Method, system, device and electronic device for creating autonomous driving scene

Abstract

The present invention discloses a method, system, device and electronic device for creating an autonomous driving scene. The method can be applied at least in the field of AI driving, and the method may include: obtaining the driving trajectory of a reference vehicle traveling on an initial lane; in response to determining that the reference vehicle has changed lanes on the initial lane based on the driving trajectory, determining the target position information on the initial lane based on the lane changing behavior; based on the target position information and lane information, creating an autonomous driving scene for the autonomous driving vehicle, wherein the lane information includes the lane information of the initial lane and the lane information of the target lane, and the autonomous driving scene includes a diverging driving scene corresponding to the diverging driving behavior, or a merging driving scene corresponding to the merging driving behavior. The present invention solves the technical problem of low flexibility in creating autonomous driving scenes.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving, and in particular to a method, system, device and electronic device for creating an autonomous driving scene. Background Art

[0002] At present, in the field of autonomous driving, when an autonomous driving vehicle turns on artificial intelligence (AI) driving (for example, turning on commuting mode), an autonomous driving scene needs to be created. To create an autonomous driving scene, the road divergence and road merging technology of autonomous driving vehicles is often used, which mainly relies on pre-designed road models, road structure characteristics and specific traffic rules algorithms.

[0003] However, the above-mentioned road divergence and road merging technologies, due to ignoring the vehicle's driving data, are not only difficult to adapt to changing road conditions, but also cause limitations in scene construction when constructing road divergence scenarios and road merging scenarios, thereby leading to the problem of low flexibility in creating autonomous driving scenarios.

[0004] Currently, no effective solution has been proposed to the above-mentioned problem of low flexibility in creating autonomous driving scenarios. Summary of the invention

[0005] Embodiments of the present invention provide a method, system, device and electronic device for creating an autonomous driving scene, so as to at least solve the technical problem of low flexibility in creating an autonomous driving scene.

[0006] According to one aspect of an embodiment of the present invention, a method for creating an autonomous driving scene is provided. The method may include: obtaining a driving trajectory of a reference vehicle traveling on an initial lane; in response to determining that a lane change occurs in the driving behavior of the reference vehicle on the initial lane based on the driving trajectory, determining target position information on the initial lane based on the lane change behavior, wherein the lane change behavior is used to indicate the behavior of the reference vehicle changing lanes from the initial lane to the target lane, and the target position information is used to indicate the position where the autonomous driving vehicle corresponding to the reference vehicle is allowed to perform diverging driving behavior or merging driving behavior on the initial lane; creating an autonomous driving scene of the autonomous driving vehicle based on the target position information and lane information, wherein the lane information includes lane information of the initial lane and lane information of the target lane, and the autonomous driving scene includes a diverging driving scene corresponding to the diverging driving behavior, or a merging driving scene corresponding to the merging driving behavior.

[0007] Optionally, in response to determining that a reference vehicle changes lanes in an initial lane based on a driving trajectory, determining target position information in the initial lane based on the lane changing behavior includes: in response to determining that a reference vehicle changes lanes in an initial lane based on a driving trajectory, obtaining a target intersection point corresponding to the lane changing behavior, wherein the target intersection point is used to represent an intersection point between the driving trajectory and a first boundary line during the process of the reference vehicle performing the lane changing behavior, the first boundary line being a common boundary line between the initial lane and the target lane; determining the target position information in the initial lane based on the target intersection point.

[0008] Optionally, based on the target intersection, the target position information is determined on the initial lane, including: traversing the points on the first boundary line starting from the target intersection according to the lane direction of the initial lane to obtain the traversed points; determining an area centered on the traversed points; in response to the intersection of the boundary line of the area with the second boundary line, determining the position information corresponding to the traversed points on the initial lane as the target position information, wherein the second boundary line is a boundary line on the target lane set opposite to the first boundary line.

[0009] Optionally, in response to the intersection of the boundary line of the area and the second boundary line, the position information corresponding to the traversed point on the initial lane is determined as the target position information, including: in response to the intersection of the boundary line of the area and the second boundary line, and the second boundary line does not belong to the predecessor boundary line or the successor boundary line of the first boundary line, the position information corresponding to the traversed point on the initial lane is determined as the target position information.

[0010] Optionally, traversing points on the first boundary line starting from the target intersection according to the lane direction of the initial lane to obtain the traversed points includes: traversing points on the first boundary line starting from the target intersection according to the first lane direction and the second lane direction of the initial lane, respectively, wherein the first lane direction and the second lane direction are opposite directions to each other.

[0011] Optionally, traversing points on the first boundary line from the target intersection according to the first lane direction and the second lane direction of the initial lane respectively to obtain the traversed points, including: determining a first length range and a second length range corresponding to the divergence driving scenario, wherein the second length range with the target intersection as an endpoint is greater than the first length range with the target intersection as an endpoint; traversing points within the first length range on the first boundary line from the target intersection according to the first lane direction to obtain the traversed points; traversing points within the second length range on the first boundary line from the target intersection according to the second lane direction to obtain the traversed points.

[0012] Optionally, the method further includes: in response to the second length range including points on a predecessor boundary line of the first boundary line, traversing points on the predecessor boundary line of the first boundary line to obtain the traversed points.

[0013] Optionally, traversing points on the first boundary line from the target intersection according to the first lane direction and the second lane direction of the initial lane respectively to obtain the traversed points, including: determining a third length range and a fourth length range corresponding to the merging driving scenario, wherein the fourth length range with the target intersection as the endpoint is smaller than the third length range with the target intersection as the endpoint; traversing points within the third length range on the first boundary line from the target intersection according to the first lane direction to obtain the traversed points; traversing points within the fourth length range on the first boundary line from the target intersection according to the second lane direction to obtain the traversed points.

[0014] Optionally, the method further includes: in response to the third length range including points on a predecessor boundary line of the first boundary line, traversing points on the predecessor boundary line of the first boundary line to obtain the traversed points.

[0015] Optionally, determining an area centered on the traversed point includes: determining a circular area centered on the traversed point.

[0016] Optionally, based on the target position information and lane information, an autonomous driving scene for an autonomous driving vehicle is created, including: determining a sub-boundary line between a point corresponding to the target position information and a target intersection point on a first boundary line; and creating an autonomous driving scene based on the sub-boundary line and the lane information.

[0017] Optionally, an autonomous driving scenario is created based on the sub-boundary line and lane information, including: using the sub-boundary line to associate with the lane information to obtain the autonomous driving scenario, wherein the autonomous driving vehicle is used to perform a diverging driving behavior in a diverging driving scenario in the autonomous driving scenario to diverge from an initial lane to a target lane via the sub-boundary line, or the autonomous driving vehicle is used to perform a merging driving behavior in a merging driving scenario in the autonomous driving scenario to merge from the target lane to the initial lane via the sub-boundary line.

[0018] Optionally, the sub-boundary line is used to associate lane information to obtain an autonomous driving scene, including: in response to the length of the sub-boundary line being within a fifth length range, the sub-boundary line is used to associate the target lane and the initial lane to obtain the autonomous driving scene.

[0019] Optionally, the method includes: in response to the presence of a target intersection between the driving trajectory and a first boundary line, determining that the reference vehicle has changed lanes in an initial lane, wherein the first boundary line is a common boundary between the initial lane and the target lane.

[0020] Optionally, in response to the presence of a target intersection between the driving trajectory and the first boundary line, determining that the reference vehicle has changed lanes in the initial lane includes: dividing the driving trajectory into multiple sub-driving trajectories; in response to the presence of a target intersection between the sub-driving trajectories and the first boundary line, determining that the reference vehicle has changed lanes in the initial lane.

[0021] According to another aspect of an embodiment of the present invention, a system for creating an autonomous driving scenario is provided. The system may include: a reference vehicle, which is used to upload a driving trajectory of the reference vehicle on an initial lane; a server, which is used to respond to a determination based on the driving trajectory that the reference vehicle has a lane change behavior on the initial lane, and to determine target position information on the initial lane based on the lane change behavior, wherein the lane change behavior is used to indicate the behavior of the reference vehicle changing lanes from the initial lane to the target lane, and the target position information is used to indicate the position where the autonomous driving vehicle corresponding to the reference vehicle is allowed to perform a diverging driving behavior or a merging driving behavior on the initial lane; based on the target position information and the lane information, an autonomous driving scenario of the autonomous driving vehicle is created, wherein the lane information includes: lane information of the initial lane and lane information of the target lane, and the autonomous driving scenario includes a diverging driving scenario corresponding to the diverging driving behavior, or a merging driving scenario corresponding to the merging driving behavior.

[0022] According to another aspect of an embodiment of the present invention, a device for creating an autonomous driving scene is also provided. The device may include: an acquisition unit for acquiring a driving trajectory of a reference vehicle traveling on an initial lane; a determination unit for responding to a lane change behavior determined based on the driving trajectory of the reference vehicle on the initial lane, and determining target position information on the initial lane based on the lane change behavior, wherein the lane change behavior is used to indicate the behavior of the reference vehicle changing lanes from the initial lane to the target lane, and the target position information is used to indicate the position of the autonomous driving vehicle corresponding to the reference vehicle on the initial lane to perform a diverging driving behavior or a merging driving behavior; a creation unit for creating an autonomous driving scene of the autonomous driving vehicle based on the target position information and lane information, wherein the lane information includes lane information of the initial lane and lane information of the target lane, and the autonomous driving scene includes a diverging driving scene corresponding to the diverging driving behavior, or a merging driving scene corresponding to the merging driving behavior.

[0023] Optionally, the determination unit includes: an acquisition module, used to acquire a target intersection point corresponding to the lane changing behavior in response to determining that the reference vehicle has changed lanes in the initial lane based on the driving trajectory, wherein the target intersection point is used to represent the intersection point between the driving trajectory and the first boundary line when the reference vehicle is performing the lane changing behavior, and the first boundary line is the common boundary line between the initial lane and the target lane; a first determination module, used to determine the target position information on the initial lane based on the target intersection point.

[0024] Optionally, the first determination module includes: a traversal submodule, used to traverse the points on the first boundary line starting from the target intersection point according to the lane direction of the initial lane to obtain the traversed points; a first determination submodule, used to determine the area centered on the traversed points; a second determination submodule, used to determine the position information corresponding to the traversed points on the initial lane as the target position information in response to the intersection of the boundary line of the area with the second boundary line, wherein the second boundary line is a boundary line on the target lane set opposite to the first boundary line.

[0025] Optionally, the second determination submodule determines the position information corresponding to the traversed point on the initial lane as the target position information in response to the intersection of the boundary line of the area with the second boundary line by executing the following steps: In response to the intersection of the boundary line of the area with the second boundary line, and the second boundary line does not belong to the predecessor boundary line or the successor boundary line of the first boundary line, the position information corresponding to the traversed point on the initial lane is determined as the target position information.

[0026] Optionally, the traversal submodule traverses the points on the first boundary line starting from the target intersection according to the lane direction of the initial lane by executing the following steps to obtain the traversed points: traverse the points on the first boundary line starting from the target intersection according to the first lane direction and the second lane direction of the initial lane, respectively, wherein the first lane direction and the second lane direction are in opposite directions to each other.

[0027] Optionally, the traversal submodule traverses the points on the first boundary line starting from the target intersection according to the first lane direction and the second lane direction of the initial lane, respectively, to obtain the traversed points by executing the following steps: determine a first length range and a second length range corresponding to the divergence driving scenario, wherein the second length range with the target intersection as the endpoint is greater than the first length range with the target intersection as the endpoint; traverse the points within the first length range on the first boundary line starting from the target intersection according to the first lane direction to obtain the traversed points; traverse the points within the second length range on the first boundary line starting from the target intersection according to the second lane direction to obtain the traversed points.

[0028] Optionally, the device for creating an autonomous driving scene also includes: a first traversal unit, which is used to respond to the points on the predecessor boundary line of the first boundary line included in the second length range, traverse the points on the predecessor boundary line of the first boundary line, and obtain the traversed points.

[0029] Optionally, the traversal submodule also traverses the points on the first boundary line starting from the target intersection according to the first lane direction and the second lane direction of the initial lane, respectively, to obtain the traversed points by executing the following steps: determine a third length range and a fourth length range corresponding to the merging driving scenario, wherein the fourth length range with the target intersection as the endpoint is smaller than the third length range with the target intersection as the endpoint; traverse the points within the third length range on the first boundary line starting from the target intersection in the first lane direction to obtain the traversed points; traverse the points within the fourth length range on the first boundary line starting from the target intersection in the second lane direction to obtain the traversed points.

[0030] Optionally, the device for creating an autonomous driving scene also includes: a second traversal unit, used to traverse the points on the predecessor boundary line of the first boundary line in response to the third length range including the points on the predecessor boundary line of the first boundary line, to obtain the traversed points.

[0031] Optionally, the creation unit includes: a second determination module, used to determine the sub-boundary line between the point corresponding to the target position information and the target intersection point on the first boundary line; and a creation module, used to create an autonomous driving scene based on the sub-boundary line and lane information.

[0032] Optionally, the creation module includes: an association submodule, used to associate lane information with the sub-boundary line to obtain an autonomous driving scenario, wherein the autonomous driving vehicle is used to perform a diverging driving behavior in a diverging driving scenario in the autonomous driving scenario to diverge from the initial lane to the target lane via the sub-boundary line, or the autonomous driving vehicle is used to perform a merging driving behavior in a merging driving scenario in the autonomous driving scenario to merge from the target lane to the initial lane via the sub-boundary line.

[0033] Optionally, the association submodule uses the sub-boundary line to associate lane information to obtain an autonomous driving scenario by performing the following steps: in response to the length of the sub-boundary line being within a fifth length range, using the sub-boundary line to associate the target lane and the initial lane to obtain an autonomous driving scenario.

[0034] Optionally, the device for creating the autonomous driving scenario also includes: a first determination unit, used to determine that the reference vehicle has changed lanes in the initial lane in response to the presence of a target intersection between the driving trajectory and the first boundary line, wherein the first boundary line is a common boundary between the initial lane and the target lane.

[0035] Optionally, the first determination unit includes: a division module for dividing the driving trajectory into multiple sub-driving trajectories; and a third determination module for determining that the reference vehicle has changed lanes in the initial lane in response to the presence of a target intersection between the sub-driving trajectory and the first boundary line.

[0036] According to another aspect of an embodiment of the present invention, there is also provided an autonomous driving vehicle, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes any one of the above methods when running.

[0037] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium including a stored executable program, wherein when the executable program runs, the device where the storage medium is located is controlled to execute any one of the above methods.

[0038] According to another aspect of an embodiment of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, any one of the above methods is implemented.

[0039] In an embodiment of the present invention, when creating an autonomous driving scene, the driving trajectory of a reference vehicle traveling on an initial lane may be obtained. Based on the obtained driving trajectory, the driving behavior of the reference vehicle on the initial lane may be determined. The driving behavior of the reference vehicle on the initial lane is judged, and if it is judged that the driving behavior of the reference vehicle on the initial lane is a lane change behavior, the target position information may be determined on the initial lane according to the lane change behavior. According to the target position information determined on the initial lane, and the lane information, an autonomous driving scene of the autonomous driving vehicle may be created. That is, since the embodiment of the present application can determine the driving behavior of the reference vehicle on the initial lane according to the driving trajectory of the reference vehicle obtained, and in the case where the above-mentioned driving behavior is a lane change behavior, the target position information determined according to the lane change behavior, and the lane information, an autonomous driving scene may be created, and since the embodiment of the present application determines the driving behavior of the reference vehicle on the initial lane according to the driving trajectory of the reference vehicle, the obtained driving trajectory may include rich behavioral characteristics and preference information of the reference vehicle, thereby achieving the purpose of adapting the process of creating the autonomous driving scene to the changing road conditions, thereby solving the technical problem of low flexibility of the autonomous driving scene, and further achieving the technical effect of improving the flexibility of the autonomous driving scene. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0041] Figure 1 is a schematic diagram of an application scenario of a method for creating an autonomous driving scenario according to an embodiment of the present invention;

[0042] FIG2( a ) is a flow chart of a method for creating an autonomous driving scenario according to an embodiment of the present invention;

[0043] FIG2( b ) is a schematic diagram of a vehicle lane changing scenario according to an embodiment of the present invention;

[0044] FIG2( c ) is a schematic diagram showing data interaction between a vehicle and a server according to an embodiment of the present invention;

[0045] Figure 3 is a structural block diagram of a system for creating an autonomous driving scenario according to an embodiment of the present invention;

[0046] Figure 4 is a structural block diagram of a device for creating an autonomous driving scenario according to an embodiment of the present invention;

[0047] Figure 5 is a structural block diagram of an autonomous driving vehicle according to an embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0049] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0050] Example 1

[0051] According to an embodiment of the present invention, a method for creating an autonomous driving scene is provided.

[0052] As an optional implementation, the above-mentioned method for creating an autonomous driving scene can be applied to, but is not limited to, Figure 1 The application scenario shown. Figure 1 is a schematic diagram of an application scenario of a method for creating an autonomous driving scenario according to an embodiment of the present invention, such as Figure 1 As shown, in the application scenario, the terminal device 10 can, but is not limited to, communicate with the server 13 through the network 11, and the server 13 can, but is not limited to, perform operations on the database, such as write data operations or read data operations. The above-mentioned terminal device 10 can, but is not limited to, include a human-computer interaction screen, a processor, and a memory. The above-mentioned human-computer interaction screen can, but is not limited to, be used to display a virtual machine on the terminal device 10. The above-mentioned autonomous driving vehicle 12 can, but is not limited to, be used to respond to the above-mentioned human-computer interaction operations, perform corresponding operations, or generate corresponding instructions, and send the generated instructions to the server 13.

[0053] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0054] Figure 1 is a schematic diagram of an application scenario of a method for creating an autonomous driving scenario according to an embodiment of the present invention, such as Figure 1 As shown, the method comprises the following steps:

[0055] Step S102, obtaining the driving trajectory of the reference vehicle traveling on the initial lane.

[0056] In the technical solution provided in the above step S102 of the present invention, the above reference vehicle can be used to represent the actual vehicle in the actual application scenario, which can be the actual vehicle traveling in the historical period, or the actual vehicle in driving state in the current period. The above initial lane can be used to represent the lane where the reference vehicle is located. The driving trajectory of the above reference vehicle can be used to represent the driving process of the reference vehicle in the historical time, and can at least include: the driving data of the reference vehicle and the behavior habits of the reference vehicle, etc., which are only used as examples here and are not specifically limited. Optionally, the reference vehicle of this embodiment is an object to be considered in the process of generating the autonomous driving scene of the autonomous driving vehicle, and its driving trajectory can be used to generate the above autonomous driving scene.

[0057] In this embodiment, the driving trajectory of the reference vehicle traveling on the initial lane is obtained. Optionally, this embodiment monitors the driving data of the reference vehicle in real time, and when it is monitored that the speed in the driving data is reduced to a certain speed value and the turning angular velocity in the driving data is increased to a certain angular velocity value, at least the speed reduced to a certain speed value and the turning angular velocity increased to a certain angular velocity value are used as the driving data of the reference vehicle. Based on the driving data of the reference vehicle, the driving trajectory of the reference vehicle can be generated and obtained. Optionally, this embodiment directly calls the historical driving data of the reference vehicle from the cloud, and based on the called historical driving data, the driving trajectory of the reference vehicle can be generated and obtained.

[0058] It should be noted that the above-mentioned driving trajectory may be the driving trajectory of the actual driving subject driving the reference vehicle, which is only used as an example here and is not specifically limited.

[0059] Step S104, in response to determining based on the driving trajectory that the reference vehicle has changed lanes in the initial lane, determining target position information in the initial lane based on the lane changing behavior.

[0060] In the technical solution provided in the above step S104 of the present invention, the above lane change behavior can be used to indicate the behavior of the reference vehicle changing lanes from the initial lane to the target lane, and the above target position information can be used to indicate the position where the autonomous driving vehicle corresponding to the reference vehicle is allowed to perform diverging driving behavior or merging driving behavior in the initial lane.

[0061] In this embodiment, the lane changing behavior of the reference vehicle can be used to represent the behavior of the reference vehicle changing lanes from an initial lane to a target lane during driving. The above-mentioned target position information can be a point on the boundary line of the initial lane that meets the divergence and merging characteristics. The above-mentioned autonomous driving vehicle can be a vehicle with an autonomous driving function, for example, it can be a vehicle with an autonomous driving function turned on during driving. This is only an example here and is not specifically limited.

[0062] In this embodiment, after the driving trajectory of the reference vehicle traveling on the initial lane is obtained, in response to determining that the reference vehicle has changed lanes on the initial lane based on the driving trajectory, target position information is determined on the initial lane based on the lane change behavior. Optionally, in the case of obtaining the driving trajectory of the reference vehicle, it is determined whether there is a target intersection between the obtained driving trajectory and the boundary line of the initial lane, and it can be determined whether the driving behavior of the reference vehicle on the initial lane is a lane change behavior. If it is determined that there is a target intersection between the obtained driving trajectory and the boundary line of the initial lane, it can be determined that the driving behavior of the reference vehicle on the initial lane is a lane change behavior. In the case of determining that the reference vehicle has changed lanes on the initial lane, the target position information can be determined on the initial lane based on the intersection corresponding to the lane change behavior, that is, the target position information of the autonomous driving vehicle performing diverging driving behavior or merging driving behavior on the initial lane can be determined.

[0063] In this embodiment, the target position information can be determined on the initial lane according to the intersection corresponding to the lane change behavior. For example, according to the lane direction of the initial lane, starting from the above intersection, traversing the points on the boundary line of the initial lane can obtain the traversed points, and the area including the point can be determined. According to the relationship between the boundary line of the area and the boundary line of the target lane, the target position information of the autonomous driving vehicle performing the diverging driving behavior or the merging driving behavior on the initial lane can be determined.

[0064] Step S106, creating an autonomous driving scene for the autonomous driving vehicle based on the target position information and the lane information.

[0065] In the technical solution provided in the above step S106 of the present invention, the above lane information may include lane information of the initial lane and lane information of the target lane, and the above autonomous driving scenario may at least include a diverging driving scenario corresponding to the diverging driving behavior, or a merging driving scenario corresponding to the merging driving behavior.

[0066] In this embodiment, in response to determining that the reference vehicle has changed lanes in the initial lane based on the driving trajectory, after determining the target position information in the initial lane based on the lane change behavior, an autonomous driving scene of the autonomous driving vehicle is created based on the target position information and the lane information. Optionally, on the basis of determining the target position information, a sub-boundary line between the point corresponding to the target position information and the above-mentioned target intersection point can be determined on the boundary line of the initial lane. Based on the determined sub-boundary line, the lane information of the initial lane, and the lane information of the target lane, an autonomous driving scene of the autonomous driving vehicle can be created.

[0067] In this embodiment, an autonomous driving scene of an autonomous driving vehicle can be created based on the determined sub-boundary line, lane information of the initial lane, and lane information of the target lane. For example, the target lane and the initial lane can be connected using the sub-boundary line between the point corresponding to the target position information and the target intersection point, thereby obtaining an autonomous driving scene of an autonomous driving vehicle.

[0068] It should be noted that the method for creating an autonomous driving scene in this application can also be applied to at least the following scenes: autonomous driving scene, assisted driving scene and passive driving scene. Among them, the autonomous driving scene can be used to represent a scene where the vehicle uses artificial intelligence technology to autonomously complete the driving operation, and the driving object does not need to intervene in any way. The assisted driving scene can be used to represent a scene where the vehicle's control system provides assistance during the driving process, but the driving object still needs to maintain control and supervision of the driving. The passive driving scene can be used to represent a scene where the driving object controls the vehicle to complete the driving operation.

[0069] In the AI ​​driver of autonomous vehicles, commuting mode usually refers to a driving mode designed for commuting or daily commuting. Among them, the AI ​​driver can collect data by learning the user's driving route and driving behavior. When all the learning is completed, the collected data is screened and checked, and then the full segment of data after screening and checking is automatically transmitted back to the cloud server to execute the construction of the cloud map. The next time you drive and choose the same route, the AI ​​driver will be activated, and the vehicle will be driven to the destination of the route according to the constructed cloud map. Among them, matching and complementing the offline map with the constructed cloud map can improve the accuracy of the map.

[0070] In the above steps S102 to S106 of the present application, when the same route as the last driving is chosen for this driving, the AI ​​driver can be activated to obtain the driving trajectory of the reference vehicle driving on the initial lane from the vehicle's cloud. The AI ​​driver can determine the driving behavior of the reference vehicle on the initial lane based on the acquired driving trajectory. The AI ​​driver judges the driving behavior of the reference vehicle on the initial lane. If it is judged that the driving behavior of the reference vehicle on the initial lane is a lane change behavior, the target position information can be determined on the initial lane based on the lane change behavior. The AI ​​driver can create an autonomous driving scene for the autonomous driving vehicle based on the target position information determined on the initial lane, as well as the lane information. Therefore, in the autonomous driving scene created by the AI ​​driver, the autonomous driving vehicle can be driven along the same route as the last driving to perform diverging driving behavior, or to perform merging driving behavior.

[0071] In this embodiment, the commuting mode can be optimized according to the needs of the driver or passenger to improve the efficiency and comfort of commuting. The design of the commuting mode can take into account at least one of the following information:

[0072] (1) Route information: AI driver can select the route information for the vehicle to travel based on factors such as real-time traffic conditions and estimated arrival time. AI driver can also monitor traffic conditions in real time and adjust the selected route information when congested sections are detected, thereby achieving the purpose of avoiding congested sections.

[0073] (2) Travel time: AI driver can predict travel time based on historical driving data and current road conditions. If the user's schedule changes, the AI ​​driver can adjust the travel time according to the changed schedule.

[0074] (3) Personalized information: The AI ​​driver can adjust at least one of the following personalized information based on the user's preferences and habits: the vehicle's seat position, the air conditioning temperature in the car, the type of music and news played in the car, etc.;

[0075] (4) Safety level: In commuting mode, the AI ​​driver can adjust the safety level to maintain a safe distance from the surrounding vehicles and comply with the traffic rules of the country of origin;

[0076] (5) Energy information: AI driver can adjust the energy output power based on information such as current road conditions and the distance between the current location and the destination to optimize battery life or fuel efficiency;

[0077] (6) Parking information: When approaching the destination, the AI ​​driver can automatically find a parking space and perform automatic parking. The parking information can also be uploaded to the cloud and / or client. The parking information may include at least: the location information of the vehicle and the parking time information;

[0078] (7) Emergency response: In commuting mode, if an emergency occurs, the AI ​​driver can respond quickly to ensure the safety of the people in the vehicle;

[0079] (8) Travel planning: AI chauffeurs can collect historical commuting data and provide travel reports to help users understand their commuting habits and optimize their travel plans.

[0080] From the above content, we can see that the design purpose of commuting mode is to enable users of autonomous vehicles to complete daily commuting tasks more easily and safely, while improving the efficiency and comfort of commuting. As technology continues to develop, commuting mode can also include more personalized and intelligent functions.

[0081] In the above steps S102 to S106 of the present application, when creating an autonomous driving scenario, the driving trajectory of the reference vehicle traveling on the initial lane can be obtained. Based on the obtained driving trajectory, the driving behavior of the reference vehicle on the initial lane can be determined. The driving behavior of the reference vehicle on the initial lane is judged, and if it is judged that the driving behavior of the reference vehicle on the initial lane is a lane change behavior, then according to the lane change behavior, the target position information can be determined on the initial lane. Based on the target position information determined on the initial lane, and the lane information, an autonomous driving scenario for the autonomous driving vehicle can be created. That is to say, since the embodiment of the present application can determine the driving behavior of the reference vehicle in the initial lane based on the acquired driving trajectory of the reference vehicle, and when the above-mentioned driving behavior is a lane change behavior, the target position information determined according to the lane change behavior, and the lane information, an autonomous driving scene can be created, and since the embodiment of the present application determines the driving behavior of the reference vehicle in the initial lane based on the driving trajectory of the reference vehicle, the acquired driving trajectory can include rich behavioral characteristics and preference information of the reference vehicle, thereby achieving the purpose of the process of creating the autonomous driving scene being able to adapt to changing road conditions, thereby solving the technical problem of low flexibility of the autonomous driving scene, and further achieving the technical effect of improving the flexibility of the autonomous driving scene.

[0082] The above method of this embodiment is further introduced below.

[0083] The method for determining target position information on the initial lane based on the lane change behavior of this embodiment is further described below.

[0084] As an optional implementation method, step S104, in response to determining based on the driving trajectory that the reference vehicle has changed lanes in the initial lane, determining the target position information in the initial lane based on the lane changing behavior, includes: in response to determining based on the driving trajectory that the reference vehicle has changed lanes in the initial lane, obtaining the target intersection corresponding to the lane changing behavior; and determining the target position information in the initial lane based on the target intersection.

[0085] In this embodiment, the first boundary line may be a common boundary line between the initial lane and the target lane, and the target intersection point may be used to indicate the intersection point between the driving trajectory of the reference vehicle and the first boundary line when the reference vehicle is performing a lane change.

[0086] In this embodiment, after the driving trajectory of the reference vehicle traveling in the initial lane is obtained, in response to determining that the reference vehicle has changed lanes in the initial lane based on the driving trajectory, a target intersection point corresponding to the lane change behavior is obtained. Optionally, this embodiment determines the behavior of the reference vehicle in the initial lane based on the driving trajectory of the reference vehicle, and if it is determined that the behavior of the reference vehicle in the initial lane is a lane change behavior, the intersection point between the driving trajectory of the reference vehicle and the first boundary line during the process of the reference vehicle performing the lane change behavior is obtained.

[0087] In this embodiment, the target position information is determined on the initial lane based on the target intersection. Optionally, this embodiment can determine the target position information on the initial lane based on the intersection between the acquired driving trajectory and the first boundary line, that is, it can determine the position of the autonomous driving vehicle on the initial lane when performing diverging driving behavior or merging driving behavior, thereby achieving the purpose of determining the position of the autonomous driving vehicle on the initial lane when performing diverging driving behavior or merging driving behavior.

[0088] The method for determining the target position information on the initial lane based on the target intersection in this embodiment is further described below.

[0089] As an optional implementation method, based on the target intersection, the target position information is determined on the initial lane, including: traversing the points on the first boundary line starting from the target intersection according to the lane direction of the initial lane to obtain the traversed points; determining an area centered on the traversed points; in response to the intersection of the boundary line of the area with the second boundary line, determining the position information corresponding to the traversed points on the initial lane as the target position information.

[0090] In this embodiment, the lane direction may include: a first lane direction and a second lane direction. The traversed point may be used to represent a point on the boundary line of the initial lane that meets the divergence and merging characteristics. The second boundary line may be a boundary line on the target lane that is set opposite to the first boundary line. For example, the first lane direction may be the front side direction of the boundary line of the initial lane, and the second lane direction may be the rear side direction of the boundary line of the initial lane. This is only an example and is not specifically limited.

[0091] In this embodiment, in response to determining that the reference vehicle has changed lanes on the initial lane based on the driving trajectory, after obtaining the target intersection corresponding to the lane change behavior, the points on the first boundary line are traversed from the target intersection according to the lane direction of the initial lane to obtain the traversed points and determine the area centered on the traversed points. Optionally, the points on the first boundary line are traversed from the intersection between the driving trajectory and the first boundary line according to the lane direction of the initial lane, thereby determining the area centered on the traversed points.

[0092] In this embodiment, in response to the intersection of the boundary line of the area and the second boundary line, the position information corresponding to the traversed point on the initial lane is determined as the target position information. Optionally, this embodiment determines the relationship between the boundary line of the area and the second boundary line. If it is determined that the boundary line of the area intersects with the second boundary line, the position information corresponding to the traversed point on the initial lane can be determined as the target position information, thereby achieving the purpose of determining the position of the autonomous driving vehicle on the initial lane to perform diverging driving behavior or merging driving behavior.

[0093] The following further describes the method of determining the position information corresponding to the traversed point on the initial lane as the target position information in response to the intersection of the boundary line of the area and the second boundary line of the embodiment.

[0094] As an optional implementation method, in response to the intersection of the boundary line of the area and the second boundary line, the position information corresponding to the traversed point on the initial lane is determined as the target position information, including: in response to the intersection of the boundary line of the area and the second boundary line, and the second boundary line does not belong to the predecessor boundary line or the successor boundary line of the first boundary line, the position information corresponding to the traversed point on the initial lane is determined as the target position information.

[0095] In this embodiment, after determining the area centered on the traversed point, in response to the boundary line of the area intersecting with the second boundary line, and the second boundary line not belonging to the predecessor boundary line or the successor boundary line of the first boundary line, the position information corresponding to the traversed point on the initial lane is determined as the target position information. Optionally, this embodiment determines the relationship between the boundary line of the area and the second boundary line, and the relationship between the second boundary line and the first boundary line. If it is determined that the boundary line of the area intersects with the second boundary line, and the second boundary line does not belong to the predecessor boundary line or the successor boundary line of the first boundary line, the position information corresponding to the traversed point on the initial lane can be determined as the target position information, thereby achieving the purpose of determining the position of the autonomous driving vehicle on the initial lane to perform diverging driving behavior or merging driving behavior.

[0096] The method of traversing points on the first boundary line starting from the target intersection point according to the lane direction of the initial lane to obtain the traversed points in this embodiment is further described below.

[0097] As an optional implementation method, traversing points on the first boundary line starting from the target intersection point according to the lane direction of the initial lane to obtain the traversed points includes: traversing points on the first boundary line starting from the target intersection point according to the first lane direction and the second lane direction of the initial lane respectively to obtain the traversed points.

[0098] In this embodiment, the lane direction may include: a first lane direction and a second lane direction, and the first lane direction and the second lane direction may be opposite directions to each other. For example, the first lane direction may be the front side direction of the boundary line of the initial lane, and the second lane direction may be the rear side direction of the boundary line of the initial lane, which is only an example and not specifically limited.

[0099] In this embodiment, in response to the reference vehicle determining based on the driving trajectory that a lane change occurs in the initial lane, after obtaining the target intersection corresponding to the lane change behavior, the points on the first boundary line are traversed from the target intersection according to the first lane direction and the second lane direction of the initial lane, respectively, to obtain the traversed points. Optionally, based on obtaining the target intersection, the embodiment can traverse the points on the first boundary line from the target intersection according to the front side direction of the first boundary line and the rear side direction of the first boundary line, respectively, to obtain the traversed points, thereby achieving the purpose of traversing the points on the first boundary line.

[0100] The method of traversing points on the first boundary line starting from the target intersection according to the first lane direction and the second lane direction of the initial lane to obtain the traversed points in this embodiment is further described below.

[0101] As an optional implementation method, traversing points on the first boundary line from the target intersection according to the first lane direction and the second lane direction of the initial lane respectively to obtain the traversed points, including: determining a first length range and a second length range corresponding to the divergence driving scenario; traversing points within a first length range on the first boundary line from the target intersection according to the first lane direction to obtain the traversed points; traversing points within a second length range on the first boundary line from the target intersection according to the second lane direction to obtain the traversed points.

[0102] In this embodiment, the second length range with the target intersection as the endpoint may be greater than the first length range with the target intersection as the endpoint. For example, the second length range may be 15m and the first length range may be 4m, which is only used as an example and is not specifically limited.

[0103] In this embodiment, in response to determining that the reference vehicle changes lanes in the initial lane based on the driving trajectory, after obtaining the target intersection corresponding to the lane change behavior, the first length range and the second length range corresponding to the diverging driving scenario are determined. Optionally, based on the determination of the diverging driving scenario, the corresponding first length range and the second length range with the target intersection as the endpoint can be determined.

[0104] In this embodiment, the points within the first length range on the first boundary line are traversed from the target intersection point according to the first lane direction to obtain the traversed points. Alternatively, the points within the first length range on the first boundary line can be traversed from the target intersection point according to the front side direction of the first boundary line to obtain the traversed points, thereby achieving the purpose of traversing the points on the first boundary line.

[0105] In this embodiment, the points within the second length range on the first boundary line are traversed from the target intersection point according to the second lane direction to obtain the traversed points. Alternatively, in this embodiment, the points within the second length range on the first boundary line can be traversed from the target intersection point according to the rear side direction of the first boundary line to obtain the traversed points, thereby achieving the purpose of traversing the points on the first boundary line.

[0106] The following is a further description of the method for creating the above-mentioned autonomous driving scenario of this embodiment.

[0107] As an optional embodiment, the method further includes: in response to the second length range including points on a predecessor boundary line of the first boundary line, traversing points on the predecessor boundary line of the first boundary line to obtain the traversed points.

[0108] In this embodiment, in response to the second length range including points on the predecessor boundary line of the first boundary line, the points on the predecessor boundary line of the first boundary line are traversed to obtain the traversed points. Optionally, the relationship between the second length range and the length of the first boundary line is judged. If it is judged that the second length range exceeds the length of the first boundary line, it means that the second length range can include points on the predecessor boundary line of the first boundary line. In the case that the second length range can include points on the predecessor boundary line of the first boundary line, the points on the predecessor boundary line of the first boundary line are traversed to obtain the traversed points, thereby achieving the purpose of ensuring the comprehensiveness of scene recognition.

[0109] In this embodiment, the relationship between the detection distance and the length of the boundary line of the initial lane is judged. If it is judged that the detection distance exceeds the length of the boundary line of the initial lane, the points on the predecessor boundary line of the boundary line of the initial lane continue to be detected, thereby achieving the purpose of ensuring the comprehensiveness of scene recognition.

[0110] The method of traversing points on the first boundary line starting from the target intersection according to the first lane direction and the second lane direction of the initial lane to obtain the traversed points in this embodiment is further described below.

[0111] As an optional implementation method, the points on the first boundary line are traversed from the target intersection according to the first lane direction and the second lane direction of the initial lane respectively to obtain the traversed points, including: determining a third length range and a fourth length range corresponding to the merging driving scenario; traversing the points within the third length range on the first boundary line from the target intersection according to the first lane direction to obtain the traversed points; traversing the points within the fourth length range on the first boundary line from the target intersection according to the second lane direction to obtain the traversed points.

[0112] In this embodiment, the fourth length range with the target intersection as the endpoint may be smaller than the third length range with the target intersection as the endpoint. For example, the third length range may be 15m, and the fourth length range may be 4m, which is only used as an example and is not specifically limited.

[0113] In this embodiment, in response to determining that the reference vehicle changes lanes in the initial lane based on the driving trajectory, after obtaining the target intersection corresponding to the lane change behavior, the third length range and the fourth length range corresponding to the merging driving scene are determined. Optionally, based on the determination of the merging driving scene, the corresponding third length range and the fourth length range with the target intersection as the endpoint can be determined.

[0114] In this embodiment, points within the third length range on the first boundary line are traversed from the target intersection point according to the first lane direction. Alternatively, in this embodiment, points within the third length range on the first boundary line can be traversed from the target intersection point according to the front side direction of the first boundary line, and the traversed points can be obtained, thereby achieving the purpose of traversing the points on the first boundary line.

[0115] In this embodiment, points within the fourth length range on the first boundary line are traversed from the target intersection point according to the second lane direction. Alternatively, in this embodiment, points within the fourth length range on the first boundary line can be traversed from the target intersection point according to the rear side direction of the first boundary line, and the traversed points can be obtained, thereby achieving the purpose of traversing the points on the first boundary line.

[0116] The following is a further description of the method for creating the above-mentioned autonomous driving scenario of this embodiment.

[0117] As an optional embodiment, the method further includes: in response to the third length range including points on a predecessor boundary line of the first boundary line, traversing points on the predecessor boundary line of the first boundary line to obtain the traversed points.

[0118] In this embodiment, in response to the third length range including points on the predecessor boundary line of the first boundary line, the points on the predecessor boundary line of the first boundary line are traversed to obtain the traversed points. Optionally, the relationship between the third length range and the length of the first boundary line is judged. If it is judged that the third length range exceeds the length of the first boundary line, it means that the third length range can include points on the predecessor boundary line of the first boundary line. In the case where the third length range can include points on the predecessor boundary line of the first boundary line, the points on the predecessor boundary line of the boundary line of the initial lane are traversed to obtain the traversed points.

[0119] In this embodiment, the relationship between the detection distance and the length of the boundary line of the initial lane is judged. If it is judged that the detection distance exceeds the length of the boundary of the initial lane, the points on the predecessor boundary line of the boundary line of the initial lane continue to be detected, thereby achieving the purpose of ensuring the comprehensiveness of scene recognition.

[0120] The method for determining the area centered on the traversed point described above in this embodiment is further described below.

[0121] As an optional implementation manner, determining an area centered on the traversed point includes: determining a circular area centered on the traversed point.

[0122] In this embodiment, a circular area centered on the traversed point is determined. Optionally, the traversed point on the initial lane is set as the center of the circle, and the preset threshold is set as the radius of the circle, so that a circular area centered on the traversed point can be obtained. The preset threshold can be, but is not limited to, 2, which is only used as an example and is not specifically limited.

[0123] The following further describes the method for creating an autonomous driving scene for an autonomous driving vehicle based on target position information and lane information in this embodiment.

[0124] As an optional implementation method, step S106 creates an autonomous driving scene for an autonomous driving vehicle based on the target position information and lane information, including: determining a sub-boundary line between a point corresponding to the target position information and the target intersection point on the first boundary line; and creating an autonomous driving scene based on the sub-boundary line and the lane information.

[0125] In this embodiment, in response to determining that the reference vehicle has changed lanes in the initial lane based on the driving trajectory, after determining the target position information in the initial lane based on the lane change behavior, a sub-boundary line between the point corresponding to the target position information and the target intersection is determined on the first boundary line. Optionally, this embodiment can determine a sub-boundary line between the point corresponding to the target position information and the target intersection on the common boundary line between the initial lane and the target lane based on the determination of the target position information.

[0126] In this embodiment, an autonomous driving scene is created based on the sub-boundary line and lane information. Optionally, this embodiment can create an autonomous driving scene for an autonomous driving vehicle based on the determined sub-boundary line, lane information of the initial lane, and lane information of the target lane. For example, by connecting the target lane with the initial lane using the sub-boundary line between the point corresponding to the target position information and the target intersection, an autonomous driving scene for an autonomous driving vehicle can be obtained, thereby achieving the purpose of being able to adapt to changing road conditions.

[0127] The following further describes the method for creating an autonomous driving scene based on the above-mentioned boundary line and lane information of this embodiment.

[0128] As an optional implementation method, an autonomous driving scene is created based on sub-boundary lines and lane information, including: using sub-boundary lines to associate lane information to obtain an autonomous driving scene.

[0129] In this embodiment, the above-mentioned autonomous driving vehicle can be used in a diverging driving scenario in an autonomous driving scenario to perform diverging driving behavior to diverge from the initial lane to the target lane via the sub-boundary line, or the autonomous driving vehicle can be used in a merging driving scenario in an autonomous driving scenario to perform merging driving behavior to merge from the target lane to the initial lane via the sub-boundary line.

[0130] In this embodiment, in response to determining that the reference vehicle changes lanes in the initial lane based on the driving trajectory, after determining the target position information in the initial lane based on the lane change behavior, the lane information is associated with the sub-boundary line to obtain the autonomous driving scene. Optionally, this embodiment deletes the sub-boundary line between the point corresponding to the target position information and the target intersection point, and connects the target lane with the initial lane, so as to obtain the autonomous driving scene of the autonomous driving vehicle, thereby achieving the purpose of being able to adapt to changing road conditions.

[0131] The method of obtaining an autonomous driving scene by associating lane information with sub-boundary lines in this embodiment is further described below.

[0132] As an optional implementation method, sub-boundary lines are used to associate lane information to obtain an autonomous driving scene, including: in response to the length of the sub-boundary line being within a fifth length range, the sub-boundary line is used to associate the target lane and the initial lane to obtain an autonomous driving scene.

[0133] In this embodiment, the fifth length range may be used to limit the length of the sub-boundary line. For example, the fifth length range may be, but is not limited to, 30 m. This is merely an example and is not specifically limited thereto.

[0134] In this embodiment, in response to the length of the sub-boundary line being within the fifth length range, the target lane and the initial lane are associated with the sub-boundary line to obtain an autonomous driving scene. Optionally, this embodiment determines the relationship between the length of the sub-boundary line and the fifth length range. If it is determined that the length of the sub-boundary line is within the fifth length range, the sub-boundary line between the point corresponding to the target position information and the target intersection is deleted, and the target lane and the initial lane are connected, so that the autonomous driving scene of the autonomous driving vehicle can be obtained, thereby achieving the purpose of being able to adapt to changing road conditions.

[0135] The following is a further description of the method for creating the above-mentioned autonomous driving scenario of this embodiment.

[0136] As an optional embodiment, the method further includes: in response to the presence of a target intersection between the driving trajectory and the first boundary line, determining that the reference vehicle has changed lanes in the initial lane.

[0137] In this embodiment, in response to the existence of a target intersection point between the driving trajectory and the first boundary line, it is determined that the reference vehicle has changed lanes in the initial lane. Optionally, based on the acquired driving trajectory, this embodiment determines whether there is a target intersection point between the acquired driving trajectory and the first boundary line. If it is determined that there is a target intersection point between the acquired driving trajectory and the first boundary line, it can be determined that the reference vehicle has changed lanes in the initial lane.

[0138] The method of determining that the reference vehicle has changed lanes in the initial lane in response to the presence of a target intersection between the driving trajectory and the first boundary line in this embodiment is further described below.

[0139] As an optional implementation method, in response to the presence of a target intersection between a driving trajectory and a first boundary line, determining that a reference vehicle has changed lanes in an initial lane includes: dividing the driving trajectory into a plurality of sub-driving trajectories; and in response to the presence of a target intersection between a sub-driving trajectory and the first boundary line, determining that a reference vehicle has changed lanes in an initial lane.

[0140] In this embodiment, the driving track is divided into a plurality of sub-driving tracks. Optionally, in this embodiment, the driving track can be divided into a plurality of sub-driving tracks (eg, a plurality of driving track segments) according to a time sequence or a driving distance interval.

[0141] In this embodiment, in response to the existence of a target intersection point between the sub-driving track and the first boundary line, it is determined that the reference vehicle has changed lanes in the initial lane. Optionally, this embodiment determines whether there are target intersection points between the multiple sub-driving tracks obtained by division and the first boundary line. If it is determined that there are target intersection points between the multiple sub-driving tracks obtained by division and the first boundary line, it can be determined that the reference vehicle has changed lanes in the initial lane.

[0142] The following is a further description of the method for creating the above-mentioned autonomous driving scenario of this embodiment.

[0143] As an optional implementation mode, the method also includes: determining a driving trajectory of the autonomous driving vehicle in the autonomous driving scenario.

[0144] In this embodiment, based on the creation of the autonomous driving scene, a driving trajectory of the autonomous driving vehicle in the autonomous driving scene corresponding to the driving trajectory of the reference vehicle can be generated according to the driving trajectory of the reference vehicle.

[0145] In an embodiment of the present invention, when creating an autonomous driving scene, the driving trajectory of a reference vehicle traveling on an initial lane may be obtained. Based on the obtained driving trajectory, the driving behavior of the reference vehicle on the initial lane may be determined. The driving behavior of the reference vehicle on the initial lane is judged, and if it is judged that the driving behavior of the reference vehicle on the initial lane is a lane change behavior, the target position information may be determined on the initial lane according to the lane change behavior. According to the target position information determined on the initial lane, and the lane information, an autonomous driving scene of the autonomous driving vehicle may be created. That is, since the embodiment of the present application can determine the driving behavior of the reference vehicle on the initial lane according to the driving trajectory of the reference vehicle obtained, and in the case where the above-mentioned driving behavior is a lane change behavior, the target position information determined according to the lane change behavior, and the lane information, an autonomous driving scene may be created, and since the embodiment of the present application determines the driving behavior of the reference vehicle on the initial lane according to the driving trajectory of the reference vehicle, the obtained driving trajectory may include rich behavioral characteristics and preference information of the reference vehicle, thereby achieving the purpose of adapting the process of creating the autonomous driving scene to the changing road conditions, thereby solving the technical problem of low flexibility of the autonomous driving scene, and further achieving the technical effect of improving the flexibility of the autonomous driving scene.

[0146] Example 2

[0147] The technical solution of the embodiment of the present invention is illustrated below in conjunction with preferred implementation modes.

[0148] At present, the road divergence and road merging technologies for autonomous driving vehicles mainly rely on pre-designed road models, road structure characteristics, and specific traffic rules algorithms. However, such road divergence and road merging technologies are not only difficult to adapt to changing road conditions, but also cause limitations when constructing road divergence and road merging scenarios, resulting in low flexibility in creating autonomous driving scenarios.

[0149] However, an embodiment of the present invention proposes a method for creating an autonomous driving scene. By recording and analyzing the user's driving trajectory, when the user changes lanes, the method finds feature points that meet the divergence and merging characteristics on the lane boundary line, and creates a new divergence or merging scene based on the divergence and merging feature points, thereby achieving the purpose of adapting to changing road conditions, thereby solving the technical problem of low flexibility of autonomous driving scenes, and further achieving the technical effect of improving the flexibility of autonomous driving scenes.

[0150] In this embodiment, FIG. 2( a) is a flowchart of a method for creating an autonomous driving scene according to an embodiment of the present invention. The method for creating an autonomous driving scene may include the following steps:

[0151] Step S201, recording and processing the driving trajectory of the reference vehicle.

[0152] In the technical solution provided in the above step S201 of the present invention, the driving trajectory of the reference vehicle (for example, the driving trajectory of the vehicle driven by the user) is uploaded to the cloud in real time, and the map is built based on the uploaded driving trajectory. In addition, the driving trajectory is divided into multiple trajectory segments according to the time series or distance interval, providing a basis for the next step of scene construction.

[0153] After recording and processing the driving trajectory of the reference vehicle, the process proceeds to step S202 to interactively analyze the driving trajectory of the reference vehicle and the boundary line of the initial lane and the boundary line of the target lane.

[0154] In the technical solution provided in step S202 of the present invention, the trajectory segments are traversed one by one to determine whether there is an intersection with the boundary line of the initial lane. If there is an intersection with the boundary line of the initial lane, it means that the autonomous driving vehicle has changed lanes, and it is necessary to further determine whether there is a road divergence or merging.

[0155] After interactively analyzing the driving trajectory of the reference vehicle and the boundary lines of the initial lane and the target lane, the process proceeds to step S203 to determine points on the boundary lines of the initial lane that meet the divergence and merging characteristics, thereby creating a new divergence or merging scene.

[0156] In the technical solution provided in S203 of the present invention, the lane changing scenario of the autonomous driving vehicle may be as shown in FIG2( b ), which is a schematic diagram of a vehicle lane changing scenario according to an embodiment of the present invention.

[0157] In this embodiment, from the intersection point where the driving trajectory intersects with the boundary line of the initial lane, the detection is performed in the forward and backward directions along the boundary line of the initial lane until a point on the boundary line of the initial lane that meets the divergence and merging characteristics is found. Among them, the point that meets the divergence and merging characteristics can be: a circle with a radius of 2 and a traversed point on the boundary line of the initial lane as the center. If the circle circles to other boundary lines, and the boundary line does not belong to the current boundary or its predecessor and successor. According to the obtained feature points, the boundary line of the initial lane is adjusted, the section from the intersection to the feature point on the boundary line of the initial lane is deleted, and the adjacent initial lane and target lane are connected, so that a new divergence or merging scene can be created.

[0158] It should be noted that the following restrictions are imposed on the distance of detecting diverging and converging points and the length of deleting boundaries: 4 meters can be deleted upwards, 15 meters can be found downwards, and a maximum of 30 meters can be deleted. If the current boundary length does not reach the detection distance, the previous boundary will continue to be detected, thereby achieving the purpose of ensuring the comprehensiveness of scene recognition.

[0159] In this embodiment, a new divergence or merging scene can be created by the server, and the created new divergence or merging scene can be sent to the vehicle. For example, FIG2(c) is a schematic diagram of data interaction between a vehicle and a server according to an embodiment of the present invention. As shown in FIG2(c), the autonomous driving vehicle 210 can upload its driving trajectory on the initial lane to the server 211. When the server 211 receives the driving trajectory, the driving behavior of the reference vehicle on the initial lane can be determined according to the driving trajectory. The server 211 judges the driving behavior of the reference vehicle on the initial lane. If it is determined that the driving behavior of the reference vehicle on the initial lane is a lane change behavior, the target position information can be determined on the initial lane according to the lane change behavior. The server 211 can create an autonomous driving scene of the autonomous driving vehicle based on the target position information determined on the initial lane and the lane information, and send the created autonomous driving scene to the autonomous driving vehicle 210.

[0160] In this embodiment, after recording and processing the driving trajectory of the reference vehicle, the driving trajectory of the reference vehicle is interactively analyzed with the boundary lines of the initial lane and the target lane to determine the points on the boundary lines of the initial lane that meet the divergence and merging characteristics, thereby creating a new divergence or merging scene, thereby achieving the purpose of adapting to changing road conditions, thereby solving the technical problem of low flexibility of the autonomous driving scene, and further achieving the technical effect of improving the flexibility of the autonomous driving scene.

[0161] Example 3

[0162] According to another aspect of an embodiment of the present invention, corresponding to the embodiment of the method for creating an autonomous driving scene, this specification also provides a system for creating an autonomous driving scene. Figure 3 is a structural block diagram of a system for creating an autonomous driving scenario according to an embodiment of the present invention. Figure 3 As shown, the system 300 for creating the autonomous driving scenario may include: a reference vehicle 302 and a server 304 .

[0163] Reference vehicle 302 is used to upload a driving trajectory traveling in an initial lane.

[0164] Server 304 is used to respond to a reference vehicle determined to have changed lanes in an initial lane based on a driving trajectory, and determine target position information in the initial lane based on the lane changing behavior, wherein the lane changing behavior is used to indicate the behavior of the reference vehicle changing lanes from the initial lane to the target lane, and the target position information is used to indicate a position in the initial lane where the autonomous driving vehicle corresponding to the reference vehicle is allowed to perform diverging driving behavior or merging driving behavior; based on the target position information and the lane information, create an autonomous driving scenario for the autonomous driving vehicle, wherein the lane information includes: lane information of the initial lane and lane information of the target lane, and the autonomous driving scenario includes a diverging driving scenario corresponding to the diverging driving behavior, or a merging driving scenario corresponding to the merging driving behavior.

[0165] In the technical solution provided by the system 300 for creating the above-mentioned autonomous driving scene of the present invention, the above-mentioned reference vehicle can be used to represent an actual vehicle in an actual application scene, which can be an actual vehicle traveling in a historical period, or an actual vehicle in a driving state in a current period. The above-mentioned server can be used to represent a local server or a cloud server. For example, the above-mentioned server can be, but is not limited to, a cloud server, etc., which is only used as an example here and is not specifically limited.

[0166] In this embodiment, when creating an autonomous driving scene, the reference vehicle can upload the driving trajectory of the reference vehicle traveling on the initial lane to the server through the reference vehicle. When the server receives the driving trajectory, the server can determine the driving behavior of the reference vehicle on the initial lane based on the acquired driving trajectory. The driving behavior of the reference vehicle on the initial lane is judged, and if it is judged that the driving behavior of the reference vehicle on the initial lane is a lane change behavior, the target position information can be determined on the initial lane according to the lane change behavior. That is to say, since the embodiment of the present application can determine the driving behavior of the reference vehicle on the initial lane according to the acquired driving trajectory of the reference vehicle, and in the case where the above-mentioned driving behavior is a lane change behavior, the target position information determined according to the lane change behavior, and the lane information, the autonomous driving scene can be created, and since the embodiment of the present application determines the driving behavior of the reference vehicle on the initial lane based on the driving trajectory of the reference vehicle, the acquired driving trajectory can include rich behavioral characteristics and preference information of the reference vehicle, thereby achieving the purpose of adapting to the changing road conditions in the process of creating the autonomous driving scene, thereby solving the technical problem of low flexibility of the autonomous driving scene, and then achieving the technical effect of improving the flexibility of the autonomous driving scene.

[0167] Example 4

[0168] According to another aspect of an embodiment of the present invention, corresponding to the embodiment of the method for creating an autonomous driving scene, this specification also provides a device for creating an autonomous driving scene. Figure 4 is a structural block diagram of a device for creating an autonomous driving scene according to an embodiment of the present invention. Figure 4 As shown, the device 400 for creating the autonomous driving scenario may include: an acquisition unit 402 , a determination unit 404 and a creation unit 406 .

[0169] The acquisition unit 402 is used to acquire the driving trajectory of the reference vehicle traveling on the initial lane.

[0170] The determination unit 404 is used to respond to the lane change behavior of the reference vehicle determined based on the driving trajectory in the initial lane, and determine the target position information on the initial lane based on the lane change behavior, wherein the lane change behavior is used to indicate the behavior of the reference vehicle changing lanes from the initial lane to the target lane, and the target position information is used to indicate the position of the automatic driving vehicle corresponding to the reference vehicle in the initial lane to allow the automatic driving vehicle to perform diverging driving behavior or merging driving behavior.

[0171] The creation unit 406 is used to create an autonomous driving scenario for the autonomous driving vehicle based on the target position information and the lane information, wherein the lane information includes lane information of the initial lane and lane information of the target lane, and the autonomous driving scenario includes a diverging driving scenario corresponding to the diverging driving behavior, or a merging driving scenario corresponding to the merging driving behavior.

[0172] Optionally, the determination unit 404 includes: an acquisition module, used to acquire a target intersection point corresponding to the lane changing behavior in response to determining that the reference vehicle has changed lanes in the initial lane based on the driving trajectory, wherein the target intersection point is used to represent the intersection point between the driving trajectory and the first boundary line when the reference vehicle is performing the lane changing behavior, and the first boundary line is the common boundary line between the initial lane and the target lane; a first determination module, used to determine the target position information on the initial lane based on the target intersection point.

[0173] Optionally, the first determination module includes: a traversal submodule, used to traverse the points on the first boundary line starting from the target intersection point according to the lane direction of the initial lane to obtain the traversed points; a second determination submodule, used to determine the position information corresponding to the traversed points on the initial lane as the target position information in response to the intersection of the boundary line of the area with the second boundary line, wherein the second boundary line is a boundary line on the target lane set opposite to the first boundary line.

[0174] Optionally, the second determination submodule determines the position information corresponding to the traversed point on the initial lane as the target position information in response to the intersection of the boundary line of the area with the second boundary line by executing the following steps: In response to the intersection of the boundary line of the area with the second boundary line, and the second boundary line does not belong to the predecessor boundary line or the successor boundary line of the first boundary line, the position information corresponding to the traversed point on the initial lane is determined as the target position information.

[0175] Optionally, the traversal submodule traverses the points on the first boundary line starting from the target intersection according to the lane direction of the initial lane by executing the following steps to obtain the traversed points: traverse the points on the first boundary line starting from the target intersection according to the first lane direction and the second lane direction of the initial lane, respectively, wherein the first lane direction and the second lane direction are in opposite directions to each other.

[0176] Optionally, the traversal submodule traverses the points on the first boundary line starting from the target intersection according to the first lane direction and the second lane direction of the initial lane, respectively, to obtain the traversed points by executing the following steps: determine a first length range and a second length range corresponding to the divergence driving scenario, wherein the second length range with the target intersection as the endpoint is greater than the first length range with the target intersection as the endpoint; traverse the points within the first length range on the first boundary line starting from the target intersection according to the first lane direction to obtain the traversed points; traverse the points within the second length range on the first boundary line starting from the target intersection according to the second lane direction to obtain the traversed points.

[0177] Optionally, the automatic driving scene creation device 400 further includes: a first traversal unit, configured to respond to the second length range including the points on the predecessor boundary line of the first boundary line, traverse the points on the predecessor boundary line of the first boundary line, and obtain the traversed points

[0178] Optionally, the traversal submodule also traverses the points on the first boundary line starting from the target intersection according to the first lane direction and the second lane direction of the initial lane, respectively, to obtain the traversed points by executing the following steps: determine a third length range and a fourth length range corresponding to the merging driving scenario, wherein the fourth length range with the target intersection as the endpoint is smaller than the third length range with the target intersection as the endpoint; traverse the points within the third length range on the first boundary line starting from the target intersection in the first lane direction to obtain the traversed points; traverse the points within the fourth length range on the first boundary line starting from the target intersection in the second lane direction to obtain the traversed points.

[0179] Optionally, the device 400 for creating an autonomous driving scene also includes: a second traversal unit, used to traverse the points on the predecessor boundary line of the first boundary line in response to the third length range including the points on the predecessor boundary line of the first boundary line, to obtain the traversed points.

[0180] Optionally, the creation unit 406 includes: a second determination module, used to determine the sub-boundary line between the point corresponding to the target position information and the target intersection point on the first boundary line; and a creation module, used to create an autonomous driving scene based on the sub-boundary line and lane information.

[0181] Optionally, the creation module includes: an association submodule, used to associate lane information with the sub-boundary line to obtain an autonomous driving scenario, wherein the autonomous driving vehicle is used to perform a diverging driving behavior in a diverging driving scenario in the autonomous driving scenario to diverge from the initial lane to the target lane via the sub-boundary line, or the autonomous driving vehicle is used to perform a merging driving behavior in a merging driving scenario in the autonomous driving scenario to merge from the target lane to the initial lane via the sub-boundary line.

[0182] Optionally, the association submodule uses the sub-boundary line to associate lane information to obtain an autonomous driving scenario by performing the following steps: in response to the length of the sub-boundary line being within a fifth length range, using the sub-boundary line to associate the target lane and the initial lane to obtain an autonomous driving scenario.

[0183] Optionally, the device 400 for creating the autonomous driving scenario also includes: a first determination unit, for determining that the reference vehicle has changed lanes in the initial lane in response to the presence of a target intersection between the driving trajectory and the first boundary line, wherein the first boundary line is a common boundary between the initial lane and the target lane.

[0184] Optionally, the first determination unit includes: a division module for dividing the driving trajectory into multiple sub-driving trajectories; and a third determination module for determining that the reference vehicle has changed lanes in the initial lane in response to the presence of a target intersection between the sub-driving trajectory and the first boundary line.

[0185] Optionally, the device 400 for creating an autonomous driving scene also includes: a second determination unit, used to determine a driving trajectory of the autonomous driving vehicle in the autonomous driving scene.

[0186] In this embodiment, the following units are provided in the device for creating an autonomous driving scene: an acquisition unit for acquiring a driving trajectory of a reference vehicle traveling on an initial lane; a determination unit for responding to a lane change behavior determined based on the driving trajectory of the reference vehicle on the initial lane, and determining target position information on the initial lane based on the lane change behavior, wherein the lane change behavior is used to indicate the behavior of the reference vehicle changing lanes from the initial lane to the target lane, and the target position information is used to indicate the position at which the autonomous driving vehicle corresponding to the reference vehicle is allowed to perform a diverging driving behavior or a merging driving behavior on the initial lane; a creation unit for creating an autonomous driving scene of the autonomous driving vehicle based on the target position information and the lane information, wherein the lane information includes the lane information of the initial lane and the lane information of the target lane, and the autonomous driving scene includes a diverging driving scene corresponding to the diverging driving behavior, or a merging driving scene corresponding to the merging driving behavior, thereby achieving the purpose of adapting the process of creating the autonomous driving scene to changing road conditions, thereby solving the technical problem of low flexibility of the autonomous driving scene, and further achieving the technical effect of improving the flexibility of the autonomous driving scene.

[0187] Example 5

[0188] According to another aspect of an embodiment of the present invention, there is also provided an autonomous driving vehicle, comprising: a memory storing an executable program; and a processor running the program, wherein the program executes any one of the above methods when running.

[0189] Figure 5is a structural block diagram of an automatic driving vehicle according to an embodiment of the present invention. Figure 5 As shown, the components of the autonomous driving vehicle 500 include but are not limited to a memory 510 and a processor 520. The processor 520 is connected to the memory 510 via a bus 530, and the database 550 is used to store data.

[0190] The autonomous vehicle 500 may also include an access device 540 that enables the autonomous vehicle 500 to communicate via one or more networks 560. Examples of these networks include a Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the Internet. The access device 540 may include one or more of any type of network interface (e.g., a network interface controller (NIC)) of wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, a Near Field Communication (NFC) interface, and the like.

[0191] In one embodiment of the present disclosure, the above components of the autonomous driving vehicle 500 and Figure 5 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 5 The structure block diagram of the autonomous driving vehicle shown is for illustrative purposes only and is not intended to limit the scope of the present disclosure. Those skilled in the art may add or replace other components as needed.

[0192] Example 6

[0193] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium including a stored executable program, wherein when the executable program runs, the device where the storage medium is located is controlled to execute any one of the above methods.

[0194] Example 7

[0195] According to another aspect of an embodiment of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, any one of the above methods is implemented.

[0196] It should be noted that the serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0197] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0198] In the several embodiments provided by the present invention, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic, for example, the division of units can be a logical function division, and there can be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0199] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0200] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0201] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, referred to as Read-Only Memory), random access memory (RAM, referred to as Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc., which can store program code.

[0202] The above are only preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for creating an autonomous driving scenario, characterized in that: include: Obtaining a driving trajectory of a reference vehicle traveling on an initial lane; In response to determining that the reference vehicle has changed lanes in the initial lane based on the driving trajectory, determining target position information in the initial lane based on the lane change behavior, wherein the lane change behavior is used to indicate the behavior of the reference vehicle changing lanes from the initial lane to the target lane, and the target position information is used to indicate a position where the autonomous driving vehicle corresponding to the reference vehicle is allowed to perform a diverging driving behavior or a merging driving behavior in the initial lane; Based on the target position information and the lane information, an autonomous driving scenario of the autonomous driving vehicle is created, wherein the lane information includes: lane information of the initial lane and lane information of the target lane, and the autonomous driving scenario includes a diverging driving scenario corresponding to the diverging driving behavior, or a merging driving scenario corresponding to the merging driving behavior; Wherein, in response to determining that the reference vehicle has changed lanes on the initial lane based on the driving trajectory, determining target position information on the initial lane based on the lane changing behavior includes: in response to determining that the reference vehicle has changed lanes on the initial lane based on the driving trajectory, obtaining a target intersection corresponding to the lane changing behavior, wherein the target intersection is used to represent the intersection between the driving trajectory and a first boundary line when the reference vehicle is performing the lane changing behavior, and the first boundary line is a common boundary line between the initial lane and the target lane; traversing points on the first boundary line starting from the target intersection according to the lane direction of the initial lane to obtain the traversed points; determining an area centered on the traversed points; and based on the relationship between the boundary line of the area and a second boundary line, determining the position information corresponding to the traversed points on the initial lane as the target position information, wherein the second boundary line is a boundary line on the target lane set opposite to the first boundary line.

2. The method according to claim 1, characterized in that Based on the relationship between the boundary line of the area and the second boundary line, determining the position information corresponding to the traversed point on the initial lane as the target position information includes: In response to the relationship indicating that the boundary line of the area intersects with the second boundary line, the position information corresponding to the traversed point on the initial lane is determined as the target position information.

3. The method according to claim 2, characterized in that In response to the relationship indicating that the boundary line of the area intersects with the second boundary line, determining the position information corresponding to the traversed point on the initial lane as the target position information, including: In response to the relationship indicating that the boundary line of the area intersects with the second boundary line, and the second boundary line does not belong to the predecessor boundary line or the successor boundary line of the first boundary line, the position information corresponding to the traversed point on the initial lane is determined as the target position information.

4. The method according to claim 1, characterized in that According to the lane direction of the initial lane, traversing points on the first boundary line from the target intersection point to obtain the traversed points includes: The points on the first boundary line are traversed starting from the target intersection according to the first lane direction and the second lane direction of the initial lane respectively, to obtain the traversed points, wherein the first lane direction and the second lane direction are opposite directions to each other.

5. The method according to claim 4, characterized in that Traversing points on the first boundary line from the target intersection point according to the first lane direction and the second lane direction of the initial lane respectively, to obtain the traversed points, includes: Determining a first length range and a second length range corresponding to the diverging driving scenario, wherein the second length range with the target intersection as an endpoint is greater than the first length range with the target intersection as an endpoint; Traversing points within the first length range on the first boundary line starting from the target intersection point in the first lane direction to obtain the traversed points; According to the second lane direction, points within the second length range on the first boundary line are traversed from the target intersection point to obtain the traversed points.

6. The method according to claim 5, characterized in that The method further comprises: In response to the second length range including points on a predecessor boundary line of the first boundary line, the points on the predecessor boundary line of the first boundary line are traversed to obtain the traversed points.

7. The method according to claim 4, characterized in that Traversing points on the first boundary line from the target intersection point according to the first lane direction and the second lane direction of the initial lane respectively, to obtain the traversed points, includes: Determining a third length range and a fourth length range corresponding to the merging driving scene, wherein the fourth length range with the target intersection as an endpoint is smaller than the third length range with the target intersection as an endpoint; Traversing points within the third length range on the first boundary line starting from the target intersection point in the first lane direction to obtain the traversed points; According to the second lane direction, points within the fourth length range on the first boundary line are traversed from the target intersection point to obtain the traversed points.

8. The method according to claim 7, characterized in that The method further comprises: In response to the third length range including points on a predecessor boundary line of the first boundary line, the points on the predecessor boundary line of the first boundary line are traversed to obtain the traversed points.

9. The method according to claim 1, characterized in that: Creating an autonomous driving scenario for the autonomous driving vehicle based on the target position information and the lane information includes: On the first boundary line, determining a sub-boundary line between the point corresponding to the target position information and the target intersection point; The autonomous driving scenario is created based on the sub-boundary line and the lane information.

10. The method according to claim 9, characterized in that Creating the autonomous driving scenario based on the sub-boundary line and the lane information includes: The lane information is associated with the sub-boundary line to obtain the autonomous driving scenario, wherein the autonomous driving vehicle is used to perform the diverging driving behavior in the diverging driving scenario in the autonomous driving scenario to diverge from the initial lane to the target lane via the sub-boundary line, or the autonomous driving vehicle is used to perform the merging driving behavior in the merging driving scenario in the autonomous driving scenario to merge from the target lane to the initial lane via the sub-boundary line.

11. The method according to claim 10, characterized in that The lane information is associated with the sub-boundary line to obtain the autonomous driving scenario, including: In response to the length of the sub-boundary line being within a fifth length range, the target lane and the initial lane are associated with the sub-boundary line to obtain the autonomous driving scenario.

12. The method according to any one of claims 1 to 11, characterized in that The method further comprises: In response to the presence of a target intersection between the driving trajectory and a first boundary line, it is determined that the reference vehicle has performed the lane change behavior in the initial lane, wherein the first boundary line is a common boundary between the initial lane and the target lane.

13. The method according to claim 12, characterized in that In response to the presence of a target intersection between the driving trajectory and the first boundary line, determining that the reference vehicle has performed the lane change behavior in the initial lane includes: Dividing the driving trajectory into a plurality of sub-driving trajectories; In response to the target intersection between the sub-driving trajectory and the first boundary line, it is determined that the reference vehicle has performed the lane change behavior in the initial lane.

14. A system for creating an autonomous driving scenario, characterized in that: include: The reference vehicle is used to upload the driving trajectory on the initial lane; A server, configured to respond to a determination based on the driving trajectory that the reference vehicle has changed lanes in the initial lane, and determine target position information in the initial lane based on the lane change behavior, wherein the lane change behavior is used to indicate the behavior of the reference vehicle changing lanes from the initial lane to the target lane, and the target position information is used to indicate a position at which the autonomous driving vehicle corresponding to the reference vehicle is allowed to perform a diverging driving behavior or a merging driving behavior in the initial lane; and to create an autonomous driving scenario for the autonomous driving vehicle based on the target position information and the lane information, wherein the lane information includes: lane information of the initial lane and lane information of the target lane, and the autonomous driving scenario includes a diverging driving scenario corresponding to the diverging driving behavior, or a merging driving scenario corresponding to the merging driving behavior; Wherein, in response to determining that the reference vehicle has changed lanes on the initial lane based on the driving trajectory, determining target position information on the initial lane based on the lane changing behavior includes: in response to determining that the reference vehicle has changed lanes on the initial lane based on the driving trajectory, obtaining a target intersection corresponding to the lane changing behavior, wherein the target intersection is used to represent the intersection between the driving trajectory and a first boundary line when the reference vehicle is performing the lane changing behavior, and the first boundary line is a common boundary line between the initial lane and the target lane; traversing points on the first boundary line starting from the target intersection according to the lane direction of the initial lane to obtain the traversed points; determining an area centered on the traversed points; and based on the relationship between the boundary line of the area and a second boundary line, determining the position information corresponding to the traversed points on the initial lane as the target position information, wherein the second boundary line is a boundary line on the target lane set opposite to the first boundary line.

15. A device for creating an autonomous driving scene, characterized in that: include: an acquisition unit, used for acquiring a driving trajectory of a reference vehicle traveling on an initial lane; a determination unit, configured to determine target position information on the initial lane based on the lane change behavior in response to determining that the reference vehicle has performed a lane change behavior on the initial lane based on the driving trajectory, wherein the lane change behavior is used to indicate an action of the reference vehicle changing lanes from the initial lane to a target lane, and the target position information is used to indicate a position at which the autonomous driving vehicle corresponding to the reference vehicle is allowed to perform a diverging driving behavior or a merging driving behavior on the initial lane; a creating unit, configured to create an autonomous driving scenario of the autonomous driving vehicle based on the target position information and the lane information, wherein the lane information includes: lane information of the initial lane and lane information of the target lane, and the autonomous driving scenario includes a diverging driving scenario corresponding to the diverging driving behavior, or a merging driving scenario corresponding to the merging driving behavior; Wherein, the determination unit is used to respond to the determination based on the driving trajectory that the reference vehicle has changed lanes in the initial lane, and determine the target position information on the initial lane based on the lane change behavior by executing the following steps: in response to the determination based on the driving trajectory that the reference vehicle has changed lanes in the initial lane, obtain the target intersection corresponding to the lane change behavior, wherein the target intersection is used to represent the intersection between the driving trajectory and a first boundary line when the reference vehicle is performing the lane change behavior, and the first boundary line is a common boundary line between the initial lane and the target lane; according to the lane direction of the initial lane, traverse the points on the first boundary line starting from the target intersection to obtain the traversed points; determine an area centered on the traversed points; based on the relationship between the boundary line of the area and the second boundary line, determine the position information corresponding to the traversed point on the initial lane as the target position information, wherein the second boundary line is a boundary line on the target lane set opposite to the first boundary line.

16. An autonomous driving vehicle, characterized in that: include: A memory storing an executable program; A processor, configured to run the program, wherein the program executes the method according to any one of claims 1 to 13 when running.

17. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is run, the device where the storage medium is located is controlled to execute the method according to any one of claims 1 to 13.

18. A computer program product, characterized in that It comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 13.

Images