WO2021170140A1 - Lane structure detection method and apparatus - Google Patents

Abstract

A lane structure detection method and apparatus. The accuracy of lane structure detection can be improved by means of determining a change in a lane structure according to a change in the distance between a vehicle and a lane boundary. The method comprises: acquiring lane boundary information (S101), wherein the lane boundary information comprises position information of a left lane boundary and a right lane boundary; acquiring position information, respectively corresponding to at least two time points, of a vehicle (S102); determining, with regard to each time point, the distance between the vehicle and the left lane boundary and the distance between the vehicle and the right lane boundary according to the position information, corresponding to the time point, of the vehicle (S103); determining a change in a first distance between the vehicle and the left lane boundary at the at least two time points and a change in a second distance between the vehicle and the right lane boundary at the at least two time points (S104); and determining a lane change on the basis of the change in the first distance and the change in the second distance (S105).

Description

Method and device for detecting lane structure

Cross-references to related applications

This application claims the priority of a Chinese patent application filed with the State Intellectual Property Office of China, the application number is 202010131023.1, and the application name is "a method and device for lane structure detection" on February 28, 2020, the entire content of which is incorporated by reference In this application.

Technical field

This application relates to the field of automatic driving, and in particular to a method and device for detecting a lane structure.

Background technique

In driving roads, road separation and merging are often accompanied by lane changes. Therefore, in the driving process, road merging or separation has a very important impact on driving decision-making and needs to be detected in advance.

At present, it is possible to obtain lane structure information through high-precision maps, and obtain information on the separation and merging of lane lines. However, the high-precision map has a certain degree of coverage. When the vehicle travels to an area without a high-precision map, the road structure cannot be obtained, and the information of the lane line merge point and separation point cannot be known. At the same time, high-precision maps still have the problem of failure. Due to urban renewal or construction, the map after a certain period of time may become invalid, so that the vehicle cannot obtain accurate lane structure information.

Summary of the invention

The present application provides a lane structure detection method and device, which are used to improve the accuracy of acquiring lane structure information.

In a first aspect, an embodiment of the present application provides a lane structure detection method. The method includes: acquiring lane boundary information, where the lane boundary information includes position information of the left lane boundary and the right lane boundary; acquiring the vehicle at least two points in time Respectively corresponding location information; for each time point, determine the distance between the vehicle and the left lane boundary and the right lane boundary according to the vehicle's corresponding location information at the time point; determine the distance between the vehicle and the left lane boundary at at least two time points The first distance change and the second distance change between the vehicle and the right lane boundary at at least two points in time; the lane change is determined based on the first distance change and the second distance change. In the embodiment of the present application, the change of the lane structure is judged according to the change of the distance between the vehicle and the lane boundary. Compared with the method of acquiring the lane structure change through the high-precision map, the embodiment of the present application can realize the detection of the road structure, so as to inform the front The lane structure of the road environment helps intelligent vehicles to carry out risk analysis and path planning in advance under the combined or separated road structure environment, and improve driving safety.

In a possible design, when judging the lane change based on the first distance change and the second distance change, if the first distance change satisfies: the difference between the first distance and the second distance is less than the first threshold, and the second distance The change satisfies: the third distance is less than the fourth distance, and the difference between the third distance and the fourth distance is greater than the second threshold, it is determined that the right side of the first lane has changed, and the first lane is the lane where the vehicle is located; At least two time points include a first time point and a second time point. The first time point is before the second time point, the first distance is the distance between the vehicle at the first time point and the left lane boundary, and the second distance is the vehicle The distance from the left lane boundary at the second time point, the third distance is the distance between the vehicle and the right lane boundary at the first time point, and the fourth distance is the distance between the vehicle and the right lane boundary at the second time point.

In the above design, the change in the right side of the lane can be more accurately determined when the distance between the vehicle and the left lane boundary changes less and the distance from the right lane boundary changes greatly.

In a possible design, if the first distance change still satisfies: the difference between the fifth distance and the second distance is less than the first threshold, the second distance change also satisfies: the sixth distance is greater than the fourth distance, and the sixth distance is greater than the fourth distance. If the difference between the distance and the fourth distance is greater than the second threshold, it is determined that a new lane is added to the right of the first lane; wherein, the multiple time points also include the third time point, and the third time point is after the second time point , The fifth distance is the distance between the vehicle and the left lane boundary at the third time point, and the sixth distance is the distance between the vehicle and the right lane boundary at the third time point.

In the above-mentioned embodiment, due to the right lane separation, the distance between the vehicle and the left lane boundary will be small, while the distance between the vehicle and the right lane boundary will gradually increase and increase to the lane width threshold or encounter The new lane line, so when the first distance changes: the distance between the vehicle and the left lane boundary changes less, the second distance change is: the distance between the vehicle and the right lane boundary gradually increases, and increases to the lane width threshold or When a new lane line is encountered, it can be more accurately judged that the right lane is divided.

In a possible design, if the first distance change still satisfies: the difference between the fifth distance and the second distance is less than the first threshold, the second distance change also satisfies: the sixth distance is less than the fourth distance, and the sixth distance is less than the fourth distance. The difference between the distance and the fourth distance is greater than the second threshold, it is determined that the lane on the right side of the first lane is merged into the first lane; wherein, the multiple time points also include the third time point, and the third time point is in the second After the time point, the fifth distance is the distance between the vehicle and the left lane boundary at the third time point, and the sixth distance is the distance between the vehicle and the right lane boundary at the third time point.

In the above embodiment, when the lane is joined to the right, the distance between the vehicle and the left lane boundary changes little, and the distance between the vehicle and the right lane boundary suddenly increases, and then gradually decreases to the lane width, so when the first lane The first distance change is: the distance between the vehicle and the left lane boundary changes less, the second distance change is that the distance between the vehicle and the right lane boundary suddenly increases, and then gradually decreases to the lane width, then the right lane can be judged more accurately. Hedao.

In a possible design, when judging the lane change based on the first distance change and the second distance change, if the first distance change satisfies: the first distance is less than the second distance, and the difference between the first distance and the second distance If the value is greater than the second threshold, the second distance change satisfies: the difference between the third distance and the fourth distance is less than the first threshold, then it is determined that the left side of the first lane has changed, and the first lane is the lane where the vehicle is located; The multiple time points include a first time point and a second time point. The first time point is before the second time point. The first distance is the distance between the vehicle at the first time point and the left lane boundary, and the second distance is the vehicle at the The distance between the second time point and the left lane boundary, the third distance is the distance between the vehicle and the right lane boundary at the first time point, and the fourth distance is the distance between the vehicle and the right lane boundary at the second time point.

Because when the left side of the lane changes, the distance between the vehicle and the right lane boundary changes less, and the distance between the vehicle and the left lane boundary changes more, so the change in the distance between the vehicle and the left and right lane boundaries can be more accurate judgments The direction in which the lane structure changes.

In a possible design, if the first distance change also satisfies: the fifth distance is greater than the second distance, and the difference between the fifth distance and the second distance is greater than the second threshold, the second distance change also satisfies: The difference between the sixth distance and the fourth distance is less than the first threshold, then it is determined that a new lane is added to the left of the first lane; wherein, the multiple time points also include the third time point, and the third time point is at the second time point After that, the fifth distance is the distance between the vehicle and the left lane boundary at the third time point, and the sixth distance is the distance between the vehicle and the right lane boundary at the third time point.

In the above embodiment, due to the left lane separation, the distance between the vehicle and the right lane boundary changes little, while the distance between the vehicle and the left lane boundary will gradually increase and increase to the lane width threshold or encounter The new lane line, so when the second distance changes: the distance between the vehicle and the right lane boundary changes less, the first distance change is that the distance between the vehicle and the left lane boundary gradually increases, and increases to the lane width threshold or When encountering a new lane line, it can be more accurately judged that the left lane is divided.

In a possible design, if the first distance change also satisfies: the fifth distance is less than the second distance, and the difference between the fifth distance and the second distance is greater than the second threshold, the second distance change also satisfies: If the difference between the sixth distance and the fourth distance is less than the first threshold, it is determined that the lane on the left side of the first lane will be merged into the first lane; wherein, the multiple time points also include the third time point, and the third time point is at After the second time point, the fifth distance is the distance between the vehicle and the left lane boundary at the third time point, and the sixth distance is the distance between the vehicle and the right lane boundary at the third time point.

In the above embodiment, when the lane is joined to the left, the distance between the vehicle and the right lane boundary changes little, and the distance between the vehicle and the left lane boundary suddenly increases, and then gradually decreases to the lane width. The second distance change is: the distance between the vehicle and the right lane boundary changes slightly, the first distance change is: the distance between the vehicle and the left lane boundary suddenly increases, and then gradually decreases to the lane width, then the occurrence lane can be judged more accurately Left Hedao.

In a possible design, when judging the lane change based on the first distance change and the second distance change, if the first distance change satisfies: the first distance is greater than the second distance, and the difference between the first distance and the second distance is greater than The third threshold, the second distance change satisfies: the fourth distance is greater than the third distance, and the difference between the fourth distance and the third distance is greater than the fourth threshold, it is determined that the first lane is merged with the second lane to the right, and the first The lane is the lane where the vehicle is located, and the second lane is the lane on the right side of the first lane; among them, at least two time points include the first time point and the second time point, the first time point is before the second time point, and the first time point is before the second time point. The distance is the distance between the vehicle and the left lane boundary at the first time point, the second distance is the distance between the vehicle and the left lane boundary at the second time point, and the third distance is the distance between the vehicle and the right lane boundary at the first time point. Distance, the fourth distance is the distance between the vehicle and the right lane boundary at the second time point.

When the lane merges with the lane to the right, the distance between the vehicle and the right lane boundary gradually changes, while the distance between the vehicle and the left lane boundary gradually decreases, so the change in the distance between the vehicle and the left and right lane boundary can be Judge the direction of the lane structure change more accurately.

In a possible design, if the first distance change still satisfies: the fifth distance is less than the second distance, and the difference between the fifth distance and the second distance is greater than the third threshold, the second distance change still satisfies: the sixth distance If the difference between the fourth distance and the fourth distance is less than the first threshold, it is determined that the first lane is merged into the second lane; wherein the multiple time points also include the third time point, the third time point is after the second time point, and the fifth distance Is the distance between the vehicle and the left lane boundary at the third time point, and the sixth distance is the distance between the vehicle and the right lane boundary at the third time point.

In the above embodiment, when the first lane is merged into the right lane, the distance between the vehicle and the left lane boundary gradually decreases, and the distance between the vehicle and the right lane boundary increases and the change becomes smaller. Therefore, if the first distance The change is that the distance between the vehicle and the left lane boundary gradually decreases, and the second distance change is that the distance between the vehicle and the right lane boundary increases and the change is small, and it can be more accurately judged that the left lane will merge to the right.

In a possible design, if the first distance change still satisfies: the fifth distance is less than the second distance, and the difference between the fifth distance and the second distance is greater than the third threshold, the second distance change still satisfies: the sixth distance Is less than the fourth distance, and the difference between the sixth distance and the fourth distance is greater than the fifth threshold, it is determined that the first lane and the second lane are merged into the third lane, and the third lane is on the right side of the first lane and at The left side of the second lane; where the multiple time points also include the third time point, the third time point is after the second time point, and the fifth distance is the distance between the vehicle at the third time point and the left lane boundary, and the first The six distance is the distance between the vehicle and the right lane boundary at the third time point.

In the above embodiment, when the lane and the right lane are merged into one lane, the distance between the vehicle and the left lane boundary gradually decreases, and the distance between the vehicle and the right lane boundary suddenly increases and then gradually decreases. The first distance change is: the distance between the vehicle and the left lane boundary gradually decreases, and the second distance change is that the distance between the vehicle and the right lane boundary suddenly increases and then gradually decreases. It can be more accurately judged that the vehicle merges into one through the left lane On the driveway.

In a possible design, when judging the lane change based on the first distance change and the second distance change, if the first distance change satisfies: the second distance is greater than the first distance, and the difference between the second distance and the first distance is greater than The fourth threshold, the second distance change satisfies: the fourth distance is less than the third distance, and the difference between the fourth distance and the third distance is greater than the third threshold, then it is determined that the first lane is merged with the fourth lane to the left. The lane is the lane where the vehicle is located, and the fourth lane is the lane to the left of the first lane; among them, at least two time points include the first time point and the second time point, the first time point is before the second time point, and the first time point is before the second time point. The distance is the distance between the vehicle and the left lane boundary at the first time point, the second distance is the distance between the vehicle and the left lane boundary at the second time point, and the third distance is the distance between the vehicle and the right lane boundary at the first time point. Distance, the fourth distance is the distance between the vehicle and the right lane boundary at the second time point.

When the lane merges with the lane to the left, the distance between the vehicle and the left lane boundary gradually changes, and the distance between the vehicle and the right lane boundary gradually decreases. Therefore, the change in the distance between the vehicle and the left and right lane boundary can be Judge the direction of the lane structure change more accurately.

In a possible design, if the first distance change still satisfies: the difference between the fifth distance and the second distance is less than the first threshold, the second distance change still satisfies: the sixth distance is less than the fourth distance, and the sixth distance If the difference between the fourth distance and the fourth distance is greater than the third threshold, it is determined that the first lane is merged into the fourth lane; wherein, the multiple time points also include the third time point, the third time point is after the second time point, and the fifth distance Is the distance between the vehicle and the left lane boundary at the third time point, and the sixth distance is the distance between the vehicle and the right lane boundary at the third time point.

In the above embodiment, when the left lane merges to the left, the distance between the vehicle and the right lane boundary gradually decreases, and the distance between the vehicle and the left lane boundary increases and the change is small. Therefore, the first distance changes Because the distance between the vehicle and the right lane boundary gradually decreases, and the second distance change is that the distance between the vehicle and the left lane boundary increases and the change is small, it can be accurately judged that the left lane will merge to the left.

In a possible design, if the first distance change also satisfies: the fifth distance is less than the second distance, and the difference between the fifth distance and the second distance is greater than the fifth threshold, the second distance change also satisfies: If the sixth distance is less than the fourth distance, and the difference between the sixth distance and the fourth distance is greater than the third threshold, it is determined that the first lane and the fourth lane are merged into the fifth lane, and the fifth lane is on the left side of the first lane and in The right side of the fourth lane; where the multiple time points also include the third time point, the third time point is after the second time point, and the fifth distance is the distance between the vehicle at the third time point and the left lane boundary, and the first The six distance is the distance between the vehicle and the right lane boundary at the third time point.

In the above embodiment, when the lane and the left lane are merged into the same lane, the distance between the vehicle and the right lane boundary gradually decreases, and the distance between the vehicle and the left lane boundary increases and then gradually decreases. The distance change is that the distance between the vehicle and the right lane boundary gradually decreases, and the second distance change is that the distance between the vehicle and the left lane boundary increases and then gradually decreases. It can be more accurately judged that the vehicle merges into a lane through the right lane.

In a possible design, when judging the lane change based on the first distance change and the second distance change, if the first distance change satisfies: the second distance is greater than the first distance, and the difference between the second distance and the first distance If the value is greater than the sixth threshold, the second distance change satisfies: the fourth distance is greater than the third distance, and the difference between the fourth distance and the third distance is greater than the seventh threshold, then it is judged that the first lane has a road separation, the first lane Is the lane where the vehicle is located; wherein, at least two time points include the first time point and the second time point, the first time point is before the second time point, and the first distance is the boundary between the vehicle at the first time point and the left lane The second distance is the distance between the vehicle and the left lane boundary at the second time point, the third distance is the distance between the vehicle and the right lane boundary at the first time point, and the fourth distance is the distance between the vehicle and the left lane boundary at the second time point. The distance of the right lane boundary.

In the above implementation, in the case of lane separation, the distance between the vehicle and the left lane boundary and the distance between the vehicle and the right lane boundary gradually increase to the width of the lane or there is a new lane line, so if the first distance Changes to the distance between the vehicle and the left lane boundary and the distance between the vehicle and the right lane boundary gradually increase to the width of the lane or there is a new lane line, which can indicate that the lane is separated from the road.

In a possible design, before obtaining the location information corresponding to the vehicle at least two points in time, it can be determined that the change in the distance between the historical driving trajectory of the vehicle within the preset time range and the lane boundary is within the preset range . In the above method, the vehicle trajectory is greatly affected by the vehicle attitude information. When the distance difference is relatively large, the vehicle may already be at a changing position of the road structure or changing lanes by itself. By judging that the vehicle trajectory is parallel or parallel to the lane boundary. When the lane structure is approximately parallel, the judgment of the subsequent lane structure can improve the accuracy of the lane structure judgment.

In a possible design, when acquiring the lane boundary information, the data collected by the sensor can be acquired; based on the data collected by the sensor, the lane boundary information in the driving environment is acquired. Through the above design, the lane boundary information can be accurately obtained.

In a second aspect, the present application provides a lane structure detection device, which has the function of realizing any one of the possible designs of the first aspect and the first aspect. The function can be realized by hardware, or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above-mentioned functions.

In the third aspect, the present application provides an electronic device, including: a processor and a memory. The memory is used to store computer-executable instructions. When the electronic device is running, the processor executes the computer-executable instructions stored in the memory, so that the device executes the method according to the first aspect or any one of the first aspects.

In a fourth aspect, a computer storage medium is provided, and a computer program is stored, and the computer program includes instructions for executing the methods of the foregoing aspects.

In a fifth aspect, a computer program product containing instructions is provided, which when run on a computer, causes the computer to execute the methods described in the above aspects.

In a sixth aspect, the present application provides a chip, which is coupled with a memory, and is used to read and execute the program instructions stored in the memory, so as to realize the above-mentioned first aspect or any one of the possibilities of the first aspect. The method described in the design.

Description of the drawings

FIG. 1 is a schematic flowchart of a method for detecting a lane structure according to an embodiment of the application;

2 is a schematic diagram of a lane structure detection process provided by an embodiment of the application;

FIG. 3 is a schematic diagram of another lane structure detection process provided by an embodiment of the application;

FIG. 4 is a schematic diagram of a lane structure provided by an embodiment of the application;

FIG. 5 is a schematic diagram of a lane structure provided by an embodiment of the application;

FIG. 6 is a schematic diagram of a lane structure provided by an embodiment of the application;

FIG. 7 is a schematic diagram of a lane structure provided by an embodiment of the application;

FIG. 8 is a schematic diagram of a lane structure provided by an embodiment of the application;

FIG. 9 is a schematic diagram of a lane structure provided by an embodiment of the application;

FIG. 10 is a schematic diagram of a lane structure provided by an embodiment of the application;

FIG. 11 is a schematic diagram of a lane structure provided by an embodiment of the application;

FIG. 12 is a schematic diagram of a lane structure provided by an embodiment of the application;

FIG. 13 is a schematic diagram of a lane structure provided by an embodiment of the application;

FIG. 14 is a schematic diagram of a lane structure provided by an embodiment of the application;

15 is a schematic structural diagram of a lane structure detection device provided by an embodiment of the application;

FIG. 16 is a schematic structural diagram of a lane structure detection device provided by an embodiment of the application.

Detailed ways

In order to make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present application.

With the advent of smart driving, smart cars have become the key research targets of major manufacturers.

Intelligent driving includes assisted driving and automatic driving. The key technologies for its realization include: perception and positioning, planning and decision-making (such as path planning, motion planning, etc.), executive control, and so on. For example, in autonomous driving and assisted driving, smart vehicles need to perceive the surrounding environment. In smart vehicles, the typical sensors used include millimeter wave radar, cameras, and lidar. The vehicle can detect and classify the environment around the vehicle through these sensors, and transmit this information to the planning and control module to form a pair The decision of the vehicle's future travel path is finally executed by the actuator, completing the entire process of assisted driving or automatic driving.

In the driving road, the separation and merging of roads often indicate changes in the road structure. At the same time, it is also accompanied by the occurrence of vehicle lane changes, which poses a certain safety risk. Therefore, in the driving process, the merger or separation of roads has a very important impact on driving decision-making, and it needs to be detected in advance.

At present, it is possible to obtain lane structure information through high-precision maps, and obtain information on the separation and merging of lane lines. However, the high-precision map has a certain degree of coverage. When the vehicle travels to an area without a high-precision map, the road structure cannot be obtained, and the information of the lane line merge point and separation point cannot be known. At the same time, high-precision maps still have the problem of failure. Due to urban renewal or construction, the map data after a certain period of time may be invalid, resulting in vehicles unable to obtain accurate lane structure information.

Based on this, the embodiments of the present application provide a lane structure detection method and device, which can obtain more accurate lane structure information, thereby improving the safety of automatic driving or assisted driving. Among them, the method and the device are based on the same concept. Since the principles of the method and the device to solve the problem are similar, the implementation of the device and the method can be referred to each other, and the repetition will not be repeated.

The lane structure detection method provided by the embodiment of the present application is applied to an electronic device, and the electronic device can be applied to a vehicle, especially a smart car. Vehicles can include, but are not limited to, millimeter wave radar, lidar, ultrasonic radar, cameras, positioning systems such as global positioning system (GPS), inertial measurement unit (IMU), speed sensor, acceleration sensor, humidity sensor , Light intensity sensors, microphones and other sensors, can also include display screens, external power amplifiers, speakers and other playback devices. It can also include other devices, which will not be listed here.

Exemplarily, the electronic device may be a vehicle-mounted controller.

The lane structure detection method provided by the embodiments of the present application can be applied to automatic driving scenarios, and can also be extended to manual driving scenarios.

It should be understood that in the embodiments of the present application, "at least one" refers to one or more, and "multiple" refers to two or more than two. "And/or" describes the association relationship of the associated object, indicating that there can be three relationships, for example, A and/or B, which can mean: A alone exists, A and B exist at the same time, and B exists alone, where A, B can be singular or plural. The character "/" generally indicates that the associated objects before and after are in an "or" relationship. "The following at least one (item)" or similar expressions refers to any combination of these items, including any combination of a single item (a) or a plurality of items (a). For example, at least one of a, b, or c can mean: a, b, c, a and b, a and c, b and c, or a, b and c, where a, b, c It can be single or multiple.

It should be understood that in the description of this application, words such as "first" and "second" are only used for the purpose of distinguishing the description, and cannot be understood as indicating or implying relative importance, nor can it be understood as indicating or implying order.

The embodiments of the present application will be described in detail below in conjunction with the accompanying drawings.

1 is a flowchart of a method for detecting a lane structure according to an embodiment of this application. The method is executed by an electronic device or a chip or chipset in the electronic device. The electronic device may be a vehicle-mounted controller. The vehicle controller may include a functional module for acquiring the lane structure, or the electronic device may also be a device independent of the on-board controller for acquiring the lane structure. The method may specifically include the following:

S101: Acquire lane boundary information, where the lane boundary information includes position information of the left lane boundary and the right lane boundary.

Exemplarily, the lane boundary may include, but is not limited to: lane lines, road shoulders, curbs, flower beds on both sides of the road, flower beds in the middle of the road, or other objects that divide the lane.

In a possible implementation manner, acquiring lane boundary information can be achieved through the following process: acquiring data collected by sensors; acquiring lane boundary information in a driving environment based on the data collected by sensors.

For example, the data collected by the camera sensor can be obtained, and the lane boundary information in the driving environment can be obtained.

An alternative method is to obtain lane boundary information in the image through gradient threshold or color threshold, including lane line information and road boundary information; another alternative method is to use machine learning methods through pre-training The lane boundary neural network model or other data model detects the lane information in the image to obtain lane boundary information, including lane line information and road boundary information. More specifically, after obtaining the characteristic points of the lane information, the lane boundary equation can be obtained by methods such as fitting and tracking.

One way to describe the lane boundary equation is:

y(x)=C0+C1x+C2x ² +C3x ³

Among them, C0 is the lateral offset of the lane boundary, C1 is the heading angle of the lane boundary, C2 is the average curvature of the lane boundary twice, and C3 is the average curvature change rate of the lane boundary 6 times.

Alternatively, sensor data such as millimeter wave radar and lidar can also be obtained to obtain lane boundary information. An optional method is to obtain the reflection information of the road boundary, such as guardrail, and process it to obtain the road boundary information, which can also be used as part of the lane information.

For another example, the final lane boundary information can also be output by fusing the results of multiple sensors, for example, fusing data collected by camera sensors, millimeter wave radar and other sensor data to output the final lane boundary information.

S102: Acquire location information corresponding to the vehicle at at least two points in time, respectively.

In an implementation manner, the driving trajectory of the vehicle may be acquired, and the position information corresponding to at least two time points may be determined according to the driving trajectory. Wherein, the at least two points in time may be points in the future, and can also be understood as determining the location information corresponding to at least two points in the future according to the trajectory of the vehicle.

The driving trajectory of the vehicle can be determined in the following manner: by acquiring the data collected by the vehicle sensor and the data collected by the camera, the driving trajectory of the vehicle is determined according to the data collected by the sensor and the amount data collected by the camera.

In an exemplary illustration, the time interval between any two adjacent time points in the at least two time points may be the same. For example, set a time point every 0.5s.

In one implementation, the time interval between two adjacent time points can be set according to the driving speed of the vehicle. For example, the greater the speed of the vehicle, the smaller the time interval between two adjacent points in time. Exemplarily, when the driving speed of the vehicle is greater than 100KM/h, a time point can be set every 0.2s, that is, the interval between two adjacent time points is 0.2s. When the driving speed of the vehicle is [50KM/h, 100KM/h), a time point can be set every 0.4s, that is, the interval between two adjacent time points is 0.4s. For another example, the greater the traveling speed of the vehicle, the greater the time interval between two adjacent time points.

In another exemplary illustration, the driving distance between any two adjacent time points in the at least two time points may be the same.

In an implementation manner, the driving distance between two adjacent time points can be set according to the driving speed of the vehicle. For example, the greater the traveling speed of the vehicle, the greater the traveling distance between two adjacent points in time. Exemplarily, when the driving speed of the vehicle is greater than 100KM/h, the driving distance between two adjacent time points may be 100m. When the driving speed of the vehicle is [50KM/h, 100KM/h), the driving distance between two adjacent time points can be 50m.

For another example, the greater the traveling speed of the vehicle, the smaller the traveling distance between two adjacent points in time.

S103: For each time point, the distance between the vehicle and the left lane boundary and the right lane boundary may be determined according to the position information of the vehicle at the time point.

In one implementation, the distance can be calculated in different coordinate systems, such as using pixel values to describe, or using actual distance length to describe.

S104: Determine the first distance change between the vehicle and the left lane boundary at at least two time points and the second distance change between the vehicle and the right lane boundary at at least two time points.

Exemplarily, the first distance change may be the distance difference between the vehicle and the left lane boundary at two adjacent time points. The second distance change may be the distance difference between the vehicle and the right lane boundary at two adjacent time points.

For example, taking two time points t1 and t2 as an example, suppose that the distance between the vehicle and the left lane boundary at time t1 is L _{(1, L)} , and the distance between the vehicle and the left lane boundary at time t2 is L _{( 2, L)} . The distance between the vehicle and the right lane boundary at time t1 is L _{(1, R)} , and the distance between the vehicle and the right lane boundary at time t2 is L _{(2, R)} . Then, the first distance change can be the distance difference between the vehicle and the left lane boundary at t1 and t2, that is, L _{(2, L)} -L _{(1, L)} . The second distance change can be the distance difference between the vehicle and the right lane boundary at t1 and t2, that is, L _{(2, R)} -L _{(1, R)} .

For another example, taking three time points t1, t2, and t3 as an example, suppose that the distance between the vehicle and the left lane boundary at time t1 is L _{(1, L)} , and the distance between the vehicle and the left lane boundary at time t2 Is L _{(2, L)} , the distance between the vehicle and the left lane boundary at time t3 is L _{(3, L)} . The distance between the vehicle and the right lane boundary at t1 is L _{(1, R)} , the distance between the vehicle and the right lane boundary at t2 is L _{(2, R)} , and the vehicle is at the right lane boundary at t3 The distance is L _{(3, R)} . Then, the first distance change may include Δ _{(1, L)} = L _{(2, L)} -L _{(1, L)} , Δ _{(2, L)} = L _{(3, L)} -L _{(2, L)} . The second distance change may include Δ _(1,R) =L _(2,R) -L _(1,R) , Δ _(2,R) =L _(3,R) -L _(2,R) .

S105: Determine the lane change based on the first distance change and the second distance change.

Because different road lane structures have different lane distance changes, the lane structure can be judged according to the different measured distance changes. For example, a lane structure keeps one side unchanged while the other side changes from small to large; for example, one The lane structure remains unchanged on one side, suddenly becomes larger on the other side, and then gradually becomes smaller; for another example, there are other ways to change the distance to correspond to different lane structures. Further, the information of adjacent lanes can be combined to output different lane structures, such as road merging or separation, left-division road, right-division road, etc., for subsequent regulation and control. Exemplarily, the lane structure detection process may be as shown in FIG. 2 or FIG. 3.

In the embodiment of the present application, the change of the lane structure is judged according to the change of the distance between the vehicle and the lane boundary. Compared with the way of obtaining the lane structure change through the high-precision map, the embodiment of the present application can realize the complete detection of the road structure, so as to inform The lane structure of the road environment ahead helps intelligent vehicles to conduct risk analysis and path planning in advance in a combined or separated road structure environment, and improve driving safety.

In some embodiments, step S104 may be implemented in any one of the following seven implementation manners:

In the first implementation manner, if the first distance change satisfies: the difference between the first distance and the second distance is less than the first threshold, the second distance change satisfies: the third distance is less than the fourth distance, and the third distance is less than the If the difference between the fourth distance is greater than the second threshold, it can be determined that the right side of the first lane has changed, and the first lane is the lane where the vehicle is located. Wherein, at least two time points include a first time point and a second time point, the first time point is before the second time point, the first distance is the distance between the vehicle at the first time point and the left lane boundary, and the second distance Is the distance between the vehicle and the left lane boundary at the second time point, the third distance is the distance between the vehicle and the right lane boundary at the first time point, and the fourth distance is the distance between the vehicle and the right lane boundary at the second time point . Exemplarily, the first threshold may be smaller than the second threshold.

For example, taking two time points t1 and t2 as an example, suppose that the distance between the vehicle and the left lane boundary at time t1 is L _{(1, L)} , and the distance between the vehicle and the left lane boundary at time t2 is L _{( 2, L)} . The distance between the vehicle and the right lane boundary at time t1 is L _{(1, R)} , and the distance between the vehicle and the right lane boundary at time t2 is L _{(2, R)} . If, |L _(2,L) -L _{(1, L)} |<ΔL1, L _(1,R) <L _(2,R) and L _(2,R) -L _(1,R) >ΔL2, It can be judged that the right side of the first lane has changed, and the first lane is the lane where the vehicle is located. Exemplarily, ΔL1 may be smaller than ΔL3.

In a specific embodiment, after determining that the lane change is a change on the right side of the first lane, if the first distance change is still satisfied: the difference between the fifth distance and the second distance is less than the first threshold, and the second distance changes It is also satisfied that: the sixth distance is greater than four distances, and the difference between the sixth distance and the fourth distance is greater than the second threshold, it can be determined that a new lane is added to the right of the first lane. Among them, the multiple time points also include a third time point, the third time point is after the second time point, the fifth distance is the distance between the vehicle at the third time point and the left lane boundary, and the sixth distance is the vehicle at the third time point. The distance between the time point and the right lane boundary.

For example, taking three time points t1, t2, and t3 as an example, suppose that the distance between the vehicle and the left lane boundary at time t1 is L _{(1, L)} , and the distance between the vehicle and the left lane boundary at time t2 is L _{(2, L)} , the distance between the vehicle and the left lane boundary at time t3 is L _{(3, L)} . The distance between the vehicle and the right lane boundary at t1 is L _{(1, R)} , the distance between the vehicle and the right lane boundary at t2 is L _{(2, R)} , and the vehicle is at the right lane boundary at t3 The distance is L _{(3, R)} .

If, |L _(2,L) -L _(1,L) |＜ΔL1, |L _(3,L) -L _(2,L) |＜ΔL1, L _(1,R) ＜L _{(2,R) )} , L _(2,R) <L _{(3, R)} and L _(2,R) -L _(1,R) ＞ΔL2, L _(3,R) -L _(2,R) ＞ΔL2, it can be judged A new lane is added to the right of the first lane, and the first lane is the lane where the vehicle is located, for example, as shown in Figure 4.

In the above embodiment, the first distance change is: the distance between the vehicle and the left lane boundary changes slightly, and the second distance change is: the distance between the vehicle and the right lane boundary gradually increases, and increases to the lane width threshold or meets When the new lane line is reached, it can be judged that the lane divides to the right.

In another specific embodiment, after judging that the lane change is a change on the right side of the first lane, if the first distance change still satisfies: the difference between the fifth distance and the second distance is less than the first threshold, and the second The distance change also satisfies: the sixth distance is less than four distances, and the difference between the sixth distance and the fourth distance is greater than the second threshold, it can be judged that the lane on the right side of the first lane merges into the first lane; The time point also includes the third time point, the third time point is after the second time point, the fifth distance is the distance between the vehicle at the third time point and the left lane boundary, and the sixth distance is the distance between the vehicle and the right lane at the third time point. The distance of the side lane boundary.

For example, taking three time points t1, t2, and t3 as an example, suppose that the distance between the vehicle and the left lane boundary at time t1 is L _{(1, L)} , and the distance between the vehicle and the left lane boundary at time t2 is L _{(2, L)} , the distance between the vehicle and the left lane boundary at time t3 is L _{(3, L)} . The distance between the vehicle and the right lane boundary at t1 is L _{(1, R)} , the distance between the vehicle and the right lane boundary at t2 is L _{(2, R)} , and the vehicle is at the right lane boundary at t3 The distance is L _{(3, R)} .

If, |L _(2,L) -L _(1,L) |＜ΔL1, |L _(3,L) -L _(2,L) |＜ΔL1, L _(1,R) ＜L _{(2,R) )} , L _(2,R) ＞L _{(3, R)} and L _(2,R) -L _(1,R) ＞ΔL2, L _(2,R) -L _(3,R) ＞ΔL2, it can be judged The lane on the right side of the first lane is merged into the first lane, and the first lane is the lane where the vehicle is located, for example, as shown in FIG. 5.

In the above embodiment, the first distance change is: the distance between the vehicle and the left lane boundary changes less, and the second distance change is that the distance between the vehicle and the right lane boundary suddenly increases, and then gradually decreases to the lane width, it can be judged The right lane of the incident occurred.

In the second implementation manner, if the first distance change satisfies: the first distance is less than the second distance, and the difference between the first distance and the second distance is greater than the second threshold, the second distance change satisfies: If the difference between the fourth distance is less than the first threshold, it is determined that the left side of the first lane has changed, and the first lane is the lane where the vehicle is located; wherein the multiple time points include the first time point and the second time point, and the first A time point is before the second time point, the first distance is the distance between the vehicle and the left lane boundary at the first time point, the second distance is the distance between the vehicle and the left lane boundary at the second time point, and the third distance is The distance between the vehicle and the right lane boundary at the first time point, and the fourth distance is the distance between the vehicle and the right lane boundary at the second time point.

For example, taking two time points t1 and t2 as an example, suppose that the distance between the vehicle and the left lane boundary at time t1 is L _{(1, L)} , and the distance between the vehicle and the left lane boundary at time t2 is L _{( 2, L)} . The distance between the vehicle and the right lane boundary at time t1 is L _{(1, R)} , and the distance between the vehicle and the right lane boundary at time t2 is L _{(2, R)} . If, |L _(2,R) -L _{(1, R)} |<ΔL1, L _(1,L) <L _(2,L) and L _(2,L) -L _(1,L) >ΔL2, It can be judged that the left side of the first lane has changed, and the first lane is the lane where the vehicle is located.

In a specific implementation, after determining that the left side of the first lane has changed, if the first distance change is still satisfied: the fifth distance is greater than the second distance, and the difference between the fifth distance and the second distance is greater than the first distance. Second threshold, the second distance change is still satisfied: the difference between the sixth distance and the fourth distance is less than the first threshold, then it is determined that a new lane is added to the left of the first lane. Among them, the multiple time points also include a third time point, the third time point is after the second time point, the fifth distance is the distance between the vehicle at the third time point and the left lane boundary, and the sixth distance is the vehicle at the third time point. The distance between the time point and the right lane boundary.

For example, taking three time points t1, t2, and t3 as an example, suppose that the distance between the vehicle and the left lane boundary at time t1 is L _{(1, L)} , and the distance between the vehicle and the left lane boundary at time t2 is L _{(2, L)} , the distance between the vehicle and the left lane boundary at time t3 is L _{(3, L)} . The distance between the vehicle and the right lane boundary at t1 is L _{(1, R)} , the distance between the vehicle and the right lane boundary at t2 is L _{(2, R)} , and the vehicle is at the right lane boundary at t3 The distance is L _{(3, R)} .

If, |L _(2,R) -L _(1,R) |＜ΔL1, |L _(3,R) -L _(2,R) |＜ΔL1, L _(1,L) ＜L _{(2,L )} , L _(2,L) <L _{(3, L)} and L _(2,L) -L _(1,L) ＞ΔL2, L _(3,L) -L _(2,L) ＞ΔL2, it can be judged A new lane is added to the left of the first lane, and the first lane is the lane where the vehicle is located, for example, as shown in Figure 6.

In the above embodiment, the second distance change is: the distance between the vehicle and the right lane boundary changes slightly, and the first distance change is that the distance between the vehicle and the left lane boundary gradually increases and increases to the lane width threshold or encounters With the new lane line, it can be judged that the left lane is divided.

In another possible implementation manner, after determining that the left side of the first lane has changed, if the first distance change still satisfies: the fifth distance is less than the second distance, and the difference between the fifth distance and the second distance is greater than The second threshold, the second distance change also satisfies: the difference between the sixth distance and the fourth distance is less than the first threshold, it can be judged that the lane on the left side of the first lane will be merged into the first lane; where, multiple times The point also includes the third time point, the third time point is after the second time point, the fifth distance is the distance between the vehicle at the third time point and the left lane boundary, and the sixth distance is the vehicle at the third time point to the right The distance of the lane boundary.

For example, taking three time points t1, t2, and t3 as an example, suppose that the distance between the vehicle and the left lane boundary at time t1 is L _{(1, L)} , and the distance between the vehicle and the left lane boundary at time t2 is L _{(2, L)} , the distance between the vehicle and the left lane boundary at time t3 is L _{(3, L)} . The distance between the vehicle and the right lane boundary at t1 is L _{(1, R)} , the distance between the vehicle and the right lane boundary at t2 is L _{(2, R)} , and the vehicle is at the right lane boundary at t3 The distance is L _{(3, R)} .

If, |L _(2,R) -L _(1,R) |＜ΔL1, |L _(3,R) -L _(2,R) |＜ΔL1, L _(1,L) ＜L _{(2,L )} , L _(2,L) ＞L _{(3, L)} and L _(2,L) -L _(1,L) ＞ΔL2, L _(2,L) -L _(3,L) ＞ΔL2, it can be judged The left lane of the first lane is merged into the first lane, and the first lane is the lane where the vehicle is located, for example, as shown in FIG. 7.

In the above embodiment, the second distance change is: the distance between the vehicle and the right lane boundary changes slightly, and the first distance change is: the distance between the vehicle and the left lane boundary suddenly increases, and then gradually decreases to the lane width, then Judge the left side of the lane.

In the third implementation manner, if the first distance change satisfies: the first distance is greater than the second distance, and the difference between the first distance and the second distance is greater than the third threshold, the second distance change satisfies: the fourth distance is greater than the third Distance, and the difference between the fourth distance and the third distance is greater than the fourth threshold, it is determined that the first lane to the right is merged with the second lane, the first lane is the lane where the vehicle is located, and the second lane is the right side of the first lane Where at least two time points include a first time point and a second time point, the first time point is before the second time point, and the first distance is the distance between the vehicle at the first time point and the left lane boundary, The second distance is the distance between the vehicle and the left lane boundary at the second time point, the third distance is the distance between the vehicle and the right lane boundary at the first time point, and the fourth distance is the vehicle and the right lane boundary at the second time point. The distance of the border.

For example, taking two time points t1 and t2 as an example, suppose that the distance between the vehicle and the left lane boundary at time t1 is L _{(1, L)} , and the distance between the vehicle and the left lane boundary at time t2 is L _{( 2, L)} . The distance between the vehicle and the right lane boundary at time t1 is L _{(1, R)} , and the distance between the vehicle and the right lane boundary at time t2 is L _{(2, R)} . If, L _(2,L) <L _{(1, L)} , L _(1,L) -L _(2,L) >ΔL3, L _(1,R) <L _(2,R) and L _{(2, R)} -L _{(1, R)} > ΔL4, it can be judged that the first lane is merged with the second lane to the right, the first lane is the lane where the vehicle is located, and the second lane is the lane on the right side of the first lane.

In a specific embodiment, if the first distance change also satisfies: the fifth distance is less than the second distance, and the difference between the fifth distance and the second distance is greater than the third threshold, so The second distance change also satisfies: the difference between the sixth distance and the fourth distance is less than the first threshold, then it is determined that the first lane is merged into the second lane. Wherein, the multiple time points further include a third time point, the third time point is after the second time point, and the fifth distance is the distance between the vehicle and the left at the third time point. The distance of the side lane boundary, and the sixth distance is the distance between the vehicle and the right lane boundary at the third time point. Exemplarily, the fourth threshold may be greater than or equal to the width of the lane, or the fourth threshold may be less than or equal to the width of the lane.

For example, taking three time points t1, t2, and t3 as an example, suppose that the distance between the vehicle and the left lane boundary at time t1 is L _{(1, L)} , and the distance between the vehicle and the left lane boundary at time t2 is L _{(2, L)} , the distance between the vehicle and the left lane boundary at time t3 is L _{(3, L)} . The distance between the vehicle and the right lane boundary at t1 is L _{(1, R)} , the distance between the vehicle and the right lane boundary at t2 is L _{(2, R)} , and the vehicle is at the right lane boundary at t3 The distance is L _{(3, R)} .

If, L _(3,L) <L _(2,L) <L _(1,L) , L _(1,L) -L _(2,L) ＞ΔL3, L _(2,L) -L _{(3, L)} >ΔL3,L _(1,R) <L _(2,R) and L _(2,R) -L _(1,R) >ΔL4,L _(3,R) <L _(2,R) , yes It is determined that the first lane is merged into the second lane, as shown in FIG. 8.

In the above embodiment, the first distance change is that the distance between the vehicle and the left lane boundary gradually decreases, and the second distance change is that the distance between the vehicle and the right lane boundary increases and the change is small. Right Hedao.

In another specific embodiment, if the first distance change also satisfies: the fifth distance is less than the second distance, and the difference between the fifth distance and the second distance is greater than the third threshold, The second distance change also satisfies: the sixth distance is less than the fourth distance, and the difference between the sixth distance and the fourth distance is greater than the fifth threshold, then it is determined that the first lane and the The second lane is merged into a third lane, and the third lane is on the right side of the first lane and on the left side of the second lane; wherein, the multiple time points further include a third time point, The third time point is after the second time point, the fifth distance is the distance between the vehicle and the left lane boundary at the third time point, and the sixth distance is the vehicle The distance from the boundary of the right lane at the third time point.

For example, taking three time points t1, t2, and t3 as an example, suppose that the distance between the vehicle and the left lane boundary at time t1 is L _{(1, L)} , and the distance between the vehicle and the left lane boundary at time t2 is L _{(2, L)} , the distance between the vehicle and the left lane boundary at time t3 is L _{(3, L)} . The distance between the vehicle and the right lane boundary at t1 is L _{(1, R)} , the distance between the vehicle and the right lane boundary at t2 is L _{(2, R)} , and the vehicle is at the right lane boundary at t3 The distance is L _{(3, R)} .

If, L _(3,L) <L _(2,L) <L _(1,L) , L _(1,L) -L _(2,L) ＞ΔL3, L _(2,L) -L _{(3, L)} >ΔL3, L _(1,R) <L _(2,R) and L _(2,R) -L _(1,R) >ΔL4, L _(3,R) <L _(2,R) and L _{(2, R)} -L _{(3, R)} > ΔL5, it can be judged that the first lane and the second lane are merged into a third lane, and the third lane is on the right side of the first lane and at The left side of the second lane is as shown in FIG. 9.

In the above embodiment, the first distance change is: the distance between the vehicle and the left lane boundary gradually decreases, and the second distance change is that the distance between the vehicle and the right lane boundary suddenly increases and then gradually decreases. It can be determined that the vehicle passes through the left lane. Merge into one lane.

In the fourth implementation manner, if the first distance change satisfies: the second distance is greater than the first distance, and the difference between the second distance and the first distance is greater than the fourth threshold, the second distance change satisfies: the fourth distance is less than the third Distance, and the difference between the fourth distance and the third distance is greater than the third threshold, it is judged that the first lane to the left is merged with the fourth lane, the first lane is the lane where the vehicle is located, and the fourth lane is the left side of the first lane The lane; where at least two time points include a first time point and a second time point, the first time point is before the second time point, and the first distance is the distance between the vehicle at the first time point and the left lane boundary, The second distance is the distance between the vehicle and the left lane boundary at the second time point, the third distance is the distance between the vehicle and the right lane boundary at the first time point, and the fourth distance is the vehicle and the right lane boundary at the second time point. The distance of the border.

For example, taking two time points t1 and t2 as an example, suppose that the distance between the vehicle and the left lane boundary at time t1 is L _{(1, L)} , and the distance between the vehicle and the left lane boundary at time t2 is L _{( 2, L)} . The distance between the vehicle and the right lane boundary at time t1 is L _{(1, R)} , and the distance between the vehicle and the right lane boundary at time t2 is L _{(2, R)} . If, L _{(2, R)} <L _{(1, R)} , L _{(1,) R-} L _{(2, R)} > ΔL3, L _{(1, L)} <L _{(2, L)} and L _{(2, L)} -L _(1,L) > ΔL4, it can be judged that the first lane is merged with the fourth lane to the left, the first lane is the lane where the vehicle is located, and the fourth lane is the left lane of the first lane.

In a specific implementation, if the first distance change also satisfies: the difference between the fifth distance and the second distance is less than the first threshold, the second distance change also satisfies: the sixth distance is less than the If the fourth distance and the difference between the sixth distance and the fourth distance are greater than the third threshold, it is determined that the first lane is merged into the fourth lane. Wherein, the multiple time points further include a third time point, the third time point is after the second time point, and the fifth distance is the distance between the vehicle and the left at the third time point. The distance of the side lane boundary, and the sixth distance is the distance between the vehicle and the right lane boundary at the third time point.

For example, taking three time points t1, t2, and t3 as an example, suppose that the distance between the vehicle and the left lane boundary at time t1 is L _{(1, L)} , and the distance between the vehicle and the left lane boundary at time t2 is L _{(2, L)} , the distance between the vehicle and the left lane boundary at time t3 is L _{(3, L)} . The distance between the vehicle and the right lane boundary at t1 is L _{(1, R)} , the distance between the vehicle and the right lane boundary at t2 is L _{(2, R)} , and the vehicle is at the right lane boundary at t3 The distance is L _{(3, R)} .

If, L _(3,R) <L _(2,R) <L _(1,R) , L _(1,R) -L _(2,R) ＞ΔL3, L _(2,R) -L _{(3, R)} >ΔL3,L _(1,L) <L _(2,L) and L _(2,L) -L _(1,L) >ΔL4,L _(3,L) <L _(2,L) , yes It is determined that the first lane is merged into the second lane, as shown in FIG. 10.

In the above-mentioned embodiment, the first distance change means that the distance between the vehicle and the right lane boundary gradually decreases, and the second distance change means that the distance between the vehicle and the left lane boundary becomes larger and the change is smaller, which indicates that it will occur from the left lane. Hop left.

In another specific implementation manner, if the first distance change also satisfies: the fifth distance is less than the second distance, and the difference between the fifth distance and the second distance is greater than a fifth threshold , The second distance change also satisfies: the sixth distance is less than the fourth distance, and the difference between the sixth distance and the fourth distance is greater than the third threshold, then it is determined that the first lane is The fourth lane is merged into a fifth lane, and the fifth lane is on the left side of the first lane and on the right side of the fourth lane; wherein, the multiple time points further include a third time point , The third time point is after the second time point, the fifth distance is the distance between the vehicle and the left lane boundary at the third time point, and the sixth distance is the The distance between the vehicle and the right lane boundary at the third time point.

For example, taking three time points t1, t2, and t3 as an example, suppose that the distance between the vehicle and the left lane boundary at time t1 is L _{(1, L)} , and the distance between the vehicle and the left lane boundary at time t2 is L _{(2, L)} , the distance between the vehicle and the left lane boundary at time t3 is L _{(3, L)} . The distance between the vehicle and the right lane boundary at t1 is L _{(1, R)} , the distance between the vehicle and the right lane boundary at t2 is L _{(2, R)} , and the vehicle is at the right lane boundary at t3 The distance is L _{(3, R)} .

If, L _(3,R) <L _(2,R) <L _(1,R) , L _(1,R) -L _(2,R) ＞ΔL3, L _(2,R) -L _{(3, R)} ＞ΔL3, L _(1,L) ＜L _(2,L) and L _(2,L) -L _(1,L) ＞ΔL4, L _(3,L) ＜L _(2,L) and L _{(2, L)} -L _{(3, L)} > ΔL5, it can be judged that the first lane and the fourth lane are merged into the fifth lane, and the fifth lane is on the left side of the first lane and at The right side of the fourth lane is shown in Figure 11.

In the foregoing embodiment, when the first distance changes, the distance between the vehicle and the right lane boundary gradually decreases, and the distance between the vehicle and the left lane boundary increases and then gradually decreases. It can be determined that the vehicle merges into one lane through the right lane.

In the fifth implementation manner, if the first distance change satisfies: the second distance is greater than the first distance, and the difference between the second distance and the first distance is greater than the sixth threshold, the second distance change satisfies: the fourth distance is greater than The third distance, and the difference between the fourth distance and the third distance is greater than the seventh threshold, then it is determined that road separation occurs in the first lane, and the first lane is the lane where the vehicle is located; wherein, at least two time points include the first Time point and second time point, the first time point is before the second time point, the first distance is the distance between the vehicle at the first time point and the left lane boundary, and the second distance is the distance between the vehicle and the left side at the second time point The distance of the lane boundary, the third distance is the distance between the vehicle and the right lane boundary at the first time point, and the fourth distance is the distance between the vehicle and the right lane boundary at the second time point.

In the above implementation, if the first distance changes to the distance between the vehicle and the left lane boundary, and the distance between the vehicle and the right lane boundary gradually increases to the width of the lane or there is a new lane line, it can indicate that the lane is separated from the road. , As shown in Figure 12.

In the sixth implementation manner, if the second distance change satisfies: the difference between the fourth distance and the third distance is less than the sixth threshold, the difference between the fourth distance and the sixth distance is less than the first threshold, and the first The distance change satisfies: the second distance is less than the first distance, and the difference between the first distance and the second distance is greater than the seventh threshold, the fifth distance is less than the second distance, and the difference between the second distance and the fifth distance If the value is greater than the seventh threshold, it can be determined that a new lane is added to the left of the first lane. Wherein, at least two time points include a first time point, a second time point, and a third time point, the first time point is before the second time point, the second time point is before the third time point, and the first distance is the vehicle The distance from the left lane boundary at the first time point, the second distance is the distance between the vehicle and the left lane boundary at the second time point, and the fifth distance is the distance between the vehicle and the left lane boundary at the second time point. The third distance is the distance between the vehicle and the right lane boundary at the first time point, the fourth distance is the distance between the vehicle and the right lane boundary at the second time point, and the sixth distance is the vehicle and the right lane boundary at the third time point. the distance.

In the above implementation, if the second distance change is that the distance between the vehicle and the right lane boundary changes less, and the first distance change is that the distance between the vehicle and the left lane boundary is gradually reduced, and there is a new lane line on the left, you can It is judged that a lane is created on the left side of the occurrence lane, as shown in Figure 13.

In the seventh implementation manner, if the first distance change satisfies: the difference between the second distance and the first distance is less than the sixth threshold, the difference between the second distance and the fifth distance is less than the first threshold, and the second The distance change satisfies: the fourth distance is less than the third distance, and the difference between the third distance and the fourth distance is greater than the seventh threshold, the sixth distance is less than the fourth distance, and the difference between the fourth distance and the sixth distance If the value is greater than the seventh threshold, it can be determined that a new lane is added to the right of the first lane. Wherein, at least two time points include a first time point, a second time point, and a third time point, the first time point is before the second time point, the second time point is before the third time point, and the first distance is the vehicle The distance from the left lane boundary at the first time point, the second distance is the distance between the vehicle and the left lane boundary at the second time point, and the fifth distance is the distance between the vehicle and the left lane boundary at the second time point. The third distance is the distance between the vehicle and the right lane boundary at the first time point, the fourth distance is the distance between the vehicle and the right lane boundary at the second time point, and the sixth distance is the vehicle and the right lane boundary at the third time point. the distance.

In the above implementation, if the first distance change is that the distance between the vehicle and the left lane boundary changes less, and the first distance change is that the distance between the vehicle and the right lane boundary is gradually reduced, and there is a new lane line on the right, you can It is judged that a lane is created on the right side of the lane, as shown in Figure 14.

It is understandable that the embodiments of the present application are not limited to judging the lane structure through the above seven implementation methods. In specific implementation, the corresponding lane structure can also be judged based on the change in the distance between the vehicle and the lane boundary in other lane structures. I won't list them all here.

In some embodiments, before determining the change in the distance between the driving trajectory and the lane boundary, it may be determined that the change in the distance between the historical driving trajectory of the vehicle within a preset time range and the lane boundary is within a preset range. In the above method, the vehicle trajectory is greatly affected by the vehicle attitude information. When the distance difference is relatively large, the vehicle may already be at a changing position of the road structure or changing lanes by itself. By judging that the vehicle trajectory is parallel or parallel to the lane boundary. When the lane structure is approximately parallel, the judgment of the subsequent lane structure can improve the accuracy of the lane structure judgment.

Based on the same concept, an embodiment of the present invention also provides a lane structure detection device 150, which is specifically used to implement the methods described in the embodiments described in FIG. 1 to FIG. 14. The structure of the device is shown in FIG. 15 and includes: a communication unit 1501 and processing unit 1502. Wherein, the communication unit 1501 is configured to obtain lane boundary information, which includes the position information of the left lane boundary and the right lane boundary; the processing unit 1502 is configured to obtain corresponding position information of the vehicle at at least two points in time; And, for each time point, determine the distance between the vehicle and the left lane boundary and the right lane boundary according to the position information corresponding to the vehicle at the time point; and, determine the first distance between the vehicle and the left lane boundary at least two time points The distance change and the second distance change between the vehicle and the right lane boundary at at least two points in time; and, the lane change is judged based on the first distance change and the second distance change.

Exemplarily, the processing unit 1502, when judging the lane change based on the first distance change and the second distance change, is specifically configured to: if the first distance change satisfies: the difference between the first distance and the second distance is smaller than the first distance change. Threshold, the second distance change satisfies: the third distance is less than the fourth distance, and the difference between the third distance and the fourth distance is greater than the second threshold, then it is determined that the right side of the first lane has changed, and the first lane is where the vehicle is Lane

Wherein, at least two time points include a first time point and a second time point, the first time point is before the second time point, the first distance is the distance between the vehicle at the first time point and the left lane boundary, and the second distance Is the distance between the vehicle and the left lane boundary at the second time point, the third distance is the distance between the vehicle and the right lane boundary at the first time point, and the fourth distance is the distance between the vehicle and the right lane boundary at the second time point .

Further, the processing unit 1502 is further configured to: after judging that the lane change is a change on the right side of the first lane, if the first distance change still satisfies: the difference between the fifth distance and the second distance is less than the first threshold, The second distance change also satisfies: the sixth distance is greater than four distances, and the difference between the sixth distance and the fourth distance is greater than the second threshold, it is determined that a new lane is added to the right of the first lane;

Among them, the multiple time points also include a third time point, the third time point is after the second time point, the fifth distance is the distance between the vehicle at the third time point and the left lane boundary, and the sixth distance is the vehicle at the third time point. The distance between the time point and the right lane boundary.

Alternatively, the processing unit 1502 is further configured to: after judging that the lane change is a change on the right side of the first lane, if the first distance change still satisfies: the difference between the fifth distance and the second distance is less than the first threshold, The second distance change also satisfies: the sixth distance is less than four distances, and the difference between the sixth distance and the fourth distance is greater than the second threshold, then it is determined that the lane on the right side of the first lane is merged into the first lane;

Among them, the multiple time points also include a third time point, the third time point is after the second time point, the fifth distance is the distance between the vehicle at the third time point and the left lane boundary, and the sixth distance is the vehicle at the third time point. The distance between the time point and the right lane boundary.

Exemplarily, the processing unit 1502, when judging the lane change based on the first distance change and the second distance change, is specifically configured to: if the first distance change satisfies: the first distance is less than the second distance, and the first distance is less than the second distance The difference between the distances is greater than the second threshold, and the second distance change satisfies: the difference between the third distance and the fourth distance is less than the first threshold, then it is determined that the left side of the first lane has changed, and the first lane is where the vehicle is located Lane

The multiple time points include a first time point and a second time point. The first time point is before the second time point, the first distance is the distance between the vehicle at the first time point and the left lane boundary, and the second distance is The distance between the vehicle and the left lane boundary at the second time point, the third distance is the distance between the vehicle and the right lane boundary at the first time point, and the fourth distance is the distance between the vehicle and the right lane boundary at the second time point.

Further, the processing unit 1502 is further configured to: after determining that the left side of the first lane has changed, if the first distance change still satisfies: the fifth distance is greater than the second distance, and the difference between the fifth distance and the second distance If the value is greater than the second threshold, the second distance change also satisfies: the difference between the sixth distance and the fourth distance is less than the first threshold, then it is determined that a new lane is added to the left of the first lane;

Among them, the multiple time points also include a third time point, the third time point is after the second time point, the fifth distance is the distance between the vehicle at the third time point and the left lane boundary, and the sixth distance is the vehicle at the third time point. The distance between the time point and the right lane boundary.

Alternatively, the processing unit 1502 is further configured to: after determining that the left side of the first lane has changed, if the first distance change still satisfies: the fifth distance is less than the second distance, and the difference between the fifth distance and the second distance Is greater than the second threshold, the second distance change also satisfies: the difference between the sixth distance and the fourth distance is less than the first threshold, then it is determined that the lane on the left side of the first lane will be merged into the first lane;

Among them, the multiple time points also include a third time point, the third time point is after the second time point, the fifth distance is the distance between the vehicle at the third time point and the left lane boundary, and the sixth distance is the vehicle at the third time point. The distance between the time point and the right lane boundary.

Exemplarily, the processing unit 1502, when determining the lane change based on the first distance change and the second distance change, is specifically configured to: if the first distance change satisfies: the first distance is greater than the second distance, and the first distance is greater than the second distance The distance difference is greater than the third threshold, and the second distance change satisfies: the fourth distance is greater than the third distance, and the difference between the fourth distance and the third distance is greater than the fourth threshold, then it is determined that the first lane is to the right and the second lane When a merger occurs, the first lane is the lane where the vehicle is located, and the second lane is the lane to the right of the first lane;

Wherein, at least two time points include a first time point and a second time point, the first time point is before the second time point, the first distance is the distance between the vehicle at the first time point and the left lane boundary, and the second distance Is the distance between the vehicle and the left lane boundary at the second time point, the third distance is the distance between the vehicle and the right lane boundary at the first time point, and the fourth distance is the distance between the vehicle and the right lane boundary at the second time point .

Exemplarily, the processing unit 1502, when judging the lane change based on the first distance change and the second distance change, is specifically configured to: if the first distance change satisfies: the second distance is greater than the first distance, and the second distance is greater than the first distance. The distance difference is greater than the fourth threshold, and the second distance change satisfies: the fourth distance is less than the third distance, and the difference between the fourth distance and the third distance is greater than the third threshold, then it is judged that the first lane is to the left and the fourth lane When a merger occurs, the first lane is the lane where the vehicle is located, and the fourth lane is the left lane of the first lane;

Wherein, at least two time points include a first time point and a second time point, the first time point is before the second time point, the first distance is the distance between the vehicle at the first time point and the left lane boundary, and the second distance Is the distance between the vehicle and the left lane boundary at the second time point, the third distance is the distance between the vehicle and the right lane boundary at the first time point, and the fourth distance is the distance between the vehicle and the right lane boundary at the second time point .

Exemplarily, the processing unit 1502, when judging the lane change based on the first distance change and the second distance change, is specifically configured to: if the first distance change satisfies: the second distance is greater than the first distance, and the second distance is greater than the first distance. The difference between the distances is greater than the sixth threshold, and the change in the second distance satisfies: the fourth distance is greater than the third distance, and the difference between the fourth distance and the third distance is greater than the seventh threshold, then it is determined that the first lane has a road Separated, the first lane is the lane where the vehicle is located;

Wherein, at least two time points include a first time point and a second time point, the first time point is before the second time point, the first distance is the distance between the vehicle at the first time point and the left lane boundary, and the second distance Is the distance between the vehicle and the left lane boundary at the second time point, the third distance is the distance between the vehicle and the right lane boundary at the first time point, and the fourth distance is the distance between the vehicle and the right lane boundary at the second time point .

In an implementation manner, the processing unit 1502 is further configured to: before acquiring the location information corresponding to the vehicle at at least two time points, respectively, determine the change in the distance between the vehicle's historical driving trajectory and the lane boundary within a preset time range Within the preset range.

In an implementation manner, when acquiring lane boundary information, the communication unit 1501 is specifically configured to: acquire data collected by sensors; and acquire lane boundary information in a driving environment based on the data collected by sensors.

The division of modules in the embodiments of this application is illustrative, and it is only a logical function division. In actual implementation, there may be other division methods. In addition, the functional modules in the various embodiments of this application can be integrated into one process. In the device, it can also exist alone physically, or two or more modules can be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware or software functional modules.

Wherein, when the integrated module may be implemented in the form of hardware, as shown in FIG. 16, the lane structure detection device may include a processor 1601. The physical hardware corresponding to the foregoing module may be the processor 1601. The processor 1601 may be a central processing unit (CPU), or a digital processing module, and so on. The device also includes: a memory 1602, configured to store programs executed by the processor 1601. The memory 1602 may be a non-volatile memory, such as a hard disk drive (HDD) or a solid-state drive (SSD), etc., and may also be a volatile memory (volatile memory), such as random access memory (random access memory). -access memory, RAM). The memory 1602 is any other medium that can be used to carry or store desired program codes in the form of instructions or data structures and that can be accessed by a computer, but is not limited thereto. The device may further include a communication interface 1603, and the processor 1601 may obtain data collected by the sensor, data collected by the camera, etc. through the communication interface 1603.

In an implementation manner, the processor 1601 is configured to execute the program code stored in the memory 1602, and is specifically configured to execute the method described in the embodiments shown in FIG. 1 to FIG. 14. Reference may be made to the methods described in the embodiments shown in FIG. 1 to FIG. 14, and details are not described herein again in this application. In this implementation manner, the processor 1601 can implement the function of the lane detection device 150 shown in FIG. 15 by executing the program code stored in the memory 1602.

The specific connection medium between the processor 1601, the memory 1602, and the communication interface 1603 is not limited in the embodiment of the present application. In the embodiment of the present application in FIG. 16, the processor 1601, the memory 1602, and the communication interface 1603 are connected by a bus 1604. The bus is represented by a thick line in FIG. 16, and the connection modes between other components are merely illustrative. , Is not limited. The bus can be divided into an address bus, a data bus, a control bus, and so on. For ease of representation, only one thick line is used in FIG. 16, but it does not mean that there is only one bus or one type of bus.

The embodiment of the present invention also provides a computer-readable storage medium for storing computer software instructions required to execute the above-mentioned processor, which contains a program required to execute the above-mentioned processor.

Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, this application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

This application is described with reference to flowcharts and/or block diagrams of methods, equipment (systems), and computer program products according to this application. It should be understood that each process and/or block in the flowchart and/or block diagram, and the combination of processes and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing equipment to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing equipment are used to generate It is a device that realizes the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing equipment to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction device. The device implements the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operation steps are executed on the computer or other programmable equipment to produce computer-implemented processing, so as to execute on the computer or other programmable equipment. The instructions provide steps for implementing the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

Obviously, those skilled in the art can make various changes and modifications to the application without departing from the spirit and scope of the application. In this way, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalent technologies, then this application is also intended to include these modifications and variations.

Claims (27)

1. A method for detecting lane structure, characterized in that the method includes:

   Acquiring lane boundary information, where the lane boundary information includes position information of the left lane boundary and the right lane boundary;

   Acquiring the location information corresponding to the vehicle at at least two points in time;

   For each time point, determine the distance between the vehicle and the left lane boundary and the right lane boundary according to the location information corresponding to the vehicle at the time point;

   Determining a first distance change between the vehicle and the left lane boundary at the at least two time points and a second distance change between the vehicle and the right lane boundary at the at least two time points;

   The lane change is determined based on the first distance change and the second distance change.
2. The method of claim 1, wherein judging a lane change based on the first distance change and the second distance change comprises:

   If the first distance change satisfies: the difference between the first distance and the second distance is less than the first threshold, the second distance change satisfies: the third distance is less than the fourth distance, and the third distance is less than the fourth distance. If the difference between the fourth distance is greater than the second threshold, it is determined that the right side of the first lane is changed, and the first lane is the lane where the vehicle is located;

   Wherein, the at least two time points include a first time point and a second time point, the first time point is before the second time point, and the first distance is that the vehicle is at the first time point Point and the left lane boundary, the second distance is the distance between the vehicle and the left lane boundary at the second time point, and the third distance is the vehicle in the first The distance from the boundary of the right lane at a time point, and the fourth distance is the distance between the vehicle and the boundary of the right lane at the second time point.
3. The method according to claim 2, wherein after determining that the lane change is a change on the right side of the first lane, the method further comprises:

   If the first distance change also satisfies: the difference between the fifth distance and the second distance is less than the first threshold, the second distance change also satisfies: the sixth distance is greater than the four distances, and If the difference between the sixth distance and the fourth distance is greater than the second threshold, it is determined that a new lane is added to the right of the first lane;

   Wherein, the multiple time points further include a third time point, the third time point is after the second time point, and the fifth distance is the distance between the vehicle and the left at the third time point. The distance of the side lane boundary, and the sixth distance is the distance between the vehicle and the right lane boundary at the third time point.
4. The method according to claim 2, wherein after determining that the lane change is a change on the right side of the first lane, the method further comprises:

   If the first distance change also satisfies: the difference between the fifth distance and the second distance is less than the first threshold, the second distance change also satisfies: the sixth distance is less than the four distances, and If the difference between the sixth distance and the fourth distance is greater than the second threshold, it is determined that the lane on the right side of the first lane is merged into the first lane;

   Wherein, the multiple time points further include a third time point, the third time point is after the second time point, and the fifth distance is the distance between the vehicle and the left at the third time point. The distance of the side lane boundary, and the sixth distance is the distance between the vehicle and the right lane boundary at the third time point.
5. The method of claim 1, wherein judging a lane change based on the first distance change and the second distance change comprises:

   If the first distance change satisfies: the first distance is less than the second distance, and the difference between the first distance and the second distance is greater than the second threshold, the second distance change satisfies: the third distance If the difference between the fourth distance and the fourth distance is less than the first threshold, it is determined that the left side of the first lane has changed, and the first lane is the lane where the vehicle is located;

   Wherein, the multiple time points include a first time point and a second time point, the first time point is before the second time point, and the first distance is that the vehicle is at the first time point The distance from the boundary of the left lane, the second distance is the distance between the vehicle and the boundary of the left lane at the second time point, and the third distance is the distance between the vehicle and the boundary of the first lane. The distance between the time point and the right lane boundary, and the fourth distance is the distance between the vehicle and the right lane boundary at the second time point.
6. The method according to claim 5, wherein after determining that the left side of the first lane has changed, the method further comprises:

   If the first distance change also satisfies: the fifth distance is greater than the second distance, and the difference between the fifth distance and the second distance is greater than the second threshold, the second distance changes It is also satisfied that: the difference between the sixth distance and the fourth distance is less than the first threshold, then it is determined that a new lane is added to the left of the first lane;

   Wherein, the multiple time points further include a third time point, the third time point is after the second time point, and the fifth distance is the distance between the vehicle and the left at the third time point. The distance of the side lane boundary, and the sixth distance is the distance between the vehicle and the right lane boundary at the third time point.
7. The method according to claim 5, wherein after determining that the left side of the first lane has changed, the method further comprises:

   If the first distance change also satisfies: the fifth distance is less than the second distance, and the difference between the fifth distance and the second distance is greater than the second threshold, the second distance changes It is also satisfied that: the difference between the sixth distance and the fourth distance is less than the first threshold, then it is determined that the lane on the left side of the first lane will be merged into the first lane;

   Wherein, the multiple time points further include a third time point, the third time point is after the second time point, and the fifth distance is the distance between the vehicle and the left at the third time point. The distance of the side lane boundary, and the sixth distance is the distance between the vehicle and the right lane boundary at the third time point.
8. The method of claim 1, wherein judging a lane change based on the first distance change and the second distance change comprises:

   If the first distance change satisfies: the first distance is greater than the second distance, and the difference between the first distance and the second distance is greater than the third threshold, the second distance change satisfies: the fourth distance is greater than the first distance Three distances, and the difference between the fourth distance and the third distance is greater than the fourth threshold, then it is determined that the first lane to the right is merged with the second lane, and the first lane is the lane where the vehicle is located, The second lane is the lane on the right side of the first lane;

   Wherein, the at least two time points include a first time point and a second time point, the first time point is before the second time point, and the first distance is that the vehicle is at the first time point Point and the left lane boundary, the second distance is the distance between the vehicle and the left lane boundary at the second time point, and the third distance is the vehicle in the first The distance from the boundary of the right lane at a time point, and the fourth distance is the distance between the vehicle and the boundary of the right lane at the second time point.
9. The method of claim 1, wherein judging a lane change based on the first distance change and the second distance change comprises:

   If the first distance change satisfies: the second distance is greater than the first distance, and the difference between the second distance and the first distance is greater than the fourth threshold, the second distance change satisfies: the fourth distance is less than the first distance Three distances, and the difference between the fourth distance and the third distance is greater than the third threshold, then it is determined that the first lane is merged to the left with the fourth lane, and the first lane is the lane where the vehicle is located, The fourth lane is the lane on the left side of the first lane;

   Wherein, the at least two time points include a first time point and a second time point, the first time point is before the second time point, and the first distance is that the vehicle is at the first time point Point and the left lane boundary, the second distance is the distance between the vehicle and the left lane boundary at the second time point, and the third distance is the vehicle in the first The distance from the boundary of the right lane at a time point, and the fourth distance is the distance between the vehicle and the boundary of the right lane at the second time point.
10. The method of claim 1, wherein judging a lane change based on the first distance change and the second distance change comprises:

    If the first distance change satisfies: the second distance is greater than the first distance, and the difference between the second distance and the first distance is greater than the sixth threshold, the second distance change satisfies: the fourth distance Is greater than the third distance, and the difference between the fourth distance and the third distance is greater than the seventh threshold, then it is determined that a road separation occurs in the first lane, and the first lane is the lane where the vehicle is located;

    Wherein, the at least two time points include a first time point and a second time point, the first time point is before the second time point, and the first distance is that the vehicle is at the first time point Point and the left lane boundary, the second distance is the distance between the vehicle and the left lane boundary at the second time point, and the third distance is the vehicle in the first The distance from the boundary of the right lane at a time point, and the fourth distance is the distance between the vehicle and the boundary of the right lane at the second time point.
11. The method according to any one of claims 1 to 10, characterized in that, before acquiring the location information corresponding to the vehicle at at least two points in time, the method further comprises:

    It is determined that the change in the distance between the historical driving trajectory of the vehicle within a preset time range and the lane boundary is within a preset range.
12. The method according to any one of claims 1 to 11, wherein acquiring lane boundary information includes:

    Obtain the data collected by the sensor;

    Obtain the lane boundary information in the driving environment based on the data collected by the sensor.
13. A lane structure detection device, characterized in that the device includes:

    A communication unit for acquiring lane boundary information, where the lane boundary information includes position information of the left lane boundary and the right lane boundary;

    A processing unit, configured to obtain location information corresponding to the vehicle at at least two points in time;

    And, for each time point, determine the distance between the vehicle and the left lane boundary and the right lane boundary according to the position information of the vehicle at the time point;

    And, determining the first distance change between the vehicle and the left lane boundary at the at least two time points and the second distance change between the vehicle and the right lane boundary at the at least two time points ；

    And, judging a lane change based on the first distance change and the second distance change.
14. The device according to claim 13, wherein the processing unit is specifically configured to: when judging a lane change based on the first distance change and the second distance change:

    If the first distance change satisfies: the difference between the first distance and the second distance is less than the first threshold, the second distance change satisfies: the third distance is less than the fourth distance, and the third distance is less than the fourth distance. If the difference between the fourth distance is greater than the second threshold, it is determined that the right side of the first lane is changed, and the first lane is the lane where the vehicle is located;

    Wherein, the at least two time points include a first time point and a second time point, the first time point is before the second time point, and the first distance is that the vehicle is at the first time point Point and the left lane boundary, the second distance is the distance between the vehicle and the left lane boundary at the second time point, and the third distance is the vehicle in the first The distance from the boundary of the right lane at a time point, and the fourth distance is the distance between the vehicle and the boundary of the right lane at the second time point.
15. The device according to claim 14, wherein the processing unit is further configured to:

    After judging that the lane change is a change on the right side of the first lane, if the first distance change still satisfies: the difference between the fifth distance and the second distance is less than the first threshold, and the second distance The change also satisfies: the sixth distance is greater than the four distances, and the difference between the sixth distance and the fourth distance is greater than the second threshold, then it is determined that a new lane is added to the right of the first lane ；

    Wherein, the multiple time points further include a third time point, the third time point is after the second time point, and the fifth distance is the distance between the vehicle and the left at the third time point. The distance of the side lane boundary, and the sixth distance is the distance between the vehicle and the right lane boundary at the third time point.
16. The device according to claim 14, wherein the processing unit is further configured to:

    After judging that the lane change is a change on the right side of the first lane, if the first distance change still satisfies: the difference between the fifth distance and the second distance is less than the first threshold, and the second distance The change also satisfies: the sixth distance is less than the four distances, and the difference between the sixth distance and the fourth distance is greater than the second threshold, then it is determined that the lanes on the right of the first lane are merged into The first lane;

    Wherein, the multiple time points further include a third time point, the third time point is after the second time point, and the fifth distance is the distance between the vehicle and the left at the third time point. The distance of the side lane boundary, and the sixth distance is the distance between the vehicle and the right lane boundary at the third time point.
17. The device according to claim 13, wherein the processing unit is specifically configured to: when judging a lane change based on the first distance change and the second distance change:

    If the first distance change satisfies: the first distance is less than the second distance, and the difference between the first distance and the second distance is greater than the second threshold, the second distance change satisfies: the third distance If the difference between the fourth distance and the fourth distance is less than the first threshold, it is determined that the left side of the first lane has changed, and the first lane is the lane where the vehicle is located;

    Wherein, the multiple time points include a first time point and a second time point, the first time point is before the second time point, and the first distance is that the vehicle is at the first time point The distance from the boundary of the left lane, the second distance is the distance between the vehicle and the boundary of the left lane at the second time point, and the third distance is the distance between the vehicle and the boundary of the first lane. The distance between the time point and the right lane boundary, and the fourth distance is the distance between the vehicle and the right lane boundary at the second time point.
18. The device according to claim 17, wherein the processing unit is further configured to:

    After determining that the left side of the first lane has changed, if the first distance change also satisfies: the fifth distance is greater than the second distance, and the difference between the fifth distance and the second distance is greater than all For the second threshold, the change in the second distance also satisfies: the difference between the sixth distance and the fourth distance is less than the first threshold, then it is determined that a new lane is added to the left of the first lane;

    Wherein, the multiple time points further include a third time point, the third time point is after the second time point, and the fifth distance is the distance between the vehicle and the left at the third time point. The distance of the side lane boundary, and the sixth distance is the distance between the vehicle and the right lane boundary at the third time point.
19. The device according to claim 17, wherein the processing unit is further configured to:

    After determining that the left side of the first lane has changed, if the first distance change also satisfies: the fifth distance is less than the second distance, and the difference between the fifth distance and the second distance is greater than all According to the second threshold, the second distance change also satisfies: the difference between the sixth distance and the fourth distance is less than the first threshold, then it is determined that the lane on the left side of the first lane will be merged into all the lanes. State the first lane;

    Wherein, the multiple time points further include a third time point, the third time point is after the second time point, and the fifth distance is the distance between the vehicle and the left at the third time point. The distance of the side lane boundary, and the sixth distance is the distance between the vehicle and the right lane boundary at the third time point.
20. The device according to claim 13, wherein the processing unit is specifically configured to: when judging a lane change based on the first distance change and the second distance change:

    If the first distance change satisfies: the first distance is greater than the second distance, and the difference between the first distance and the second distance is greater than the third threshold, the second distance change satisfies: the fourth distance is greater than the first distance Three distances, and the difference between the fourth distance and the third distance is greater than the fourth threshold, then it is determined that the first lane to the right is merged with the second lane, and the first lane is the lane where the vehicle is located, The second lane is the lane on the right side of the first lane;

    Wherein, the at least two time points include a first time point and a second time point, the first time point is before the second time point, and the first distance is that the vehicle is at the first time point Point and the left lane boundary, the second distance is the distance between the vehicle and the left lane boundary at the second time point, and the third distance is the vehicle in the first The distance from the boundary of the right lane at a time point, and the fourth distance is the distance between the vehicle and the boundary of the right lane at the second time point.
21. The device according to claim 13, wherein the processing unit is specifically configured to: when judging a lane change based on the first distance change and the second distance change:

    If the first distance change satisfies: the second distance is greater than the first distance, and the difference between the second distance and the first distance is greater than the fourth threshold, the second distance change satisfies: the fourth distance is less than the first distance Three distances, and the difference between the fourth distance and the third distance is greater than the third threshold, then it is determined that the first lane is merged to the left with the fourth lane, and the first lane is the lane where the vehicle is located, The fourth lane is the lane on the left side of the first lane;

    Wherein, the at least two time points include a first time point and a second time point, the first time point is before the second time point, and the first distance is that the vehicle is at the first time point Point and the left lane boundary, the second distance is the distance between the vehicle and the left lane boundary at the second time point, and the third distance is the vehicle in the first The distance from the boundary of the right lane at a time point, and the fourth distance is the distance between the vehicle and the boundary of the right lane at the second time point.
22. The device according to claim 13, wherein the processing unit is specifically configured to: when judging a lane change based on the first distance change and the second distance change:

    If the first distance change satisfies: the second distance is greater than the first distance, and the difference between the second distance and the first distance is greater than the sixth threshold, the second distance change satisfies: the fourth distance Is greater than the third distance, and the difference between the fourth distance and the third distance is greater than the seventh threshold, then it is determined that a road separation occurs in the first lane, and the first lane is the lane where the vehicle is located;

    Wherein, the at least two time points include a first time point and a second time point, the first time point is before the second time point, and the first distance is that the vehicle is at the first time point Point and the left lane boundary, the second distance is the distance between the vehicle and the left lane boundary at the second time point, and the third distance is the vehicle in the first The distance from the boundary of the right lane at a time point, and the fourth distance is the distance between the vehicle and the boundary of the right lane at the second time point.
23. The device according to any one of claims 13 to 22, wherein the processing unit is further configured to:

    Before acquiring the location information corresponding to the vehicle at at least two time points, respectively, it is determined that the distance change between the historical driving track of the vehicle within a preset time range and the lane boundary is within a preset range.
24. The device according to any one of claims 13 to 23, wherein the communication unit is specifically configured to: when acquiring lane boundary information:

    Obtain the data collected by the sensor;

    Obtain the lane boundary information in the driving environment based on the data collected by the sensor.
25. A computer-readable storage medium, characterized in that computer-readable instructions are stored in the computer storage medium, and when the computer reads and executes the computer-readable instructions, the computer executes any one of claims 1-12. The method described in the item.
26. A computer program product, characterized in that when a computer reads and executes the computer program product, the computer is caused to execute the method according to any one of claims 1-12.
27. A chip, characterized in that the chip is coupled with a memory, and is used to read and execute program instructions stored in the memory, so as to implement the method according to any one of claims 1-12.

Images