, a microphone 250, and / or a speaker 252.

[0094] In some embodiments, the peripheral device 208 provides a means for the user of the smart vehicle 003 to interact with the user interface 216. For example, the onboard computer 248 can provide information to the user of the smart vehicle 003. The user interface 216 can also operate the onboard computer 248 to receive the user's input. The onboard computer 248 can be operated through a touch screen. In other cases, the peripheral device 208 can provide a means for the smart vehicle 003 to communicate with other devices located in the vehicle. For example, the microphone 250 can receive audio (e.g., voice commands or other audio input) from the user of the smart vehicle 003. Similarly, the speaker 252 can output audio to the user of the smart vehicle 003.

[0095] The wireless communication system 246 can communicate wirelessly with one or more devices directly or via a communication network. For example, the wireless communication system 246 can use 3G cellular communication, such as CDMA, EVDO, GSM / GPRS, or 4G cellular communication, such as LTE. Or 5G cellular communication. The wireless communication system 246 can communicate with a wireless local area network (WLAN) using WiFi. In some embodiments, the wireless communication system 246 can communicate directly with the device using an infrared link, Bluetooth, or ZigBee. Other wireless protocols, such as various vehicle communication systems, for example, the wireless communication system 246 may include one or more dedicated short range communications (DSRC) devices, which may include public and / or private data communications between vehicles and / or roadside stations.

[0096] The power source 210 can provide power to various components of the smart vehicle 003. In one embodiment, the power source 210 can be a rechargeable lithium-ion or lead-acid battery. One or more battery packs of such batteries can be configured as a power source to provide power to various components of the smart vehicle 003. In some embodiments, the power source 210 and the energy source 219 can be implemented together, such as in some all-electric vehicles.

[0097] Some or all functions of the smart vehicle 003 are controlled by a computer system 212. The computer system 212 may include at least one processor 213 that executes instructions 215 stored in a non-transitory computer-readable medium such as a memory 214. The computer system 212 may also be a plurality of computing devices that control individual components or subsystems of the smart vehicle 003 in a distributed manner.

[0098] 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. Figure 2CFunctionally illustrated processor, memory and other elements of the computer in the same block, but those of ordinary skill in the art will appreciate that the processor, computer or memory may actually include multiple processors, computers or memories that may or may not be stored in the same physical housing. For example, the memory may be a hard drive or other storage medium that is located in a housing different from the computer. Therefore, references to processors or computers will be understood to include references to a collection of processors or computers or memories that may or may not operate in parallel. Different from using a single processor to perform the steps described herein, some components such as steering components and deceleration components may each have their own processors that only perform calculations related to the functions specific to the components.

[0099] In various aspects described herein, the processor may be located remote 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 and others are performed by a remote processor, including taking the necessary steps to perform a single maneuver.

[0100] In some embodiments, the memory 214 may include instructions 215 (e.g., program logic) that may be executed by the processor 213 to perform various functions of the smart vehicle 003, including those described above. The memory 214 may also include additional instructions, including instructions to send data to, receive data from, interact with, and / or control one or more of the travel system 202, the sensor system 204, the control system 206, and the peripheral device 208.

[0101] In addition to instructions 215, memory 214 may also store data such as road maps, route information, the vehicle's location, direction, speed, and other such vehicle data, as well as other information. This information may be used by smart vehicle 003 and computer system 212 during operation of smart vehicle 003 in autonomous, semi-autonomous, and / or manual modes.

[0102] The user interface 216 is used to provide information to or receive information from a user of the smart vehicle 003. Optionally, the user interface 216 may include one or more input / output devices within the set of peripheral devices 208, such as a wireless communication system 246, an onboard computer 248, a microphone 250, and a speaker 252.

[0103] The computer system 212 can control the functions of the intelligent vehicle 003 based on inputs received from various subsystems (e.g., wireless communication system 246, travel system 202, sensor system 204, and control system 206) and from the user interface 216. For example, the computer system 212 can use the input from the wireless communication system 246 to plan the lane line at the intersection that needs to be passed in the automatic driving, and the lane line can avoid hitting the obstacles at the intersection. In some embodiments, the computer system 212 can be operated to provide control for many aspects of the intelligent vehicle 003 and its subsystems.

[0104] Optionally, the computer system 212 can also receive information from other computer systems, or transfer information to other computer systems. For example, the computer system 212 can transfer the sensor data collected from the sensor system 204 of the intelligent vehicle 003 to another remote computer system, and hand it over to another computer system for processing, such as another computer system to perform data fusion on the data collected by each sensor in the sensor system 204, and then return the fused data or analysis results to the computer system 212. Optionally, the data from the computer system 212 can be transmitted to the computer system on the cloud side via the network for further processing. The network and the intermediate nodes can include various configurations and protocols, including the Internet, the World Wide Web, the intranet, a virtual private network, a wide area network, a local area network, a private network using one or more companies' proprietary communication protocols, Ethernet, WiFi and HTTP, and various combinations of the foregoing. This communication can be by any device capable of transmitting data to and from other computers, such as a modem and a wireless interface.

[0105] As described above, in some possible embodiments, the remote computer system interacting with the computer system 212 in the intelligent vehicle 003 may include a server having multiple computers, such as a load balancing server group, which exchanges information with different nodes of the network for the purpose of receiving, processing and transmitting data from the computer system 212. The server may have a processor, a memory, instructions and data, etc. 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 weather-related information. The information may include precipitation, cloud, and / or temperature information in the form of reports, radar information, forecasts, etc. The data of the server may 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 may send the high-precision map data and traffic information to the computer system 212, so as to assist the intelligent vehicle 003 to better perform automatic driving and ensure driving safety.

[0106] Optionally, one or more of the above components may be installed or associated separately from the smart vehicle 003. For example, the memory 214 may be partially or completely separate from the smart vehicle 003. The above components may be communicatively coupled together in a wired and / or wireless manner.

[0107] Optionally, the above components are only examples. In actual applications, the components in the above modules may be added or deleted according to actual needs. Figure 2C It should not be understood as limiting the embodiments of the present application.

[0108] An autonomous vehicle traveling on a road, such as the smart vehicle 003 above, can identify objects in its surrounding environment to determine adjustments to the current speed. The objects can be other vehicles, traffic control devices, or other types of objects. In some examples, each identified object can be considered independently, and based on the respective characteristics of the object, such as its current speed, acceleration, spacing from the vehicle, etc., can be used to determine the speed to be adjusted by the autonomous vehicle.

[0109] Optionally, the autonomous driving intelligent vehicle 003 or a computing device associated with the autonomous driving intelligent vehicle 003 (such as Figure 2C The computer system 212, computer vision system 240, memory 214) can predict the behavior of the identified object based on the characteristics of the identified object and the state of the surrounding environment (e.g., traffic, rain, ice on the road, etc.). Optionally, each identified object depends on the behavior of each other, so all the identified objects can also be considered together to predict the behavior of a single identified object. The smart vehicle 003 can adjust its speed based on the predicted behavior of the identified object. In other words, the self-driving car can determine what stable state the vehicle will need to be adjusted to (e.g., accelerate, decelerate, or stop) based on the predicted behavior of the object. In this process, other factors can also be considered to determine the speed of the smart vehicle 003, such as the lateral position of the smart vehicle 003 in the road on which it is traveling, the curvature of the road, the proximity of static and dynamic objects, etc.

[0110] In addition to providing instructions to adjust the speed of the autonomous vehicle, the computing device may also provide instructions to modify the steering angle of the smart vehicle 003 so that the autonomous vehicle follows a given trajectory and / or maintains a safe lateral and longitudinal distance from objects near the autonomous vehicle (e.g., cars in adjacent lanes on the road).

[0111] The above-mentioned intelligent vehicle 003 can be a car, a truck, a motorcycle, a bus, a ship, an airplane, a helicopter, a lawn mower, an entertainment vehicle, an amusement park vehicle, construction equipment, a tram, a golf cart, a train, and a cart, etc., and the embodiments of the present application do not make any special limitations.

[0112] Understandably, Figure 2C The functional diagram of the smart vehicle 003 is only an exemplary implementation in the embodiment of the present application. The smart vehicle 003 in the embodiment of the present application includes but is not limited to the above structure.

[0113] See also Figure 3A , Figure 3A This is a schematic diagram of a method for drawing lane lines provided in an embodiment of the present application. The method can be applied to the above Figure 2A or Figure 2B The system architecture described above can be applied to the above Figure 2A In the drawing device 002. Figure 3A Taking this as an example, the method includes but is not limited to the following steps:

[0114] Step S301: Obtain information of the first intersection.

[0115] Specifically, the first intersection is an intersection where lane lines need to be planned. Figure 2A When the collection device 001 is a collection vehicle, the intersection information collected by the collection device 001 is the information of the intersections that need 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 intersection information to the rendering device 002, so that the rendering device 002 can obtain the information of the first intersection. Figure 2A When the collection device 001 is a roadside unit, the drawing device 002 may be an intelligent vehicle 003. Figure 2B The information of the intersections collected by the acquisition device 001 is the information of the intersections where the lane lines are to be planned in the automatic driving (including the information of the first intersection), and then the acquisition device 001 sends the information of the above intersections to the intelligent vehicle 003, so that the intelligent vehicle 003 can obtain the information of the first intersection.

[0116] 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 obstacle 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, the second lane line connects the first lane line through the lane line of the first intersection, and the obstacle is an object that hinders driving near the first intersection. Please refer to Figure 3B , Figure 3B It is a schematic diagram of intersection information provided in an embodiment of the present application. Figure 3B The following is an example of a crossroads:

[0117] Junctions are represented as areas where roads converge, optionally from Figure 3B It can be seen that the intersection 300 can be a rectangular area surrounded by 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 stop line on the fourth lane 304, or an area around the rectangle. Among them, the first lane 301, the second lane 302, the third lane 303 and the fourth lane 304 are two-way lanes, consisting of two lanes in opposite directions. It can be understood that the intersection not only includes the intersection of four roads such as Figure 3B The intersection 300 shown (e.g., a crossroads, an X-shaped intersection) also includes, but is not limited to, an intersection where two roads intersect, an intersection where three roads intersect (e.g., a T-junction, a Y-junction). It should be noted that in a circular intersection section (e.g., a roundabout), each group of two adjacent roads and a loop line can be defined to form an intersection. Among them, the intersection 300 is an intersection where lane lines need to be planned. The lane lines are used to indicate the driving route in the intersection area and are virtual curves connecting the first lane line and the second lane line. Generally speaking, one end of the lane line of the intersection is connected to the lane end point of the exit lane, and the other end is connected to the lane start point of the entry lane.

[0118] The first lane line may represent the lane line outside the intersection. It is understandable 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 on the lane can drive on the lane. From another perspective, the driving direction actually indicates how the vehicle can drive on the lane, such as going straight, turning right, or turning left. Figure 3B It can be seen that the driving directions corresponding to the first lane 301, the second lane 302, the third lane 303 and the fourth lane 304 may include one or more of the following: straight ahead, left turn or right turn. Therefore, the first lane line 301A may be the lane line of the right turn lane on the first lane 301, or the first lane line 301A may be the lane line of the straight lane on the second lane 302, or the first lane line 301A may be the lane line of the right turn lane on the third lane 303, or the first lane line 301A may be the lane line of the straight lane on the fourth lane 304.

[0119] The second lane line may represent the exit lane line outside the intersection. It is understandable that the second lane line is a lane line that has a corresponding relationship with the first lane line, that is, the lane line connected by the lane line planned at the intersection 300 and the first lane line is the second lane line. Figure 3BIt can be seen that if first lane line 301A is the lane line of the right turn lane on first lane 301, then second lane line 301B can be the lane line on the second lane, that is, second lane line 301B is the lane line connecting the first lane line 301A through the right turn lane line of intersection 300; if first lane line 301A is the lane line of the straight lane on first lane 301, then second lane 301B can be the lane line on third lane 303, that is, second lane line 301B is the lane line connecting the first lane line 301A through the straight lane line of intersection 300.

[0120] The first reference point is a point on the first lane line or an extension of the first lane line, and specifically can be a point on the first lane line close to the intersection. For example, the first reference point can be a point on the intersection of the first lane line and the stop line, or a point on the first lane line close to the stop line, or a point on the intersection of the extension of the first lane line and the intersection. Figure 3B It can be seen that the first reference point 302A can 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 point on the first lane line 301A of the third lane 303, or a point on the first lane line 301A of the fourth lane 304.

[0121] The second reference point is a point on the second lane line or the extension of the second lane line, specifically, a point on the second lane line close to the intersection. For example, the second reference point can be a point on the intersection of the second lane line and the stop line, or a point on the second lane line close to the stop line, or a point on the intersection of the extension of the second lane line and the intersection. Because the second lane line is a lane line that has a corresponding relationship with the first lane line, the second reference point is a point that has a corresponding relationship with the first reference point. Figure 3BIt can be seen that 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 can be a point on the second lane line 301B of the second lane 302, that is, the endpoint of the right-turn lane line planned at the intersection connected to the first lane line 301A of the first lane 301 is the first reference point 302A, and the endpoint of the second lane line 301B of the second lane is the second reference point 302B; if the planned lane line is a straight lane line, the first reference point 302A is the straight lane line of the first lane 301 The second reference point 302B may be a point on the lane line of the third lane 303, that is, one end of the straight lane line planned at the intersection is connected to the endpoint 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 endpoint of the second lane line 301B of the third lane 303 as the second reference point 302B; if the planned lane line is a left-turn lane line, the first reference point 302A is a point on the lane line of the left-turn lane of the first lane 301, and the second reference point 302B may be a point on the second lane line 301B of the fourth lane 304.

[0122] Obstacles can be objects that may hinder driving at the intersection, such as trees, curbs, traffic signs placed on the ground, etc. Figure 3B It can be seen that obstacle 305 is a tree near the curb at the intersection. The obstacle information collected by the collection device 001 can be 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 through the one or more coordinate points.

[0123] Step S302: Determine the target projection point.

[0124] Specifically, the target projection point is a projection point of the obstacle to a first depth and / or a second depth, wherein the first depth is a depth from a first reference point to an intersection, and the second depth is a depth from a second reference point to an intersection.

[0125] In a possible implementation, before determining the target projection point, the drawing device 002 can determine a planning area and mark the objects in the planning area as obstacles. It can be understood that the information of the obstacle obtained is vector data that can represent the shape, size and specific position of the obstacle, and the obstacle that affects the drawing of the right-turn lane line may be a part of the obstacle, such as the part near the intersection. Therefore, objects located within the planning area (including the side boundary of the right-turn area) are regarded as obstacles, which can improve the accuracy of the planned lane line not pressing the obstacle. Optionally, the drawing device 002 can determine the planning area according to the first reference point, the second reference point and the intersection, and mark the objects in the planning area as obstacles. Among them, the intersection is the point where the first depth and the second depth meet. In the embodiment of the present application, because the first reference point, the second reference point and the intersection are the points needed for planning the lane line, the planning area determined by the first reference point, the second reference point and the intersection can quickly and accurately determine the objects that hinder the planning lane line.

[0126] In a possible implementation, the drawing device 002 projects the N position points of the obstacle to the first depth, and can obtain N first projection points. The first projection point whose distance to the first reference point is the largest and 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; the N position points of the obstacle are projected to the second depth, and N second projection points are obtained. The second projection point whose distance to the first reference point is the largest and whose distance to the corresponding point on the obstacle is less than or equal to the second threshold value is selected from the N N-th projection points and 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 the embodiment of the present application, through the given preset conditions, the target projection point that meets the preset requirements is selected from the N first projection points and / or the N second projection points. Because of the existence of the first threshold value and the second threshold value in the preset conditions, the accuracy of the lane line drawn by the determined target projection will not press the obstacle can be improved, and it is also guaranteed that the vehicle can smoothly exit the intersection through the planned lane line.

[0127] The first threshold and the second threshold are empirical values ​​that can meet the needs obtained through machine learning training based on the distance between the obstacle and the lane line at the intersection. That is, the values ​​are obtained by training by analyzing the distance relationship between the obstacle and the lane line at the intersection, or analyzing the distance required for the vehicle to turn at the intersection through a large amount of data collected from the intersection. The target projection point determined by the first threshold and / or the second threshold can ensure that the planned lane line will not press on the obstacle, and can also ensure that the vehicle turns right or left through the planned lane line. Among them, the first threshold and the second threshold can be equal or unequal.

[0128] For example, see Figure 3C , Figure 3C is a schematic diagram of determining a target projection point provided by an embodiment of the present application. Figure 3C The following is an example of drawing a right turn lane line. Figure 3C It can be seen that 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 of the first reference point 302A extending to the intersection 300, that is, the extension line of the first lane line 301A along the intersection 300; the second depth 303B is the depth of the second reference point 302B extending to the intersection 300, that is, the extension line of the second lane line 301B along the intersection 300. The point where the first depth 303A and the second depth 303B meet is the intersection point 300B, which is a control point required for drawing lane lines.

[0129] The planning area can be determined based on the first reference point 302A, the second reference point 302B and the intersection 300B. The overlapped part of the obstacle 305 and the planning area can be considered as an obstacle that will affect the drawing of the lane line. The target projection point is determined by obtaining the information of the obstacle in the overlapping part. Figure 3CIt can be seen that point 30A represents any point on the obstacle 305 in the right turn area, that is, point 30A includes N position points of the obstacle, and N is greater than or equal to 1. Point 30B is obtained by drawing a perpendicular line from point 30A to the first depth 303A, and point 30C is obtained by drawing a perpendicular line from point 30A to the second depth 303B. It can be understood that because point 30A includes N position points, point 30B includes N projection points, and point 30C also includes N projection points. Then, from point 30B, a projection point with the farthest distance from the first reference point 302A and a distance from point 30B to the corresponding point on the obstacle is less than or equal to the first threshold is selected; from point 30C, a projection point with the farthest distance from the first reference point 302B and a distance from point 30C to the corresponding point on the obstacle is less than or equal to the second threshold is selected. It should be noted that the point corresponding to point 30B on the obstacle and the point corresponding to point 30C on the obstacle can be the same point or different points.

[0130] It should be noted that if the lane line is a straight lane line or a left-turn lane line, the planning area can be determined according to the above-mentioned right-turn lane line method, which will not be repeated here.

[0131] Step S303: Determine the lane line according to the first reference point, the second reference point and the target projection point.

[0132] Specifically, because the first projection point and / or the second projection point that meets the preset conditions is the target projection point, the target projection point includes one or more of the following situations: in situation one, the target projection point includes the first projection point; in situation two, the target projection point includes the second projection point; in situation three, the target projection point includes the first projection point and the second projection point.

[0133] When the target projection point is the first projection point, the drawing device 002 can determine the lane line according to the first reference point, the second reference point and the first projection point. The lane line can be composed of a first line segment and a first curve, the first line segment is determined by the first reference point and the first projection point, and the first curve is determined by the first projection point, the intersection point and the second reference point. Among them, the intersection point is the point where the first depth and the second depth meet. In an embodiment of the present application, the lane line is composed of a first line segment and a first curve, and the first line segment is the longest distance to avoid obstacles at the entrance to the intersection and to ensure the completion of the right turn. Therefore, the first line segment can be used to completely avoid obstacles and the first curve can be used to exit the intersection.

[0134] When the target projection point is the second projection point, the drawing device 002 can determine the lane line according to the first reference point, the second reference point and the second projection point. The lane line can be composed of a second line segment and a second curve, the second line segment is determined by the second reference point and the second projection point, and the second curve is determined by the second projection point, the intersection point and the first reference point. Among them, the intersection point is the point where the first depth and the second depth meet. In an 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 to avoid obstacles when leaving the intersection and to ensure the completion of the right turn, which can ensure that the second line segment is used to avoid pressing the obstacle when the obstacle is about to be pressed when turning right.

[0135] When the target projection point includes the first projection point and the second projection point, the drawing device 002 can 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 can 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, 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. Among them, 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, the third line segment is the longest distance to avoid obstacles when entering the intersection, and it can ensure that the right turn is made while completely avoiding obstacles, and the fourth line segment is the longest distance to avoid obstacles when leaving the intersection and ensure that the right turn is completed, which can ensure that the fourth line segment is used to avoid the obstacle when the obstacle is about to be pressed when turning right.

[0136] 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 embodiment of the present application does not impose any restrictions on the tool for planning the lane line.

[0137] By using the method provided in the embodiment of the present application, obstacles at the intersection are taken into consideration when planning the lane line at the intersection, so that the target projection point can be determined, and then the lane line can be determined based on 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 press on the obstacle, and no manual adjustment is required, which can improve the efficiency and accuracy of planning the lane line.

[0138] See also Figure 4 , Figure 4 This is another schematic diagram of a scene for drawing lane lines provided in an embodiment of the present application. Figure 4 This is explained by taking the drawing of the right turn lane as an example. Figure 4It can be seen 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 the information of the obstacle 400. Among them, the information of the obstacle in the right turn area determined by the first reference point 401A, the second reference point 401B and the intersection 401C includes point 400A, point 400B and point 400C. The intersection 401C is the point where the first depth 402A and the second depth 402B meet, the first depth 402A is the depth of the first reference point 401A extending to the first intersection 004, and the second depth 402B is the depth of the second reference point 401B extending to the first intersection 004.

[0139] Please refer to Figure 4 (1), the drawing device 002 draws a perpendicular line from point 400A to the first depth 402A to obtain the projection point of point 400A at the first depth 402A as point 4001A; similarly, the projection point of point 400B at the first depth 402A is point 4001B, and the projection point of point 400C at the first depth 402A is point 4001C. The drawing device 002 draws perpendicular lines from point 400A, point 400B, and point 400C to the second depth 402B to obtain the projection point as point 4002A. Next, the drawing device 002 selects the point with the largest distance to the first reference point 401A from point 4001A, point 4001B, and point 4001C, and the point with a distance to the corresponding point on the obstacle 400 less than or equal to the first threshold value as the target projection point. Because the distances determined between point 400A and point 4001A, the distances determined between point 400B and point 4001B, and the distances determined between point 400C and point 4001C are all less than or equal to the first threshold, but point 4001C is the point farthest from the first reference point 401A, so point 4001C is selected as the target projection point at the first depth. However, the distances determined between point 4002A and point 400A, the distances determined between point 4002A and point 400B, and the distances determined between point 4002A and point 400C are all greater than the second threshold, so there is no target projection point that meets the preset condition at the second depth.

[0140] Please refer to Figure 4 (2), after the target projection point 4001C is determined, a first line segment 403 determined by the first reference point 401A and the point 4001C and a first curve 404 determined by the point 4001C, the intersection point 400C and the second reference point 401B are used to form the right turn lane line. Figure 4 It can be seen from (2) that the right turn lane line drawn by the above method will not press the obstacle 400.

[0141] It can be understood that the lane in which the vehicle is traveling 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 to improve efficiency.

[0142] See also Figure 5 , Figure 5 This is another schematic diagram of a scene for drawing lane lines provided in an embodiment of the present application. Figure 5 This is explained by taking the drawing of the right turn lane as an example. Figure 5 It can be seen that the information of the first intersection 005 obtained by the drawing device 002 includes the information of the first reference point 501A, the information of the second reference point 501B and the information of the obstacle 500. Among them, the information of the obstacle in the right turn area determined by the first reference point 501A, the second reference point 501B and the intersection 501C includes point 500A, point 500B and point 500C. The intersection 501C is the point where the first depth 502A and the second depth 502B meet. The first depth 502A is the depth of the first reference point 501A extending to the first intersection 005, and the second depth 502B is the depth of the second reference point 501B extending to the first intersection 005.

[0143] Please refer to Figure 5(1), the drawing device 002 draws a perpendicular line from point 500A to the second depth 502B to obtain the projection point of point 500A at the second depth 502B as point 5001A; similarly, the projection point of point 500B at the second depth 502B is point 5001B, and the projection point of point 500C at the second depth 502B is point 5001C. The drawing device 002 draws perpendicular lines from point 500A and point 500B to the first depth 502A to obtain the projection point as point 5002A, and draws a perpendicular line from point 500C to the first depth 502A to obtain the projection point as point 5002B. Next, the drawing device 002 selects the point with the largest distance to the second reference point 501B from point 5001A, point 5001B, and point 5001C, and the point with the largest distance to the corresponding point on the obstacle 500 is less than or equal to the second threshold value as the target projection point. The drawing device 002 selects the point with the largest distance to the first reference point 501A from the point 5002A and the point 5002B, and the point with the largest distance to the corresponding point on the obstacle 500 less than or equal to the first threshold as the target projection point. Because the distances determined between the point 500A and the point 5001A, the distances determined between the point 500B and the point 5001B, and the distances determined between the point 500C and the point 5001C are all less than or equal to the first threshold, but the point 5001C is the point farthest from the second reference point 501B, so the point 5001C is selected as the target projection point at the second depth 502B. However, the distances determined between the point 5002A and the point 500A, the distances determined between the point 5002A and the point 500B, and the distances determined between the point 5002B and the point 500C are all greater than the first threshold, so there is no target projection point that meets the preset condition at the first depth.

[0144] Please refer to Figure 5 (2), after the target projection point 5001C is determined, the second curve 503 determined by the first reference point 501A, the intersection point 501C and the point 5001C, and the second line segment 504 determined by the point 5001C and the second reference point 501B form the right turn lane line through the Bezier curve or spline curve. Figure 5 It can be seen from (2) that the right turn lane line drawn by the above method will not press the obstacle 500.

[0145] It can be understood that the lane in which the vehicle is traveling 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 to improve efficiency.

[0146] See also Figure 6 , Figure 6 This is another schematic diagram of a scene for drawing lane lines provided in an embodiment of the present application. Figure 6 This is explained by taking the drawing of the right turn lane as an example. Figure 6It can be seen 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 the information of the obstacle 600. Among them, the information of the obstacle in the right turn area determined by the first reference point 601A, the second reference point 601B and the intersection 601C includes point 600A, point 600B, point 600C, point 600D and point 600E. The intersection 601C is the point where the first depth 602A and the second depth 602B meet. The first depth 602A is the depth of the first reference point 601A extending to the first intersection 006, and the second depth 602B is the depth of the second reference point 601B extending to the first intersection 006.

[0147] Please refer to Figure 6 (1), the drawing device 002 draws a perpendicular line through point 600A to the first depth 602A to obtain the projection point of point 600A at the first depth 602A as point 6001A; similarly, the projection point of point 600B at the first depth 602A is point 6001B, and the projection point of point 600C at the first depth 602A is point 6001C. Similarly, the corresponding projection points of point 600A, point 600B and point 600C at the second depth 602B can be obtained. Similarly, the drawing device 002 draws perpendicular lines through point 600D and point 600E to the second depth 602B to obtain the corresponding projection points as point 6001D and point 6001E; similarly, the projection points of point 600D and point 600E at the first depth 602A can be obtained. Next, the drawing device 002 selects the point with the largest distance to the first reference point 601A from point 6001A, point 6001B, point 6001C, and other projection points to the first depth 602A, and the point with the largest distance to the corresponding point on the obstacle 600 is less than or equal to the first threshold value as the target projection point. The drawing device 002 selects the point with the largest distance to the second reference point 601B from point 6001B, point 6001E, and other projection points to the second depth 602B, and the point with the largest distance to the corresponding point on the obstacle 600 is less than or equal to the second threshold value as the target projection point. Figure 6 It can be seen from (1) that point 6001C and point 6001D are target projection points that can meet the preset conditions.

[0148] Please refer to Figure 6 (2), after determining point 6001C and point 6001D as the target projection points, the right turn lane line is formed by the third line segment 603 determined by the first reference point 601A and point 6001C through a Bezier curve or a spline curve, the third curve 604 determined by point 6001C, the intersection point 601C and point 6001D, and the fourth line segment 605 determined by point 6001D and the second reference point 601B. Figure 6As can be seen from (2), the right-turn lane line drawn by the above method will not press the obstacle 600.

[0149] It can be understood that the lane in which the vehicle is traveling 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 to improve efficiency.

[0150] It should be noted that, according to Figure 4 , Figure 5 or Figure 6 In the illustrated embodiment, the method for planning the right-turn lane line is used to derive the planning of the straight lane line or the left-turn lane line, and the embodiments for planning the straight lane line or the left-turn lane line are not described in detail here.

[0151] The method of the embodiment of the present application is described in detail above, and the device of the embodiment of the present application is provided below.

[0152] See also Figure 7 , Figure 7 It is a structural diagram of a lane line planning device provided in an embodiment of the present application. The lane line planning device 700 can be a node or a device in a node, such as a chip or an integrated circuit. The lane line planning device 700 can include an acquisition unit 701, a determination unit 702 and a planning unit 703, wherein each unit is described in detail as follows.

[0153] The acquisition unit 701 is used to acquire information of a first intersection, wherein the information of the first intersection includes information of a first reference point, information of a second reference point, and information of an obstacle at the first intersection; wherein the first intersection is an intersection requiring lane line planning, 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 line connected to the first intersection is the first lane line and the second lane line, the second lane line connects the first lane line through the lane line of the first intersection, and the obstacle is an object in the first intersection that obstructs the planning of the lane line;

[0154] A determination unit 702 is used to determine 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, the first depth is a depth from the first lane line extending to the first intersection, and the second depth is a depth from the second lane line extending to the first intersection;

[0155] The planning unit 703 is used to determine the lane line according to the first reference point, the second reference point and the target projection point.

[0156] It can be seen that because the obstacles at the intersection are taken into consideration when planning the lane lines at the intersection, the target projection point can be determined, and then the lane lines can be determined based on 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 lines will not press on the obstacles, and no manual adjustment is required, which can improve the efficiency and accuracy of planning lane lines.

[0157] In a possible implementation, the determining unit 702 is further configured to:

[0158] Determine the planning area and mark objects within the planning area as obstacles.

[0159] 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 objects that may hinder the planning of the lane line can be marked as obstacles through the planning area.

[0160] In a possible implementation manner, the determining unit 702 is specifically configured to:

[0161] The planning area is determined according to the first reference point, the second reference point and the intersection point, where the intersection point is the point where the first depth and the second depth meet.

[0162] In an embodiment of the present application, because the first reference point, the second reference point and the intersection are the points needed to plan the lane lines, the planning area determined by the first reference point, the second reference point and the intersection can more accurately find objects that hinder the planned lane lines.

[0163] In a possible implementation manner, the determining unit 702 is specifically configured to:

[0164] 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;

[0165] Project the N position points of the obstacle to the second depth to obtain N second projection points;

[0166] A target projection point is selected from the N first projection points and the N second projection points, where:

[0167] The first projection point whose distance to the first reference point is the largest among the N first projection points and 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;

[0168] The second projection point whose distance to the second reference point is the largest among the N second projection points and whose distance to the corresponding point on the obstacle is less than or equal to the second threshold value belongs to the target projection point.

[0169] In an embodiment of the present application, through given preset conditions, a target projection point that meets the preset requirements is selected from N first projection points and / or N second projection points. Because of the existence of the first threshold and the second threshold in the preset conditions, the possibility that the lane line drawn by the determined target projection will not press onto obstacles can be increased, and it is also ensured that the vehicle can smoothly exit the intersection through the planned lane line.

[0170] In a possible implementation manner, the target projection point includes a first projection point, and the planning unit 703 is specifically configured to:

[0171] Determine a first line segment according to the first reference point and the first projection point;

[0172] Determine a first curve according to the first projection point, the second reference point and the intersection point, where the intersection point is the point where the first depth and the second depth meet;

[0173] The right-turn lane line is determined by the first line segment and the first curve.

[0174] In an 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 when entering the intersection and ensure the completion of the right turn. Therefore, the first line segment can be used to completely avoid obstacles and the first curve can be used to exit the intersection.

[0175] In a possible implementation manner, the target projection point includes the second projection point, and the planning unit 703 is specifically configured to:

[0176] Determine a 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;

[0177] Determine a second straight line according to the second projection point and the second reference point;

[0178] The right-turn lane line is determined by the second curve and the second straight line.

[0179] In an embodiment of the present application, the lane line is composed of a second line segment and a second curve. The second line segment is the longest distance to avoid obstacles when leaving the intersection and to ensure completion of the right turn. The second line segment can be used to avoid hitting the obstacle when the vehicle is about to hit the obstacle during the right turn.

[0180] 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:

[0181] Determine a third line segment according to the first reference point and the first projection point;

[0182] Determine a 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;

[0183] Determine a fourth line segment according to the second projection point and the second reference point;

[0184] The right-turn lane line is determined by the third line segment, the third curve and the fourth line segment.

[0185] 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. The third line segment is the longest distance to avoid obstacles when entering the intersection, which can ensure that the right turn can be made while completely avoiding obstacles. The fourth line segment is the longest distance to avoid obstacles when leaving the intersection and ensure that the right turn is completed. It can be ensured that the fourth line segment can be used to avoid hitting the obstacle when turning right and is about to hit the obstacle.

[0186] In a possible implementation, the first threshold and the second threshold are both reference values ​​obtained through training based on sample data, and the sample data is historical driving data of a driving trajectory avoiding obstacles.

[0187] It should be noted that the implementation of each unit can also refer to Figure 3A The corresponding description of one embodiment is shown.

[0188] See also Figure 8 , Figure 8 800 is a schematic diagram of the structure of a lane line planning device provided in an embodiment of the present application. The lane line planning device 800 can be a node, or a device in a node, such as a chip or an integrated circuit. The device 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 via a bus 803.

[0189] The memory 801 is used to provide a storage space, and the storage space can store data such as an operating system and a computer program. The memory 801 can be a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), or a portable read-only memory (CD-ROM), etc., or a combination of multiple thereof.

[0190] The processor 802 is a module that performs arithmetic operations and / or logical operations, and can specifically be a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor unit (MPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a complex programmable logic device (CPLD), and other processing modules, or a combination of multiple thereof.

[0191] The communication interface 804 is used to receive data sent externally and / or send data externally, 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 also include a transmitter (such as a radio frequency transmitter, an antenna, etc.) coupled to the interface, or a receiver, etc.

[0192] The processor 802 in the lane planning device 800 is used to read the computer program stored in the memory 801 to perform the following operations:

[0193] Obtain information of a first intersection, wherein 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 is an intersection requiring lane line planning, the first reference point is a point on the first lane line, the second reference point is a point on the second lane line, lane lines connected to the first intersection are the first lane line and the second lane line, the second lane line connects the first lane line through the lane line of the first intersection, and the obstacle is an object in the first intersection that obstructs the planning of the lane line; determine 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, the first depth is a depth of the first lane line extending to the first intersection, and the second depth is a depth of the second lane line extending to the first intersection; determine the lane line according to the first reference point, the second reference point, and the target projection point.

[0194] It can be seen that because the obstacles at the intersection are taken into consideration when planning the lane lines at the intersection, the target projection point can be determined, and then the lane lines can be determined based on 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 lines will not press on the obstacles, and no manual adjustment is required, which can improve the efficiency and accuracy of planning lane lines.

[0195] In a possible implementation, the processor 802 is further configured to:

[0196] Determine the planning area and mark objects within the planning area as obstacles.

[0197] 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 objects that may hinder the planning of the lane line can be marked as obstacles through the planning area.

[0198] In a possible implementation, the processor 802 is specifically configured to:

[0199] The planning area is determined according to the first reference point, the second reference point and the intersection point, where the intersection point is the point where the first depth and the second depth meet.

[0200] In an embodiment of the present application, because the first reference point, the second reference point and the intersection are the points needed to plan the lane lines, the planning area determined by the first reference point, the second reference point and the intersection can more accurately find objects that hinder the planned lane lines.

[0201] In a possible implementation manner, the processor 802 is specifically configured to:

[0202] 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;

[0203] Project the N position points of the obstacle to the second depth to obtain N second projection points;

[0204] A target projection point is selected from the N first projection points and the N second projection points, where:

[0205] The first projection point whose distance to the first reference point is the largest among the N first projection points and 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;

[0206] The second projection point whose distance to the second reference point is the largest among the N second projection points and whose distance to the corresponding point on the obstacle is less than or equal to the second threshold value belongs to the target projection point.

[0207] In an embodiment of the present application, through given preset conditions, a target projection point that meets the preset requirements is selected from N first projection points and / or N second projection points. Because of the existence of the first threshold and the second threshold in the preset conditions, the possibility that the lane line drawn by the determined target projection will not press onto obstacles can be increased, and it is also ensured that the vehicle can smoothly exit the intersection through the planned lane line.

[0208] In a possible implementation, the target projection point includes a first projection point, and the processor 802 is specifically configured to:

[0209] Determine a first line segment according to the first reference point and the first projection point;

[0210] Determine a first curve according to the first projection point, the second reference point and the intersection point, where the intersection point is the point where the first depth and the second depth meet;

[0211] The right-turn lane line is determined by the first line segment and the first curve.

[0212] In an 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 when entering the intersection and ensure the completion of the right turn. Therefore, the first line segment can be used to completely avoid obstacles and the first curve can be used to exit the intersection.

[0213] In a possible implementation, the target projection point includes a second projection point, and the processor 802 is specifically configured to:

[0214] Determine a 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;

[0215] Determine a second straight line according to the second projection point and the second reference point;

[0216] The right-turn lane line is determined by the second curve and the second straight line.

[0217] In an embodiment of the present application, the lane line is composed of a second line segment and a second curve. The second line segment is the longest distance to avoid obstacles when leaving the intersection and to ensure completion of the right turn. The second line segment can be used to avoid hitting the obstacle when the vehicle is about to hit the obstacle during the right turn.

[0218] In a possible implementation, the target projection point includes a first projection point and a second projection point, and the processor 802 is specifically configured to:

[0219] Determine a third line segment according to the first reference point and the first projection point;

[0220] Determine a 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;

[0221] Determine a fourth line segment according to the second projection point and the second reference point;

[0222] The right-turn lane line is determined by the third line segment, the third curve and the fourth line segment.

[0223] In a possible implementation, the first threshold and the second threshold are both reference values ​​obtained through training based on sample data, and the sample data is historical driving data of a driving trajectory avoiding obstacles.

[0224] 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. The third line segment is the longest distance to avoid obstacles when entering the intersection, which can ensure that the right turn can be made while completely avoiding obstacles. The fourth line segment is the longest distance to avoid obstacles when leaving the intersection and ensure that the right turn is completed. It can be ensured that the fourth line segment can be used to avoid hitting the obstacle when turning right and is about to hit the obstacle.

[0225] It should be noted that the implementation of each operation can also refer to Figure 3A The corresponding description of the method embodiment shown.

[0226] The embodiment of the present application further provides a chip system, the chip system comprising 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, the at least one memory stores a computer program; when the computer program is executed by the processor, Figure 3A The method flow shown is realized.

[0227] The present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, which, when executed on one or more processors, Figure 3A The method flow shown is realized.

[0228] The present application also provides a computer program product. When the computer program product is run on one or more processors, Figure 3A The method flow shown is realized.

[0229] A person skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by a computer program or hardware related to the computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned method embodiments. The aforementioned storage medium includes: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store computer program codes.

Claims

1. A lane line planning method, characterized in that: include: Acquire information of a first intersection, the information of the first intersection including information of a first reference point, information of a second reference point, and information of an obstacle at the first intersection; wherein the first intersection is an intersection requiring lane line planning, the first reference point is a point on the first lane line, the second reference point is a point on the second lane line, 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 an object in the first intersection that obstructs the planning of the lane line; Determine a target projection point, wherein the target projection point is a projection point from the obstacle to a first depth and / or a projection point from the obstacle to a second depth selected according to a preset condition, the first depth is a depth of the first lane line extending to the first intersection, and the second depth is a depth of the second lane 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.

2. The method according to claim 1, characterized in that Before determining the target projection point and after acquiring the information of the first intersection, the method further includes: A planning area is determined, and objects in the planning area are marked as obstacles.

3. The method according to claim 2, characterized in that Determining the planning area includes: 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.

4. The method according to any one of claims 1 to 3, characterized in that: Determining the target projection point includes: 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 first projection point whose distance to the first reference point is the largest among the N first projection points and 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 second projection point whose distance to the second reference point is the largest and whose distance to the corresponding point on the obstacle is less than or equal to a second threshold value belongs to the target projection point.

5. The method according to claim 4, characterized in that The target projection point includes the first projection point, and determining the lane line according to the first reference point, the second reference point and the target projection point includes: Determine a first line segment according to the first reference point and the first projection point; Determine a first curve according to the first projection point, the second reference point and an intersection point, wherein 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.

6. The method according to claim 4, characterized in that The target projection point includes the second projection point, and determining the lane line according to the first reference point, the second reference point and the target projection point includes: Determine a second curve according to the first reference point, the second projection point and an intersection point, wherein the intersection point is a point where the first depth and the second depth meet; Determine 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.

7. The method according to claim 4, characterized in that The target projection point includes the first projection point and the second projection point, and determining the lane line according to the first reference point, the second reference point and the target projection point includes: Determine a third line segment according to the first reference point and the first projection point; Determine a third curve according to the first projection point, the second projection point and an intersection point, wherein the intersection point is a point where the first depth and the second depth intersect; Determine a fourth line segment according to the second projection point and the second reference point; The right-turn lane line is determined by the third line segment, the third curve and the fourth line segment.

8. The method according to claim 4, characterized in that The first threshold value and the second threshold value are both reference values ​​obtained through training based on sample data, and the sample data is historical driving data of a driving trajectory avoiding the obstacle.

9. A lane line planning device, characterized in that: include: an acquisition unit, configured to acquire information of a first intersection, wherein the information of the first intersection includes information of a first reference point, information of a second reference point, and information of an obstacle at the first intersection; wherein the first intersection is an intersection requiring lane line planning, the first reference point is a point on the first lane line, the second reference point is a point on the second lane line, 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 an object in the first intersection that obstructs the planning of the lane line; a determination unit, configured to determine a target projection point, wherein the target projection point is a projection point from the obstacle to a first depth and / or a projection point from the obstacle to a second depth selected according to a preset condition, the first depth is a depth of the first lane line extending to the first intersection, and the second depth is a depth of the second lane line extending to the first intersection; A planning unit is used to determine the lane line according to the first reference point, the second reference point and the target projection point.

10. The device according to claim 9, characterized in that The determining unit is further configured to: A planning area is determined, and objects in the planning area are marked as obstacles.

11. The device according to claim 10, characterized in that The determining unit is specifically used for: 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.

12. The device according to any one of claims 9 to 11, characterized in that: The determining unit is specifically used for: 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 first projection point whose distance to the first reference point is the largest among the N first projection points and 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 second projection point whose distance to the second reference point is the largest and whose distance to the corresponding point on the obstacle is less than or equal to a second threshold value belongs to the target projection point.

13. The device according to claim 12, characterized in that The target projection point includes the first projection point, and the planning unit is specifically used for: Determine a first line segment according to the first reference point and the first projection point; Determine a first curve according to the first projection point, the second reference point and an intersection point, wherein 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.

14. The device according to claim 12, characterized in that The target projection point includes the second projection point, and the planning unit is specifically used for: Determine a second curve according to the first reference point, the second projection point and an intersection point, wherein the intersection point is a point where the first depth and the second depth meet; Determine 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.

15. The device according to claim 12, characterized in that 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 used for: Determine a third line segment according to the first reference point and the first projection point; Determine a third curve according to the first projection point, the second projection point and an intersection point, wherein the intersection point is a point where the first depth and the second depth intersect; Determine a fourth line segment according to the second projection point and the second reference point; The right-turn lane line is determined by the third line segment, the third curve, and the fourth line segment.

16. A high-precision map, characterized in that: The high-precision map includes the lane line determined according to the first reference point, the second reference point and the target projection point in the method described in any one of claims 1-8.

17. An intelligent vehicle, characterized in that: The intelligent vehicle comprises at least one processor and at least one memory, and the at least one processor is used to call a computer program stored in the at least one memory so that the intelligent vehicle executes the method according to any one of claims 1 to 8.

18. 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 used to call a computer program stored in the at least one memory so that the lane line planning device executes the method as described in any one of claims 1-8.

19. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is run on one or more processors, the method according to any one of claims 1 to 8 is executed.

Images