Automatic driving scene construction method and device, and storage medium

Abstract

Embodiments of the present application provide an automatic driving scene construction method and device and a storage medium. In the embodiments of the present application, the simulation traffic scene features of a target region can be determined based on static road network data; and traffic simulation is performed based on the simulation traffic scene features to determine the dynamic data of the traffic participants in the target region; then, the automatic driving scene can be constructed according to the simulation traffic scene features and the dynamic data of the traffic participants. Compared with the traditional scheme of constructing an automatic driving scene by collecting traffic scene data in the real world, the automatic driving scene is constructed based on traffic simulation, which does not need to collect traffic scene data, can improve the efficiency of obtaining traffic scene features, and thus improve the efficiency of constructing an automatic driving scene.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, and in particular to an automatic driving scene construction method, device and storage medium. BACKGROUND

[0002] With the rapid development of automobile electronics, interconnection and intelligence, automatic driving, as an important technology in the field of transportation, has gradually become a research hotspot and important development direction of the automobile industry. The automatic driving scene is a description of the traffic environment, which can be used for testing of automatic driving vehicles and can replace the testing of closed sites and part of open roads to a certain extent. Therefore, the automatic driving scene is the key to realizing the verification of automatic driving algorithms and functions and runs through the life cycle of the development and testing of automatic driving vehicles. For a long time, the construction of the automatic driving scene relies on the collection of data by entity equipment and the perception of data by sensors, which has a long collection cycle and results in low efficiency of the construction of the automatic driving scene. SUMMARY

[0003] The present application provides an automatic driving scene construction method, device and storage medium to improve the construction efficiency of the automatic driving scene.

[0004] In a first aspect, an embodiment of the present application provides an automatic driving scene construction method, comprising:

[0005] obtaining static road network data of a target area;

[0006] determining simulation traffic scene features of the target area based on at least the static road network data;

[0007] performing traffic simulation based on the simulation traffic scene features to determine dynamic data of a traffic participant in the target area;

[0008] constructing an automatic driving scene according to the simulation traffic scene features and the dynamic data of the traffic participant.

[0009] In a second aspect, an embodiment of the present application further provides an automatic driving scene construction method suitable for a cloud server, comprising:

[0010] in response to a request for calling a target service, determining a processing resource corresponding to the target service;

[0011] using the processing resource corresponding to the target service to execute the steps in the automatic driving construction method provided in the first aspect.

[0012] In a third aspect, an embodiment of the present application further provides a computing device, comprising a memory and a processor; wherein the memory is configured to store a computer program.

[0013] The processor is coupled to the memory and configured to execute the computer program to perform the steps in the method of the first aspect and / or the second aspect.

[0014] In a fourth aspect, a computer-readable storage medium storing computer instructions that, when executed by one or more processors, cause the one or more processors to perform the steps in the method of the first aspect and / or the second aspect.

[0015] In the embodiments of the present application, the simulation traffic scene features of the target region can be determined based on static road network data; and traffic simulation is performed based on the simulation traffic scene features to determine the dynamic data of the traffic participants in the target region; and then, the autonomous driving scene can be constructed according to the simulation traffic scene features and the dynamic data of the traffic participants. Compared with the way of constructing an autonomous driving scene by collecting traffic scene data in the real world in the traditional scheme, the way of constructing an autonomous driving scene based on traffic simulation does not need to collect traffic scene data, and can improve the efficiency of obtaining traffic scene features, thereby improving the efficiency of constructing an autonomous driving scene. BRIEF DESCRIPTION OF DRAWINGS

[0016] The accompanying drawings, which are included to provide a further understanding of the present application, constitute a part of this application and illustrate various illustrative embodiments of the present application and aspects thereof, and together with the description, serve to explain the present application. In the drawings:

[0017] Figure 1 A flowchart of an autonomous driving scene construction method provided by the embodiments of the present application is shown;

[0018] Figure 2 A construction process diagram of an autonomous driving scene provided by the embodiments of the present application is shown;

[0019] Figure 3 A road network diagram provided by the embodiments of the present application is shown;

[0020] Figure 4 A flowchart of another autonomous driving scene construction method provided by the embodiments of the present application is shown;

[0021] Figure 5 A structure diagram of a data processing system provided by the embodiments of the present application is shown;

[0022] Figure 6 A structure diagram of a computing device provided by the embodiments of the present application is shown. DETAILED DESCRIPTION

[0023] In order to make the purposes, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be described below in connection with specific embodiments of the present application and corresponding drawings. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort belong to the scope of protection of the present application.

[0024] The automatic driving scene refers to a dynamic description of the comprehensive and three-dimensional interaction of an automatic driving vehicle and other traffic participants (vehicles, pedestrians, etc.), roads, traffic facilities, meteorological conditions, scene features, etc. in a certain time and space range. In some solutions, the construction of the automatic driving scene relies on entity equipment to collect data and sensor perception data. Generally, the data collection equipment collects road network data and traffic scene data; then, the virtual road surface in the automatic driving scene is generated by using the road network data; then, the other elements of the automatic driving scene are generated by using the collected traffic scene data, and the virtual road surface and the scene elements are fused to obtain the automatic driving scene. The collection of the road network data and the traffic scene data relies on entity equipment, and the collection period is long, resulting in low construction efficiency of the automatic driving scene.

[0025] In some embodiments of the present application, the simulation traffic scene features of the target region can be determined based on the static road network data; the dynamic data of the traffic participant object of the target region is determined based on the simulation traffic scene features by traffic simulation; and then, the automatic driving scene can be constructed according to the simulation traffic scene features and the dynamic data of the traffic participant object. Compared with the way of constructing the automatic driving scene by collecting the traffic scene data of the real world in the traditional solution, the way of constructing the automatic driving scene based on traffic simulation does not need to collect the traffic scene data, can improve the acquisition efficiency of the traffic scene features, and thus improve the construction efficiency of the automatic driving scene.

[0026] The technical solutions provided by the embodiments of the present application will be described in detail below in connection with the drawings.

[0027] It should be noted that the same reference numerals represent the same objects in the drawings and embodiments below, and thus, once an object is defined in one drawing or embodiment, it does not need to be discussed further in subsequent drawings and embodiments.

[0028] Figure 1 The flowchart of the automatic driving scene construction method provided by the embodiments of the present application is shown in FIG. 1. Figure 1 As shown in FIG. 1, the method can include the following steps.

[0029] 101, acquiring the static road network data of the target region.

[0030] 102. Determine a simulation traffic scene feature of the target area based on at least the static road network data.

[0031] 103. Perform traffic simulation based on the simulation traffic scene feature to determine dynamic data of a traffic participant in the target area.

[0032] 104. Construct an autonomous driving scene according to the simulation traffic scene feature and the dynamic data of the traffic participant.

[0033] Traffic simulation refers to the use of simulation technology to study traffic behavior, which is a technique for tracking and describing the changes of traffic movement over time and space. The traffic scene obtained by traffic simulation contains random characteristics, can be microscopic or macroscopic, and involves mathematical models describing the real-time movement of the transportation system within a certain period. Among them, microscopic traffic simulation is to model the movement of individual traffic participants using computer technology, which can reproduce the time variation of traffic flow.

[0034] In the embodiments of the present application, the traffic participant refers to an object that affects the traffic state, including but not limited to: moving objects (such as people, vehicles, animals, etc.) and non-moving objects (such as traffic lights, etc.). Among them, the signal control parameters of the traffic light affect the traffic state.

[0035] In the embodiments, in order to improve the construction efficiency of the autonomous driving scene, the autonomous driving scene can be constructed by using traffic simulation technology. Preferably, the traffic simulation is microscopic traffic simulation. In the embodiments of the present application, autonomous driving refers to any level of L0-L5 level. Preferably, the autonomous driving is any level of L1-L5 level.

[0036] The embodiments of constructing the autonomous driving scene based on the traffic simulation technology provided in the embodiments of the present application will be described exemplarily as follows.

[0037] For traffic simulation, traffic simulation dependent data needs to be obtained first. In order to obtain the traffic simulation dependent data, in step 101, the static road network data of the target area can be obtained. In the embodiments, the target area is a to-be-simulated area determined according to the autonomous driving test requirements. The target area includes one or more intersections, and the number of intersections is 2 or more. The target area can be an area formed by one or more roads, for example, it can be an existing geographic area, for example, a city, a district of a city, etc., or it can be an area flexibly delimited according to the autonomous driving test requirements, for example, a section of a city or a district, etc., but is not limited thereto.

[0038] The intersection refers to the intersection of two or more roads, which can be a T-shaped, Y-shaped, cross-shaped, X-shaped, staggered, ring-shaped road intersection, etc.

[0039] The static road network data refers to data used to describe the static attribute information of the road network. The static attributes of the road network include but are not limited to: the topological connection relationship of the roads included in the road network, the geographic location information (such as road coordinates) of the roads, and the static element information of the road network, etc. The static element of the road network refers to the static infrastructure in the road network, including but not limited to: the lane information (such as coordinates, driving direction, etc.) of the roads included in the road network and the traffic facility information (such as the location information of the traffic facilities, etc.). The traffic facilities include but are not limited to: traffic lights, roadblocks, and traffic signs, etc.

[0040] In the embodiments of the present application, the source of the static road network data is not limited. In some embodiments, the static road network data of the target area can be obtained from electronic map data. The electronic map data can be in OpenDrive format, etc.

[0041] In step 102, the simulation traffic scene features of the target area can be determined based at least on the static road network data of the target area. The simulation traffic scene features refer to the feature information that can reflect the traffic scene to be simulated. For example, Figure 2 As shown, the simulation traffic scene features include but are not limited to: one or more of the simulation road network, the signal control parameters of the traffic lights, the departure model parameters, the path decision model, and the simulation traffic demand parameters, etc. Multiple refers to 2 or more. The simulation traffic scene features are the dependent data of the traffic simulation.

[0042] Among them, the simulation road network is the basic data of the traffic scene, including but not limited to: the topological connection relationship of the roads included in the road network, the lane information of the roads, and the traffic facility information of the roads, etc., which is the bottom basic data for building the traffic scene.

[0043] The signal control parameters of the traffic lights refer to the parameters used to control the lighting state of the traffic lights, including but not limited to: the signal cycle of the traffic lights, the green-to-red ratio, and the phase difference, etc.

[0044] The signal cycle refers to the time length experienced by the traffic light to return to the initial state from each phase, which can be equal to the sum of the phase times of all phases of the intersection. The phase is also called traffic phase or signal phase. In a signal cycle, one or more vehicle flows obtain the same traffic light color display at any time, and then the continuous time sequence of different light colors (green light, yellow light, and full red) obtained by them is called a phase. The vehicle flow in the same phase can be released by the green light at the same time. The phase time of a phase is the sum of the lighting times of all traffic light colors of the phase, which can be equal to the sum of the green light time, the yellow light time, and the full red time of the phase. The full red (all-red-signal) refers to the situation that when the traffic light changes from one phase to another phase, all the traffic lights of the intersection are red, and the purpose is to clear the vehicles in the intersection.

[0045] The green ratio refers to the green ratio of the traffic signal light at the intersection, specifically the proportion of the green light time of each phase of the traffic signal light to the cycle of the traffic signal light. At this time, the green ratio can be expressed as a percentage. It should be noted that the green ratio of the traffic signal light can also be directly expressed by the green light time. At this time, the green ratio can be expressed as a time information.

[0046] The phase difference of the traffic signal light refers to the difference between the starting time of the first phase green light in the signal cycle of two intersections. In the embodiments of the present application, any intersection in the region can be set as a reference intersection, and the phase difference of the reference intersection is 0. Correspondingly, the phase difference of the traffic signal light of other intersections is the difference between the starting time of the first phase green light in the signal cycle of the other intersections and the reference intersection.

[0047] The departure model parameter refers to the vehicle information of the departure point of the target region, including but not limited to: the vehicle composition of the departure point, the departure flow and the departure time interval, etc. The departure point refers to the starting point of entering the target region, and the departure point has no upstream connecting road segment in the simulation region, and has a downstream connecting road segment. For example, as shown in Figure 3 For the target region, road segment nodes A, B and C have downstream connecting road segments, but have no upstream connecting road segments, so the road segment nodes A, B and C are departure points.

[0048] The path decision model refers to the path decision strategy of the path decision point of the target region, that is, the decision model for selecting the downstream connecting road segment for the vehicle to travel in the multiple downstream connecting road segments of the path decision point. Among them, the path decision point refers to the node in the target region that has multiple downstream connecting road segments. For example, as shown in Figure 3 The target region, road segment nodes D and E each have 2 downstream connecting road segments, so the road segment nodes D and E are path decision points. Correspondingly, the path decision model corresponding to the road segment nodes D and E is the model for deciding which downstream connecting road segment the vehicle at the nodes D and E enters.

[0049] The simulation traffic demand parameter refers to the parameter for describing the traffic simulation demand, including: vehicle model parameter, driving behavior parameter, simulation running parameter and simulation traffic event parameter, etc.

[0050] Among them, the vehicle model parameter refers to the vehicle itself parameter required for traffic simulation, including but not limited to: vehicle composition required for traffic simulation (i.e. vehicle types constituting the traffic simulation vehicle and the number of vehicles of each vehicle type), vehicle physical parameters of the vehicle required for traffic simulation (such as vehicle size, etc.), and vehicle dynamics parameters of the vehicle required for traffic simulation (such as maximum speed, average speed, expected speed, speed standard deviation, average acceleration, maximum acceleration, acceleration standard deviation, average deceleration, maximum deceleration, and deceleration standard deviation, etc.).

[0051] The driving behavior parameter refers to a parameter used to describe the driving behavior of a vehicle required for traffic simulation, including but not limited to: car following model parameters and lane changing model parameters.

[0052] The car following model parameter refers to data reflecting relevant information between front and rear vehicles following each other, which can include: a safety time interval of a following vehicle, a maximum acceleration of the following vehicle, a stopping distance of the following vehicle, a speed difference between front and rear vehicles in a vehicle flow, a distance between the front and rear vehicles, and inherent parameters of the car following model.

[0053] The lane changing model parameter refers to lane changing information of a vehicle to be changed, and relevant information between the vehicle to be changed and other vehicles on the lane to be changed, which can include: a lane changing type (lane changing direction, number of lanes to be changed, etc.) of the vehicle to be changed, and a target minimum following distance.

[0054] The simulation running parameter refers to a running parameter of traffic simulation, including but not limited to: a running time length and a running multiple.

[0055] The simulation traffic event parameter refers to a traffic event type required for traffic simulation, including but not limited to: a weather event, a traffic accident event, a traffic control event, and a road construction event.

[0056] The simulation traffic scene features shown in the above embodiments are only exemplary and do not constitute a limitation. In the embodiments of the present application, the simulation traffic scene features used for traffic simulation can be all the above features or part of the features. According to the above simulation traffic scene features, they can be divided into two categories, one of which is obtained based on static road network data, and the other of which is independent of the static road network data. For example, the simulation traffic demand parameter is independent of the static road network data. In the embodiments of the present application, in order to improve the dimension and richness of traffic simulation, the simulation traffic scene features used for traffic simulation can include: simulation traffic scene features obtained based on static road network data (defined as first type simulation traffic scene features) and simulation traffic scene features independent of the static road network data (defined as second type simulation traffic scene features). For the second type simulation traffic scene features, they can be flexibly set according to the simulation scene requirements.

[0057] Based on this, the above step 102 can be implemented as: based on the static road network data, constructing the first type simulation traffic scene features; and determining the target traffic simulation demand parameter as the second type simulation traffic scene features. The target traffic simulation demand parameter is a traffic simulation demand parameter pre-configured for the second type simulation traffic scene features. The target traffic simulation parameter can be a default parameter or a parameter pre-configured according to the simulation scene requirements. The simulation traffic demand parameter can include: vehicle model parameters, driving behavior parameters, simulation running parameters, and simulation traffic event parameters, and specific descriptions are referred to the related contents of the above embodiments.

[0058] For the above based on static road network data, when constructing the first type of simulation traffic scene features, the topological connection relationship of the roads of the target region and the static road element information of the target region can be determined based on the static road network data. The static road element information of the target region includes but is not limited to: lane information (lane position, lane driving direction, etc.) of the road and traffic facility information (such as the position of the traffic facility, etc.). The traffic facility includes but is not limited to: traffic signal, traffic sign, and roadblock, etc.

[0059] Specifically, in combination with Figure 2 “data preprocessing”, the static road network data can be preprocessed to obtain the simulation traffic scene features. The preprocessing step can include: obtaining the topological connection relationship of the roads of the target region and the static road element information of the target region from the static road network data.

[0060] Further, the first type of simulation traffic scene features of the target region can be determined according to the topological connection relationship of the roads of the target region and the static road element information of the target region. The specific implementation of determining the first type of simulation traffic scene features of the target region according to the topological connection relationship of the roads of the target region and the static road element information of the target region will be exemplarily described below in combination with different first type of simulation traffic scene features.

[0061] Embodiment 1: The first type of simulation traffic scene features includes: simulation road network. Accordingly, the initial simulation road network of the target region can be generated according to the topological connection relationship of the roads of the target region; and the static elements of the roads of the target region are added in the initial simulation road network according to the static road element information, so as to obtain the simulation road network of the target region.

[0062] Embodiment 2: The first type of simulation traffic scene features includes: signal control parameters of the traffic signal. Accordingly, the intersection of the roads of the target region can be determined according to the topological connection relationship of the roads of the target region. Further, the traffic attribute information of the intersection is determined according to the static road element information. The traffic attribute information of the intersection refers to the information describing the traffic performance of the intersection, including but not limited to: the import and export and turning information of the intersection, etc. Accordingly, the import and export and turning information of the intersection can be determined from the static road element information.

[0063] Further, the signal control parameters of the traffic signal of the intersection can be determined according to the traffic attribute information of the intersection and the signal control rule. The signal control rule is determined according to the traffic driving rule, including but not limited to: left turn protection rule, single-port release rule, and opposite release rule, etc.

[0064] Accordingly, the embodiment of determining the signal control parameter of the traffic signal light of the intersection according to the traffic attribute information of the intersection and the signal control rule is: determining the right of passage of the phase of the intersection according to the traffic attribute information of the intersection and the signal control rule. The right of passage of the phase of the intersection refers to the right of passage of the phase of the intersection in a certain space and a certain time according to the principle of each going its own way according to the signal control rule.

[0065] Specifically, the phase of the intersection can be determined according to the import and export information and the turning information of the intersection, and the right of passage of the phase of the intersection can be determined according to the signal control rule and the turning information of the intersection.

[0066] Further, the signal control parameter of the traffic signal light of the intersection can be determined according to the right of passage of the phase of the intersection.

[0067] Embodiment 3: The first type of simulation traffic scene feature includes the emission model parameter of the traffic signal light. Accordingly, the lane information of the road of the target region can be determined from the static road element information. The lane information includes lane position and traffic attribute information. The traffic attribute of the lane can include the driving direction of the lane, etc. Further, the departure point can be determined from the road of the target region according to the topological connection relationship of the road of the target region and the lane information of the road of the target region. The departure point has no upstream connecting road section, and the departure point has a downstream connecting road section. Further, the departure model parameter of the departure point can be determined as the first type of simulation traffic scene feature.

[0068] In some embodiments, the departure model parameter includes at least one of the departure flow, the departure time interval, and the vehicle composition information of the departure point. The vehicle composition information of the departure point can include the vehicle type of the departure point and the number of vehicles of each vehicle type.

[0069] Accordingly, determining the departure model parameter of the departure point can be implemented as: determining the pre-set departure flow as the departure flow of the departure point; and / or, determining the pre-set vehicle type as the vehicle type of the departure point; and / or, determining the departure time interval of the departure point according to the set function distribution model, so that the departure time interval meets the function distribution model.

[0070] The pre-set departure flow is the departure flow pre-configured for the departure point, which can be flexibly set according to the traffic simulation requirements. For example, multiple departure flows can be set, such as 600 vehicles / hour, 1200 vehicles / hour, and 2400 vehicles / hour, etc., and the target departure flow is selected from the pre-set multiple departure flows according to the traffic simulation requirements; and the target departure flow is determined as the departure flow of the departure point, etc.

[0071] The pre-set vehicle type is a vehicle type pre-configured for the departure point, and can be flexibly set according to the traffic simulation requirement. The pre-configured vehicle type can include one or more vehicle types. More means two or more.

[0072] In the embodiments of the present application, the specific implementation form of the function distribution model is not limited. The function distribution model can be a Poisson distribution model, a uniform distribution model, a normal distribution model, and a gamma distribution model, etc. The departure time interval of the departure point meets the set function distribution model.

[0073] Embodiment 4: The first type of simulation traffic scene feature can further include a path decision model. Accordingly, the lane information of the road of the target region can be determined from the static road element information. The lane information includes lane position and traffic attribute information. The traffic attribute of the lane can include the driving direction of the lane, etc. Further, the path decision point can be determined from the road of the target region according to the topological connection relationship of the road of the target region and the lane information of the road of the target region. The path decision point has multiple downstream connected road segments. Multiple means two or more. Further, the path decision strategy of the vehicle flow of the path decision point for the multiple downstream connected road segments can be determined as the first type of simulation traffic scene feature.

[0074] In the embodiments of the present application, the specific implementation of the path decision strategy of the departure vehicle of the path decision point for the multiple downstream connected road segments is not limited. In some embodiments, the path decision strategy can determine the proportion of the vehicle flow of the path decision point driving to each downstream connected road segment. Accordingly, the proportion of the vehicle flow of the path decision point driving into the multiple downstream connected road segments (i.e., the vehicle flow proportion of the multiple downstream connected road segments) can be configured, and the sum of the vehicle flow proportions of the multiple downstream connected road segments is equal to 100%. The sum of the vehicle flow proportions corresponding to the multiple downstream connected road segments can be equal to 100%. Alternatively, the proportions of the vehicle flow of the path decision point driving into each downstream connected road segment can be configured to be the same. Accordingly, the vehicle flow proportion of each downstream connected road segment is equal to (100 / N)%. N is the number of downstream connected road segments of the path decision point; N≥2, and is an integer.

[0075] The above embodiments exemplarily give several implementation modes of determining the first type of simulation traffic scene feature of the target region, but do not constitute a limitation.

[0076] For the above-mentioned second type of simulation traffic scene feature, the target traffic simulation requirement parameter can be determined as the second type of simulation traffic scene feature. The target traffic simulation requirement parameter is a traffic simulation requirement parameter pre-configured for the second type of simulation traffic scene. The target traffic simulation parameter can be a default parameter, or a parameter pre-configured according to the simulation scene requirement.

[0077] In the real world, for a traffic scene, there are some dynamic features in addition to the static traffic scene features. For example, the moving features of the moving objects (vehicles, people, etc.) in the traffic scene and the light color changing features of the traffic signal lights in the traffic scene, etc. In order to realize the real mapping of the autonomous driving scene to the real world, after the simulation traffic scene features of the target region are determined, in step 103, traffic simulation can be performed based on the simulation traffic scene features to determine the dynamic data of the traffic participants in the target region.

[0078] Among them, the traffic participant refers to an object that affects the traffic state, including but not limited to: moving objects (such as people, vehicles, animals, etc.) and non-moving objects (such as traffic signal lights, etc.). Among them, the signal control parameters of the traffic signal lights affect the traffic state.

[0079] Correspondingly, step 103 can be implemented as: inputting the simulation traffic scene features into a traffic simulator; in the traffic simulator, the interaction behaviors between the moving objects can be simulated according to the simulation traffic scene features to obtain the moving trajectory data of the moving objects. The light state changing data of the traffic signal lights can also be determined according to the signal control parameters of the traffic signal lights. Among them, the light state changing data of the traffic signal lights includes: the light color and the light time of the traffic signal lights. Further, the moving trajectory data of the moving objects and the light state changing data of the traffic signal lights can be taken as the dynamic data of the traffic participants.

[0080] Further, in step 104, the autonomous driving scene can be constructed according to the simulation traffic scene features and the dynamic data of the traffic participants. Specifically, as shown in Figure 2 "autonomous driving scene construction", the simulation road network and the signal control parameters of the traffic signal lights can be obtained from the simulation traffic scene features; the static scene file in the target format suitable for the autonomous driving simulator can be generated according to the simulation road network and the signal control parameters of the traffic signal lights; and the dynamic scene file in the target format can be generated according to the dynamic data of the traffic participants; further, the autonomous driving scene can be constructed according to the dynamic scene file and the static scene file by using the autonomous driving simulator.

[0081] In this embodiment, the simulation traffic scene features of the target region can be determined based on the static road network data; and the dynamic data of the traffic participants in the target region can be determined by performing traffic simulation based on the simulation traffic scene features; then, the autonomous driving scene can be constructed according to the simulation traffic scene features and the dynamic data of the traffic participants. Compared with the traditional scheme of constructing the autonomous driving scene by collecting the traffic scene data in the real world, this way of constructing the autonomous driving scene based on traffic simulation does not need to collect the traffic scene data, reduces the data collection cost, improves the acquisition efficiency of the traffic scene features, and thus improves the construction efficiency of the autonomous driving scene.

[0082] In some embodiments of the present application, in order to realize the customized design of the simulation traffic scene features, a visual editing capability of the simulation traffic scene features can also be provided, including: simulation road network editing, traffic signal lamp signal control parameter editing, departure point editing, path decision corresponding path decision point editing, simulation traffic demand parameter configuration, and the like.

[0083] Specifically, as shown by the "visual editing", a visual editing interface can be provided; and on the visual editing interface, the simulation traffic scene features determined by the above embodiments can be displayed. The user can modify the simulation traffic scene features on demand through the visual editing interface, so as to realize the customization of the simulation traffic scene features. Correspondingly, the modified simulation traffic scene features can be acquired in response to the modification operation on the simulation traffic scene features, so as to realize the customization of the traffic scene features. Figure 2

[0084] Further, traffic simulation can be performed according to the modified simulation traffic scene features, so as to determine the dynamic data of the traffic participants in the target region. The specific implementation of the traffic simulation according to the modified simulation traffic scene features to determine the dynamic data of the traffic participants in the target region can refer to the related content of the traffic simulation according to the simulation traffic scene features to determine the dynamic data of the traffic participants in the target region.

[0085] Further, an automatic architecture scene can be constructed according to the modified simulation traffic scene features and the dynamic data of the traffic participants. The specific implementation of the automatic architecture scene constructed according to the modified simulation traffic scene features and the dynamic data of the traffic participants can also refer to the related content of the automatic architecture scene constructed according to the simulation traffic scene features and the dynamic data of the traffic participants.

[0086] Through the visual editing of the simulation traffic scene features, the user can construct various micro-traffic simulation running scenes under various feature conditions according to the traffic simulation requirements, so as to output the automatic driving scenes that can map various traffic features in the real world. Compared with the traditional scheme of constructing the automatic driving scene by collecting the traffic scene data in the real world, this scheme can reduce the data collection cost, improve the traffic simulation running scene acquisition efficiency, and thus improve the construction efficiency of the automatic driving scene.

[0087] ​On the other hand, in the conventional scheme, the automatic driving scene is constructed by collecting real-world traffic scene data, and the diversity of the automatic driving scene depends on the diversity of the collected traffic scene data. In actual applications, due to insufficient coverage of the collected real-world traffic scene data, the coverage of the automatic driving scene is insufficient, and the scene diversity is low. However, the embodiment of the present application can improve the diversity of the simulation traffic scene according to the traffic scene demand, and improve the diversity of the automatic driving scene through the visual editing of the simulation traffic scene features.

[0088] It should be noted that the automatic driving scene construction method provided by the embodiment of the present application can be deployed on any computing device. Alternatively, the automatic driving scene construction method provided by the embodiment of the present application can also be deployed on a cloud server as a software as a service (Software as a Service, SaaS) application. For the cloud server deployed with the SaaS application, the steps in the above automatic driving scene construction method can be executed in response to a request for invoking a target service. The specific implementation is shown in the following Figure 4 As shown in the following, the method is applicable to a cloud server, and mainly includes:

[0089] 401、In response to a request for invoking a target service, determine the processing resource corresponding to the target service.

[0090] 402、Using the processing resource corresponding to the target service, obtain the static road network data of the target area.

[0091] 403、Using the processing resource corresponding to the target service, determine the simulation traffic scene features of the target area based on at least the static road network data.

[0092] 404、Using the processing resource corresponding to the target service, perform traffic simulation based on the simulation traffic scene features to determine the dynamic data of the traffic participants in the target area.

[0093] 405、According to the simulation traffic scene features and the dynamic data of the traffic participants, construct an automatic driving scene.

[0094] In the embodiment, the target service can provide an automatic driving scene construction service, which can be a service providing an automatic driving scene construction method. The processing resource corresponding to the target service refers to the processing resource required to execute the above automatic driving scene construction method, including but not limited to: processor resource, memory resource, and input / output (Input / Output, IO) resource, etc.

[0095] The automatic driving scene construction method provided in this embodiment can be deployed on a cloud server to provide an automatic driving scene construction service, i.e., a target service, to a user. The user can be a producer or a consumer of an autonomous vehicle, etc. Optionally, the cloud server can provide an application programming interface (API) to the user. The user, i.e., a service requester, can invoke the target service by calling the API. Correspondingly, the request for invoking the target service is implemented as a calling event generated by calling the API. The user, i.e., the service requester, can also invoke the target service by using a remote procedure call (RPC) or a remote direct memory access (RDMA) technology. As shown in Figure 5 , the user terminal 10 of the service requester can send a request for invoking the target service to the cloud server 20.

[0096] For the cloud server, the processing resource corresponding to the target service can be determined in response to the request for invoking the target service, and the static road network data of the target area can be obtained by using the processing resource corresponding to the target service. In this embodiment, the implementation manner of obtaining the static road network data by the cloud server is not limited. In some embodiments, the static road network data of the target area can be provided by the service requester. In other embodiments, the request for invoking the target service provided by the service requester can carry an identifier of the target area. Correspondingly, as shown in Figure 5 , the cloud server 20 can obtain the static road network data of the target area from the storage system 30 according to the identifier of the target area.

[0097] Further, in combination with Figure 4 and Figure 5 , the cloud server 20 can determine the simulation traffic scene features of the target area based on at least the static road network data by using the processing resource corresponding to the target service, and perform traffic simulation based on the simulation traffic scene features to determine the dynamic data of the traffic participants in the target area. Then, the automatic driving scene can be constructed according to the traffic simulation scene features and the dynamic data of the traffic participants. For specific implementation manners of steps 403 and 405, please refer to the related content of the above embodiments, which will not be described here.

[0098] As shown in Figure 5 , for the cloud server 20, the automatic driving scene can be provided to the user terminal 10 after the automatic driving scene is constructed. The service requester corresponding to the user terminal 10 can use the automatic driving scene to perform function testing on the autonomous vehicle, etc.

[0099] In this embodiment, the simulation traffic scene features of the target region can be determined based on static road network data; and traffic simulation is performed based on the simulation traffic scene features to determine the dynamic data of the traffic participants in the target region; and then, the autonomous driving scene can be constructed according to the simulation traffic scene features and the dynamic data of the traffic participants. Compared with the manner of constructing an autonomous driving scene by collecting traffic scene data in the real world in the traditional scheme, the manner of constructing an autonomous driving scene based on traffic simulation does not need to collect traffic scene data, reduces the data collection cost, improves the acquisition efficiency of traffic scene features, and thus improves the construction efficiency of the autonomous driving scene.

[0100] It should be noted that the execution subject of each step of the method provided in the above embodiments can be the same device, or the method can also be executed by different devices as the execution subject. For example, the execution subject of steps 401 and 402 can be device A; for another example, the execution subject of step 401 can be device A, and the execution subject of step 402 can be device B; and the like.

[0101] In addition, in some of the processes described in the above embodiments and the accompanying drawings, a plurality of operations appearing in a specific order are included, but it should be clearly understood that these operations can be executed or executed in parallel without the order in which they appear in this text. The serial numbers of the operations, such as 401, 402, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes can include more or fewer operations, and the operations can be executed in sequence or in parallel.

[0102] Correspondingly, the embodiments of the present application also provide a computer readable storage medium storing computer instructions, which, when executed by one or more processors, cause the one or more processors to perform the steps of the above-mentioned autonomous driving scene construction methods.

[0103] It should be noted that the data involved in the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of related data comply with relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation portals for the user to choose authorization or refusal.

[0104] Figure 6 The structural schematic diagram of the computing device provided by the embodiments of the present application is shown in FIG. 1. Figure 6 As shown in FIG. 1, the computing device includes a memory 60a and a processor 60b. The memory 60a is configured to store a computer program.

[0105] The processor 60b is coupled to the memory 60a and configured to execute a computer program to acquire static road network data of a target area, determine simulation traffic scene features of the target area based on at least the static road network data, perform traffic simulation based on the simulation traffic scene features to determine dynamic data of a traffic participant in the target area, and construct an autonomous driving scene according to the simulation traffic scene features and the dynamic data of the traffic participant.

[0106] In some embodiments, the simulation traffic scene features include first-type simulation traffic scene features and second-type simulation traffic scene features. Accordingly, when determining the simulation traffic scene features of the target area based on at least the static road network data, the processor 60b is specifically configured to determine a topological connection relationship of roads in the target area and static road element information of the target area based on the static road network data, determine the first-type simulation traffic scene features of the target area according to the topological connection relationship and the static road element information, and determine a target traffic simulation demand parameter as the second-type simulation traffic scene features, wherein the target traffic simulation demand parameter is a traffic simulation demand parameter pre-configured for the second-type traffic scene features.

[0107] In some embodiments, when determining the first-type simulation traffic scene features of the target area according to the topological connection relationship and the static road element information, the processor 60b is specifically configured to generate an initial simulation road network of the target area according to the topological connection relationship, add road static elements of the target area in the initial simulation road network according to the static road element information to obtain a simulation road network of the target area as the first-type simulation traffic scene features.

[0108] In other embodiments, when determining the first-type simulation traffic scene features of the target area according to the topological connection relationship and the static road element information, the processor 60b is specifically configured to determine an intersection in the target area according to the topological connection relationship, determine traffic attribute information of the intersection according to the static road element information, and determine a signal control parameter of a traffic signal light of the intersection as the first-type simulation traffic scene features according to the traffic attribute information of the intersection and a signal control rule.

[0109] Further, when determining the signal control parameter of the traffic signal light of the intersection according to the traffic attribute information of the intersection and the signal control rule, the processor 60b is specifically configured to determine a right of way of a phase of the intersection according to the traffic attribute information of the intersection and the signal control rule, and determine the signal control parameter of the traffic signal light of the intersection according to the right of way of the phase of the intersection.

[0110] In some embodiments, the processor 60b, in determining the first type of simulation traffic scene feature of the target region according to the topological connection relationship and the static road element information, is specifically configured to: determine lane information of a road of the target region from the static road element information; determine a departure point from the road of the target region according to the topological connection relationship and the lane information of the road of the target region; the departure point has no upstream connected road segment and has downstream connected road segments; and determine a departure model parameter of the departure point as the first type of simulation traffic scene feature.

[0111] Optionally, the departure model parameter includes at least one of a departure flow, a departure time interval, and vehicle composition information. Correspondingly, the processor 60b, in determining the departure model parameter of the departure point, is specifically configured to: determine a pre-set departure flow as the departure flow of the departure point; and / or determine a departure time interval of the departure point according to a set function distribution model; and / or determine pre-set vehicle composition information as the vehicle composition information of the departure point.

[0112] In other embodiments, the processor 60b, in determining the first type of simulation traffic scene feature of the target region according to the topological connection relationship and the static road element information, is specifically configured to: determine lane information of a road of the target region from the static road element information; determine a path decision point from the road of the target region according to the topological connection relationship and the lane information of the road of the target region; the path decision point has multiple downstream connected road segments; and determine a path decision strategy of a vehicle flow of the path decision point for the multiple downstream connected road segments as the first type of simulation traffic scene feature.

[0113] Optionally, the processor 60b, in configuring the path decision strategy of the vehicle flow of the path decision point for the multiple downstream connected road segments, is specifically configured to: configure a proportion of the departure vehicle of the path decision point entering the multiple downstream connected road segments as the path decision strategy.

[0114] In some embodiments, the processor 60b is specifically configured to: display the simulation traffic scene feature in the visual editing interface; in response to a modification operation on the simulation traffic scene feature, obtain a modified simulation traffic scene feature; and perform traffic simulation based on the modified simulation traffic scene feature to determine the dynamic data of the traffic participants in the target area. In some embodiments, the traffic participants include mobile objects and traffic signal lights. Accordingly, when performing traffic simulation based on the simulation traffic scene feature, the processor 60b is specifically configured to: input the simulation traffic scene feature into a traffic simulator; simulate interaction behaviors between the mobile objects in the traffic simulator based on the simulation traffic scene feature to obtain mobile trajectory data of the mobile objects; determine light state change data of the traffic signal lights based on signal control parameters of the traffic signal lights; and use the mobile trajectory data of the mobile objects and the light state change data of the traffic signal lights as the dynamic data of the traffic participants.

[0115] Optionally, when constructing the autonomous driving scene based on the simulation traffic scene feature and the dynamic data of the traffic participants, the processor 60b is specifically configured to: obtain a simulation road network and signal control parameters of traffic signal lights from the simulation traffic scene feature; generate a static scene file in a target format adapted to an autonomous driving simulator based on the simulation road network and the signal control parameters of the traffic signal lights; generate a dynamic scene file in the target format based on the dynamic data of the traffic participants; and construct the autonomous driving scene based on the dynamic scene file and the static scene file by using the autonomous driving simulator.

[0116] In some embodiments of the present application, the computing device can be deployed in the cloud. Accordingly, the processor 60b can be configured to: in response to a request for invoking a target service, determine processing resources corresponding to the target service; and execute the steps in the autonomous driving scene construction method provided in the above embodiments by using the processing resources corresponding to the target service. The target service is used to provide an autonomous driving scene construction service.

[0117] In some optional embodiments, as shown in Figure 6 the computing device can further include a communication component 60c, a power supply component 60d, and the like. In some embodiments, the computing device can be implemented as a computer, a mobile phone, or the like. Accordingly, the computing device can further include a display component 60e, an audio component 107, and the like. Figure 6 only some components are shown schematically, and it does not mean that the computing device must include Figure 6 all the components shown, nor does it mean that the computing device can only include Figure 6 the components shown.

[0118] The computing device provided in this embodiment can determine the simulated traffic scene characteristics of a target area based on static road network data; and perform traffic simulation based on the simulated traffic scene characteristics to determine the dynamic data of traffic participants in the target area; then, an autonomous driving scenario can be constructed based on the simulated traffic scene characteristics and the dynamic data of traffic participants. This method of constructing autonomous driving scenarios based on traffic simulation, compared to the traditional method of constructing autonomous driving scenarios by collecting real-world traffic scene data, eliminates the need to collect traffic scene data, reducing data collection costs and improving the efficiency of acquiring traffic scene characteristics, thereby improving the efficiency of constructing autonomous driving scenarios.

[0119] In this embodiment, the memory is used to store computer programs and can be configured to store various other data to support operation on its host device. The processor can execute the computer programs stored in the memory to implement corresponding control logic. The memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random-Access Memory (SRAM), Electrically Erasable Programmable Read Only Memory (EEPROM), Electrically Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0120] In the embodiments of this application, the processor can be any hardware processing device capable of executing the above-described method logic. Optionally, the processor can be a central processing unit (CPU), a graphics processing unit (GPU), or a microcontroller unit (MCU); it can also be a field-programmable gate array (FPGA), a programmable array logic (PAL), a general array logic (GAL), a complex programmable logic device (CPLD), or other programmable devices; or it can be an advanced RISC machine (ARM) or a system on chip (SoC), etc., but is not limited thereto.

[0121] In this embodiment, the communication component is configured to facilitate wired or wireless communication between its host device and other devices. The device housing the communication component can access wireless networks based on communication standards, such as Wireless Fidelity (WiFi), 2G or 3G, 4G, 5G, or combinations thereof. In one exemplary embodiment, the communication component receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In another exemplary embodiment, the communication component may also be implemented based on Near Field Communication (NFC), Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra Wide Band (UWB), Bluetooth (BT), or other technologies.

[0122] In embodiments of this application, the display component may include a liquid crystal display (LCD) and a touch panel (TP). If the display component includes a touch panel, the display component can be implemented as a touchscreen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors can sense not only the boundaries of touch or swipe actions but also the duration and pressure associated with the touch or swipe operation.

[0123] In this embodiment, a power supply component is configured to provide power to various components of the device in which it resides. The power supply component may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device in which the power supply component resides.

[0124] In embodiments of this application, the audio component can be configured to output and / or input audio signals. For example, the audio component includes a microphone (MIC), which is configured to receive external audio signals when the device containing the audio component is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals can be further stored in memory or transmitted via a communication component. In some embodiments, the audio component also includes a speaker for outputting audio signals. For example, in devices with voice interaction capabilities, voice interaction with the user can be achieved through the audio component.

[0125] It should be noted that the terms "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., and do not represent a chronological order, nor do they limit "first" and "second" to different types.

[0126] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, compact disc read-only memory (CD-ROM), optical storage, etc.) containing computer-usable program code.

[0127] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0128] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0129] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0130] In a typical configuration, a computing device includes one or more processors (CPU, etc.), input / output interfaces, network interfaces, and memory.

[0131] Memory may include non-persistent storage in computer-readable media, such as random-access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0132] Computer storage media are readable storage media, also known as removable media. Removable and non-removable media can be used to store information by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, Digital Video Disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient media, such as modulated data signals and carrier waves.

[0133] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the aforementioned element.

[0134] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for constructing autonomous driving scenarios, characterized in that, include: Obtain static road network data for the target area; Based at least on the static road network data, the simulated traffic scene characteristics of the target area are determined; Traffic simulation is performed based on the characteristics of the simulated traffic scene to determine the dynamic data of traffic participants in the target area. The traffic participants include moving objects and traffic lights; The dynamic data includes: the movement trajectory data of the moving object and the light status change data of the traffic lights; the light status change data includes: the lighting color and lighting time of the traffic lights; Based on the characteristics of the simulated traffic scene and the dynamic data of the traffic participants, an autonomous driving scenario is constructed; The simulated traffic scene features include: a first type of simulated traffic scene features and a second type of simulated traffic scene features; determining the simulated traffic scene features of the target area based at least on the static road network data includes: Based on the static road network data, the topological connection relationship of roads in the target area and the static road element information of the target area are determined; Based on the topological connectivity and static road element information, the first type of simulated traffic scene features of the target area are determined; the first type of simulated traffic scene features refers to simulated traffic scene features that depend on the static road network data. Furthermore, the target traffic simulation requirement parameters are determined as the second type of simulated traffic scenario features, wherein the target traffic simulation requirement parameters are traffic simulation requirement parameters pre-configured for the second type of simulated traffic scenario features; and the second type of simulated traffic scenario features are simulated traffic scenario features that do not depend on the static road network data.

2. The method according to claim 1, characterized in that, The step of determining the first type of simulated traffic scene features of the target area based on the topological connectivity and static road element information includes: Based on the topological connections, an initial simulated road network for the target area is generated; Based on the static road element information, the static road elements of the target area are added to the initial simulated road network to obtain the simulated road network of the target area, which serves as the feature of the first type of simulated traffic scene.

3. The method according to claim 1, characterized in that, The step of determining the first type of simulated traffic scene features of the target area based on the topological connectivity and the static road element information includes: Based on the topological connections, determine the intersections of the target area; Based on the static road element information, determine the traffic attribute information of the intersection; Based on the traffic attribute information and signal control rules of the intersection, the signal control parameters of the traffic lights at the intersection are determined as the first type of simulated traffic scene features.

4. The method according to claim 3, characterized in that, The step of determining the signal control parameters of the traffic lights at the intersection based on the traffic attribute information and signal control rules of the intersection includes: Based on the traffic attribute information and signal control rules of the intersection, the right-of-way for the phase of the intersection is determined; The signal control parameters of the traffic lights at the intersection are determined based on the right-of-way of the intersection's phase.

5. The method according to claim 1, characterized in that, The step of determining the first type of simulated traffic scene features of the target area based on the topological connectivity and static road element information includes: From the static road element information, determine the lane information of the roads in the target area; Based on the topological connectivity and the lane information of the roads in the target area, a departure point is determined from the roads in the target area; the departure point has no upstream connecting road segments, and the departure point has downstream connecting road segments; The departure model parameters of the departure point are determined and used as features of the first type of simulated traffic scenario.

6. The method according to claim 5, characterized in that, The departure model parameters include at least one of: departure flow rate, departure time interval, and vehicle composition information; the departure model parameters for determining the departure point include: The pre-set departure flow rate is determined as the departure flow rate of the departure point; and / or, According to the established function distribution model, determine the departure time interval of the departure points; and / or, The pre-set vehicle composition information is determined to be the vehicle composition information of the departure point.

7. The method according to claim 1, characterized in that, The step of determining the first type of simulated traffic scene features of the target area based on the topological connectivity and static road element information includes: From the static road element information, determine the lane information of the roads in the target area; Based on the topological connectivity and the lane information of the roads in the target area, a path decision point is determined from the roads in the target area; the path decision point has multiple downstream connecting road segments; The path decision strategy for traffic flow at the path decision point for the multiple downstream connecting road segments is determined as the first type of simulated traffic scenario feature.

8. The method according to any one of claims 1-7, characterized in that, The traffic simulation based on the simulated traffic scene characteristics to determine the dynamic data of traffic participants in the target area includes: The simulated traffic scene features are displayed in the visual editing interface; In response to the modification operation on the simulated traffic scene features, the modified simulated traffic scene features are obtained; Traffic simulation is performed based on the modified simulated traffic scene characteristics to determine the dynamic data of traffic participants in the target area. The step of constructing an autonomous driving field based on the characteristics of the simulated traffic scenario and the dynamic data of the traffic participants includes: An autonomous driving field is constructed based on the modified simulated traffic scene characteristics and the dynamic data of the traffic participants.

9. The method according to any one of claims 1-7, characterized in that, The traffic simulation based on the simulated traffic scene characteristics to determine the dynamic data of traffic participants in the target area includes: The simulated traffic scene features are input into a traffic simulator; in the traffic simulator, the interaction behavior between the moving objects is simulated based on the simulated traffic scene features to obtain the movement trajectory data of the moving objects; Based on the signal control parameters of the traffic lights, determine the light status change data of the traffic lights; The movement trajectory data of the moving object and the light status change data of the traffic lights are used as the dynamic data of the traffic participants.

10. The method according to any one of claims 1-7, characterized in that, The step of constructing an autonomous driving scenario based on the characteristics of the simulated traffic scenario and the dynamic data of the traffic participants includes: The signal control parameters of the simulated road network and traffic lights are obtained from the features of the simulated traffic scene. Based on the signal control parameters of the simulated road network and traffic lights, a static scene file in the target format adapted to the autonomous driving simulator is generated; Based on the dynamic data of the traffic participants, a dynamic scene file in the target format is generated; The autonomous driving scenario is constructed using the autonomous driving simulator based on the dynamic scenario file and the static scenario file.

11. A method for constructing autonomous driving scenarios, applicable to cloud servers, characterized in that, The method includes: In response to a request to invoke a target service, the processing resources corresponding to the target service are determined; the target service is used to provide autonomous driving scenario construction services. The steps of the method according to any one of claims 1-10 are performed using the processing resources corresponding to the target service.

12. A computing device, characterized in that, include: A memory and a processor; wherein the memory is used to store computer programs; The processor is coupled to the memory for executing the computer program to perform the steps of the method according to any one of claims 1-10.

13. A computer-readable storage medium storing computer instructions, characterized in that, When the computer instructions are executed by one or more processors, the one or more processors are caused to perform the steps of the method according to any one of claims 1-10.

Images