CN117852162A - Intelligent driving scene processing method, system and terminal for vehicle - Google Patents

Abstract

The application discloses a method, a system and a terminal for processing an intelligent driving scene of a vehicle, wherein the method comprises the following steps: obtaining a driving scene, generalizing the driving scene to obtain a generalization scene, obtaining a road description file and a target vehicle information file of the generalization scene, and analyzing the target vehicle information file to obtain target information of a target vehicle; and performing scene judgment on the generalized scene according to the road description file and the target information to obtain an extreme driving scene, and collecting the extreme driving scene to obtain an intelligent driving scene library for simulation test. According to the intelligent driving system, the road description file and the target vehicle information are obtained in batches, the RSS safe distance model is utilized to judge the extreme driving scene, the existing unsafe dangerous scene is collected, and the intelligent driving scene library for simulation test is obtained, so that the scene generalization capability of the intelligent driving system is effectively improved, and the application range is wide.

Description

Intelligent driving scene processing method, system and terminal for vehicle

Technical Field

The present disclosure relates to the field of intelligent driving technologies, and in particular, to a method, a system, a terminal, and a computer readable storage medium for processing an intelligent driving scene of a vehicle.

Background

With the rapid development of automobiles, intelligent driving of automobiles is rapidly developed; the intelligent driving needs to be trained and tested in different driving scenes, so that accurate decisions are timely carried out in the corresponding driving scenes, but vehicles often cannot carry out accurate decisions when facing extreme scenes, so that safety accidents are caused, because only limited scenes are considered in the process of training and testing the intelligent driving of the vehicles, and the scene generalization capability is insufficient; therefore, for the intelligent driving system, how to quickly and accurately acquire and process the road description file and the target vehicle information, and how to perform scene generalization and extreme use case scene judgment are very critical.

Accordingly, the prior art is still in need of improvement and development.

Disclosure of Invention

The main purpose of the present application is to provide a method, a system, a terminal and a computer readable storage medium for processing an intelligent driving scene of a vehicle, which aim to solve the problems that the existing intelligent driving system has low scene generalization capability and cannot accurately judge an extreme case scene.

An embodiment of a first aspect of the present application provides a method for processing an intelligent driving scenario of a vehicle, including the following steps: obtaining a driving scene, generalizing the driving scene to obtain a generalization scene, obtaining a road description file and a target vehicle information file of the generalization scene, and analyzing the target vehicle information file to obtain target information of a target vehicle; and performing scene judgment on the generalized scene according to the road description file and the target information to obtain an extreme driving scene, and collecting the extreme driving scene to obtain an intelligent driving scene library for simulation test.

According to the technical means, the embodiment of the application can enumerate the associated parameters to generalize the collected scenes by collecting the appropriate scene library data to obtain a large number of generalization scenes, and acquire the road description files and the target vehicle information files in the generalization scenes; analyzing the road description file to obtain target information of a target vehicle, judging the generalization scene by using the RSS safe distance model to obtain an extreme driving scene, collecting the obtained extreme driving scene to form an intelligent driving scene library so as to facilitate the subsequent corresponding testing, evaluation and other purposes of the intelligent driving mode, and dynamically updating and managing the intelligent driving scene library to continuously improve the generalization capability of the intelligent driving scene.

Optionally, in an embodiment of the present application, the obtaining a driving scene, generalizing the driving scene to obtain a generalization scene, and obtaining a road description file and a target vehicle information file of the generalization scene specifically includes: acquiring an existing driving scene and associated parameters, and generalizing the driving scene according to the associated parameters to obtain a generalization scene; and acquiring a road description file of the generalization scene according to a first preset format, and acquiring a target vehicle information file of the generalization scene according to a second preset format.

According to the technical means, the embodiment of the application acquires a large number of generalized scenes by collecting the appropriate scene library data in the existing scene library and enumerating the associated parameters to generalize the collected scenes, so that scenes occurring in real traffic conditions can be better simulated; then obtaining a road description file of the generalization scene, namely describing static content in the simulated real scene, expanding according to the self-defined data, and defining a target vehicle information file of the generalization scene, namely defining dynamic content of the simulated real scene; and acquiring the road description file and the target vehicle information file in batches so as to facilitate the subsequent input of the RSS safe distance model for judgment.

Optionally, in an embodiment of the present application, the parsing the target vehicle information file to obtain target information of the target vehicle specifically includes: acquiring a target vehicle, an initialization element, scene contents and an action set of the target vehicle information file, and processing the initialization element, the scene contents and the action set according to object-oriented programming to obtain a point track of the target vehicle; acquiring rectangular coordinates of the point track, converting the rectangular coordinates to obtain longitude and latitude coordinates, and obtaining longitude and latitude information of the point track based on the longitude and latitude coordinates; and extracting a configuration file path corresponding to the target vehicle, and obtaining target information of the target vehicle according to the longitude and latitude information and the configuration file path.

According to the technical means, after obtaining the target vehicle information file, the embodiment of the application needs to analyze the target vehicle information file to obtain the target vehicle, the initialization element, the scene content and the action set of the target vehicle information file, and processes the initialization element, the scene content and the action set according to the object-oriented programming to obtain the point track of the target vehicle; then, acquiring rectangular coordinates of the point track, converting the rectangular coordinates to obtain longitude and latitude coordinates, and obtaining longitude and latitude information of the point track based on the longitude and latitude coordinates; and extracting a configuration file path corresponding to the target vehicle, obtaining target information of the target vehicle according to the longitude and latitude information and the configuration file path, and analyzing by an efficient analysis algorithm, so that the target information of the target vehicle can be obtained more efficiently.

Optionally, in one embodiment of the present application, the target information includes target vehicle track information and speed information.

According to the technical means, the method and the device for judging the extreme driving scene can obtain corresponding target vehicle track information and speed information by analyzing the target vehicle information file, so that the extreme driving scene can be accurately judged later.

Optionally, in an embodiment of the present application, the performing scene determination on the generalized scene according to the road description file and the target information to obtain an extreme driving scene, and collecting the extreme driving scene to obtain an intelligent driving scene library for simulation test, includes: acquiring driver information and initial vehicle dynamics information, and creating a responsibility sensitive safety model; inputting the driver information, the initial vehicle dynamics information, the road description file and the target information into the responsibility sensitive safety model to obtain the position information, the kinematic parameters and the transverse and longitudinal distances of the target vehicle; and performing scene judgment on the generalized scene according to the position information, the kinematic parameters and the transverse and longitudinal distances to obtain a plurality of extreme driving scenes, and collecting the extreme driving scenes to obtain an intelligent driving scene library for simulation test.

According to the technical means, the embodiment of the application judges the generalized scenes by using the RSS safe distance model, namely the responsibility sensitive safety model, determines which generalized scenes are extreme driving scenes so as to be convenient for carrying out relevant simulation tests, and creates the responsibility sensitive safety model by acquiring driver information and initial vehicle dynamics information; inputting the driver information, the initial vehicle dynamics information, the road description file and the target information into the responsibility sensitive safety model to obtain the position information, the kinematic parameters and the transverse and longitudinal distances of the target vehicle; performing scene judgment on the generalized scene according to the position information, the kinematic parameters and the transverse and longitudinal distances to obtain an extreme driving scene; the purpose is to filter the generalized intelligent driving scene to obtain the required extreme driving scene; and collecting each extreme driving scene to obtain an intelligent driving scene library for simulation test, so that the intelligent driving scene library is used for simulation test, the safety of an intelligent driving system is improved, and the intelligent driving scene library can be dynamically updated and managed to continuously improve the scene generalization capability of the system.

Optionally, in an embodiment of the present application, the inputting the driver information, the initial vehicle dynamics information, the road description file, and the target information into the responsibility sensitive security model obtains location information, kinematic parameters, and a lateral-longitudinal distance of the target vehicle, which specifically includes: initializing the initial dynamics information, the road description file and the target information to obtain initialization information; creating a target scene according to the initialization information, and acquiring a world model; and processing the target scene based on the world model to obtain a processing result, and acquiring the position information, the kinematic parameters and the transverse and longitudinal distances of the target vehicle according to the processing result.

According to the technical means, the embodiment of the application can initialize the initial dynamics information, the road description file and the target information to obtain initialization information; creating a target scene according to the initialization information, and acquiring a world model; and processing the target scene based on the world model to obtain a processing result, acquiring the position information, the kinematic parameters and the transverse and longitudinal distances of the target vehicle according to the processing result, and more accurately judging which generalized scenes are extreme driving scenes through the position information, the kinematic parameters and the transverse and longitudinal distances.

Optionally, in an embodiment of the present application, the performing scene determination on the generalized scene according to the position information, the kinematic parameter, and the lateral-longitudinal distance to obtain an extreme driving scene specifically includes: judging whether the transverse and longitudinal distances are larger than a preset safety distance according to the position information; if the transverse and longitudinal distances are larger than the preset safety distance, judging whether the information of the kinematic parameters is dangerous or not; and if the information of the kinematic parameters is dangerous, determining that the generalized scene is an extreme driving scene.

According to the technical means, whether the transverse and longitudinal distances are larger than the preset safety distance can be judged according to the position information; if the transverse and longitudinal distances are preset safe distances, removing the generalized scene so as to reduce the interference of the non-extreme driving scene; if the transverse and longitudinal distances are larger than the preset safety distance, judging whether the information of the kinematic parameters is dangerous or not; if the information of the kinematic parameters is dangerous, the generalized scene is determined to be an extreme driving scene, so that the extreme driving scene can be determined more accurately, and the scene generalization capability of the intelligent driving system is improved.

An embodiment of a second aspect of the present application provides an intelligent driving scenario processing system of a vehicle, the intelligent driving scenario processing system of a vehicle including: the generalization analysis module is used for acquiring a driving scene, generalizing the driving scene to obtain a generalization scene, acquiring a road description file and a target vehicle information file of the generalization scene, and analyzing the target vehicle information file to obtain target information of a target vehicle; and the driving scene judging module is used for judging the generalized scene according to the road description file and the target information to obtain an extreme driving scene, and collecting the extreme driving scene to obtain an intelligent driving scene library for simulation test.

Optionally, in one embodiment of the present application, the generalization and analysis module includes: the scene generalization unit is used for acquiring the existing driving scene and the related parameters, and generalizing the driving scene according to the related parameters to obtain a generalization scene; the file acquisition unit is used for acquiring a road description file of the generalization scene according to a first preset format and acquiring a target vehicle information file of the generalization scene according to a second preset format; the information processing unit is used for acquiring a target vehicle, an initialization element, scene contents and an action set of the target vehicle information file, and processing the initialization element, the scene contents and the action set according to object-oriented programming to obtain a point track of the target vehicle; the file analysis unit is used for acquiring rectangular coordinates of the point track, converting the rectangular coordinates to obtain longitude and latitude coordinates, and obtaining longitude and latitude information of the point track based on the longitude and latitude coordinates; the data extraction unit is used for extracting a configuration file path corresponding to the target vehicle and obtaining target information of the target vehicle according to the longitude and latitude information and the configuration file path.

Optionally, in one embodiment of the present application, the driving scenario determination module includes: the system comprises a model creation unit, a responsibility sensitive safety model, a control unit and a control unit, wherein the model creation unit is used for acquiring driver information and initial vehicle dynamics information and creating a responsibility sensitive safety model; the data processing sub-module is used for inputting the driver information, the initial vehicle dynamics information, the road description file and the target information into the responsibility sensitive safety model to obtain the position information, the kinematic parameters and the transverse and longitudinal distances of the target vehicle; and the scene judging sub-module is used for judging the generalized scene according to the position information, the kinematic parameters and the transverse and longitudinal distances to obtain an extreme driving scene, and collecting the extreme driving scene to obtain an intelligent driving scene library for simulation test.

Optionally, in one embodiment of the present application, the data processing submodule includes: the data initialization unit is used for initializing the initial dynamics information, the road description file and the target information to obtain initialization information; the scene creation unit is used for creating a target scene according to the initialization information and acquiring a world model; and the result processing unit is used for processing the target scene based on the world model to obtain a processing result, and acquiring the position information, the kinematic parameters and the transverse and longitudinal distances of the target vehicle according to the processing result.

Optionally, in one embodiment of the present application, the scene determination submodule includes: the first judging unit is used for judging whether the transverse and longitudinal distances are larger than a preset safety distance according to the position information; the second judging unit is used for judging whether the information of the kinematic parameters is dangerous or not if the transverse and longitudinal distances are larger than the preset safety distance; and the scene determining unit is used for determining that the generalized scene is an extreme driving scene if the information of the kinematic parameters is dangerous.

An embodiment of a third aspect of the present application provides a terminal, including: the intelligent driving scene processing method comprises the steps of the intelligent driving scene processing method of the vehicle, wherein the intelligent driving scene processing program of the vehicle is executed by the processor.

An embodiment of a fourth aspect of the present application provides a computer-readable storage medium storing an intelligent driving scenario processing program of a vehicle, which when executed by a processor, implements the steps of the intelligent driving scenario processing method of a vehicle as described in the above embodiment.

The beneficial effects of this application:

(1) According to the method and the device, the collected scenes can be generalized by collecting the appropriate scene library data and enumerating the associated parameters, so that a large number of generalized scenes are obtained, and the road description file and the target vehicle information file in the generalized scenes are obtained; analyzing the road description file to obtain target information of a target vehicle, judging the generalization scene by using the RSS safe distance model to obtain a plurality of extreme driving scenes, collecting the obtained extreme driving scenes to form an intelligent driving scene library so as to facilitate the subsequent use of corresponding testing, evaluation and the like of the intelligent driving mode, and dynamically updating and managing the intelligent driving scene library so as to continuously improve the generalization capability of the intelligent driving scene.

(2) After obtaining a target vehicle information file, the embodiment of the application needs to analyze the target vehicle information file to obtain a target vehicle, an initialization element, scene content and an action set of the target vehicle information file, and processes the initialization element, the scene content and the action set according to object-oriented programming to obtain a point track of the target vehicle; and then, acquiring rectangular coordinates of the point track, converting the rectangular coordinates to obtain longitude and latitude coordinates, obtaining longitude and latitude information of the point track based on the longitude and latitude coordinates, extracting a configuration file path corresponding to the target vehicle, obtaining target information of the target vehicle according to the longitude and latitude information and the configuration file path, and analyzing by an efficient analysis algorithm, so that the target information of the target vehicle can be obtained more efficiently.

(3) Judging generalized scenes by using an RSS safety distance model, namely a responsibility sensitive safety model, determining which generalized scenes are extreme driving scenes so as to perform relevant simulation tests, and establishing the responsibility sensitive safety model by acquiring driver information and initial vehicle dynamics information; inputting the driver information, the initial vehicle dynamics information, the road description file and the target information into the responsibility sensitive safety model to obtain the position information, the kinematic parameters and the transverse and longitudinal distances of the target vehicle; performing scene judgment on the generalized scene according to the position information, the kinematic parameters and the transverse and longitudinal distances to obtain an extreme driving scene; the purpose is to filter the generalized intelligent driving scene to obtain the required extreme driving scene; and collecting each extreme driving scene to obtain an intelligent driving scene library for simulation test, so that the intelligent driving scene library is used for simulation test, the safety of an intelligent driving system is improved, and the intelligent driving scene library can be dynamically updated and managed to continuously improve the scene generalization capability of the system.

(4) The embodiment of the application can initialize the initial dynamics information, the road description file and the target information to obtain initialization information; creating a target scene according to the initialization information, and acquiring a world model; and processing the target scene based on the world model to obtain a processing result, acquiring the position information, the kinematic parameters and the transverse and longitudinal distances of the target vehicle according to the processing result, and more accurately judging which generalized scenes are extreme driving scenes through the position information, the kinematic parameters and the transverse and longitudinal distances.

(5) According to the embodiment of the application, whether the transverse and longitudinal distances are larger than the preset safety distance can be judged according to the position information; if the transverse and longitudinal distances are preset safe distances, removing the generalized scene so as to reduce the interference of the non-extreme driving scene; if the transverse and longitudinal distances are larger than the preset safety distance, judging whether the information of the kinematic parameters is dangerous or not; if the information of the kinematic parameters is dangerous, the generalized scene is determined to be an extreme driving scene, so that the extreme driving scene can be determined more accurately, and the scene generalization capability of the intelligent driving system is improved.

Additional aspects and advantages of the application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the application.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required for the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of a preferred embodiment of a method of intelligent driving scenario processing for a vehicle of the present application;

FIG. 2 is a general flow chart of a preferred embodiment of a method for intelligent driving scenario processing of a vehicle of the present application;

FIG. 3 is a schematic diagram of the architecture of a preferred embodiment of the intelligent driving scenario processing system of the vehicle of the present application;

fig. 4 is a schematic structural diagram of a preferred embodiment of the terminal of the present application.

Wherein, the intelligent driving scene processing system of the 10-vehicle; a 100-generalization analysis module and a 200-driving scene judgment module; 501-memory, 502-processor and 503-communication interface.

Detailed Description

Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and intended for the purpose of explaining the present application and are not to be construed as limiting the present application.

The following describes an intelligent driving scene processing method, system and terminal of a vehicle according to an embodiment of the present application with reference to the accompanying drawings. Aiming at the problems that the scene generalization capability of the existing intelligent driving system is low and the extreme use case scene cannot be accurately judged in the background art, the application provides an intelligent driving scene processing method of a vehicle, wherein in the method, collected scenes can be generalized by collecting proper scene library data and enumerating associated parameters to obtain a large number of generalized scenes, and road description files and target vehicle information files in the generalized scenes are acquired; analyzing the road description file to obtain target information of a target vehicle, judging the generalization scene by using the RSS safe distance model to obtain an extreme driving scene, collecting the obtained extreme driving scene to form an intelligent driving scene library so as to facilitate the subsequent corresponding testing, evaluation and other purposes of the intelligent driving mode, and dynamically updating and managing the intelligent driving scene library to continuously improve the generalization capability of the intelligent driving scene. Therefore, the problem that the scene generalization capability of the existing intelligent driving system is low, and the extreme use case scene cannot be accurately judged is solved.

Specifically, fig. 1 is a flow chart of a method for processing an intelligent driving scenario of a vehicle according to an embodiment of the present application.

As shown in fig. 1, the intelligent driving scene processing method of the vehicle includes the following steps:

in step S101, a driving scene is acquired, the driving scene is generalized to obtain a generalized scene, a road description file and a target vehicle information file of the generalized scene are acquired, and the target vehicle information file is analyzed to obtain target information of a target vehicle.

It can be understood that in the embodiment of the present application, by collecting appropriate relevant driving scenes, for example, simulation scenes with functions of blind detection or post collision early warning, from a scene library existing in the cloud, and enumerating relevant parameters, the collected relevant driving scenes are generalized by the relevant parameters, including performing calculation and acquisition on parameters that need to be obtained by secondary processing according to an initial parameter range, so as to obtain a generalized scene, that is, a driving scene that occurs in a simulated real traffic condition is obtained, and a plurality of parameters are generalized; after the generalized scene is obtained, xodr files (i.e., road description files) and xosc files (i.e., target vehicle information files) need to be obtained in batches, the purpose of obtaining the road description files and the target vehicle information files is to be input scene files of subsequent steps, and the road description files are files of an OpenDRIVE format, wherein static contents in a simulated driving scene, such as the geometric shape of a road, related characteristics affecting road network logic, lane marker traffic lights and the like, are described in the road description files, and the current static contents can be expanded according to custom data; and the target vehicle information file is a file in the OpenScenario format, wherein the target vehicle information file defines dynamic content of the simulated driving scene, such as the behavior of traffic participants, and the like; therefore, the road description file of the generalized scene is obtained according to a first preset format, namely an OpenDRIVE format, and the target vehicle information file of the generalized scene is obtained according to a second preset format, namely an OpenScenario format.

That is, in the embodiment of the present application, appropriate scene library data is collected in the existing scene library, and the collected scenes are generalized by enumerating the associated parameters, so as to obtain a large number of generalized scenes, so that scenes occurring in real traffic conditions can be better simulated; then obtaining a road description file of the generalization scene, namely describing static content in the simulated real scene, expanding according to the self-defined data, and defining a target vehicle information file of the generalization scene, namely defining dynamic content of the simulated real scene; the road description file and the target vehicle information file are obtained in batches so as to facilitate the subsequent input of an RSS safety distance model (Responsibility Sensitive Safety, responsibility sensitive safety model) which not only ensures that the safety distance between an automatic driving vehicle and other vehicles and pedestrians participating in road traffic is always kept and traffic rules are followed, but also can make rational and responsible decisions for judgment.

Further, after the reason description file and the target vehicle information file are obtained, the target vehicle information file needs to be parsed, and in the embodiment of the application, the target vehicle information file is parsed by using an oop programming mode (Object Oriented Programming, object-oriented programming) and an efficient parsing algorithm to obtain target information of the target vehicle; the target vehicle information file includes Init (initialization element), store (scene content) and Act (action set), wherein the initialization element defines initial conditions of a scene, such as initial position and speed of an entity, and in the application, lane change overtaking is taken as an example, namely two vehicles are initialized, in particular, which position of a road the two vehicles respectively run and how much speed of the two vehicles respectively run; scene content defines what will happen in the current scene; the action set answers the problem when the situation occurs in the time line of the scene content, the action set comprises a ManeuverGroup and a StartTrigger, and the action set can be executed only when the judgment of the start trigger is true; the operation group defines an operation sequence, and solves the problem of which Entity is allocated to the operation group as an action Entity in the scene; the operation of the operation group, i.e., the definition of "what to do", for example, in the embodiment of the present application, one lane-change overtaking operation is to be performed by one of the two vehicles, and it is conceivable that at least two "things" are to occur: the first is overtaking by road, and the second is returning to the original lane; the Event is a lane changing to the left, then the dynamic element of the scene is created or modified through action, only the specific action occurs, the dynamic element of the scene changes, and then the trigger is started to judge the current condition as true, the execution of the action is triggered, for example, in the example, the action of lane changing to the left is triggered only when the distance between a rear vehicle and a front vehicle is less than 30 m; the event is a lane change to the right, then the lane change is performed, namely, the lane returns to the original lane after overtaking, and then a trigger is started to prescribe that the operation group starts to be triggered from the moment, for example, the lane change overtaking operation group is triggered at the beginning of a simulated driving scene; the specific process of analyzing the target vehicle information file is as follows: acquiring a target vehicle, an initialization element, scene contents and an action set of the target vehicle information file, and processing the initialization element, the scene contents and the action set according to object-oriented programming to obtain a point track of the target vehicle; obtaining rectangular coordinates of the point track, converting the rectangular coordinates to obtain longitude and latitude coordinates, obtaining longitude and latitude information of the point track based on the longitude and latitude coordinates, extracting a configuration file path corresponding to the target vehicle, and obtaining target information of the target vehicle according to the longitude and latitude information and the configuration file path, wherein the target information comprises target vehicle track information and speed information.

That is, after obtaining a target vehicle information file, the embodiment of the present application needs to parse the target vehicle information file to obtain a target vehicle, an initialization element, scene content and an action set of the target vehicle information file, and process the initialization element, the scene content and the action set according to object-oriented programming to obtain a point track of the target vehicle; then, acquiring rectangular coordinates of the point track, converting the rectangular coordinates to obtain longitude and latitude coordinates, and obtaining longitude and latitude information of the point track based on the longitude and latitude coordinates; and extracting a configuration file path corresponding to the target vehicle, obtaining target information of the target vehicle according to the longitude and latitude information and the configuration file path, and analyzing by an efficient analysis algorithm, so that the target information of the target vehicle can be obtained more efficiently.

In step S102, the generalized scene is subjected to scene judgment according to the road description file and the target information, so as to obtain an extreme driving scene, and the extreme driving scene is collected, so as to obtain an intelligent driving scene library for simulation test.

It can be appreciated that after generalizing a large number of driving scenarios, a scenario judgment needs to be performed on the generalized driving scenario to determine an extreme driving scenario; in the embodiment of the application, the driving scene is judged through an RSS safe distance model (namely, a responsibility sensitive safe model), and which scenes are extreme driving scenes are determined; acquiring driver information and initial vehicle dynamics information of a current driving scene, and creating a responsibility sensitive safety model, wherein the responsibility sensitive safety model is used for judging whether the driving scene is an extreme driving scene or not, and the intelligent driving scene library is used for collecting the extreme driving scene obtained by judgment; inputting the driver information, the initial vehicle dynamics information, the road description file and the target information into the responsibility sensitive safety model to obtain the position information, the kinematic parameters and the transverse and longitudinal distances of the target vehicle; then judging whether the current driving scene is an extreme driving scene or not according to the obtained position information of each target vehicle relative to the other vehicle and the information of kinematic parameters, namely whether the information is dangerous (isSafe) and the transverse and longitudinal distances (latitudedidion and longitudinaldidion); performing scene judgment on the generalized scene according to the position information, the kinematic parameters and the transverse and longitudinal distances to obtain an extreme driving scene, and collecting the extreme driving scene to obtain an intelligent driving scene library for simulation test; the intelligent driving scene library can be used for subsequent purposes such as testing, evaluation and machine learning of the intelligent driving system, and can be continuously updated and expanded to improve the processing capacity of the intelligent driving system on different driving scenes, for example, intelligent driving algorithms such as testing, controlling and predicting of extreme driving scenes obtained by changing lanes of vehicles in front or leaving lanes of a host vehicle and the like in front.

That is, the embodiment of the application judges the generalized scenes by using an RSS safe distance model, namely a responsibility sensitive safety model, determines which generalized scenes are extreme driving scenes so as to perform relevant simulation tests, acquires driver information and initial vehicle dynamics information, and creates a responsibility sensitive safety model; inputting the driver information, the initial vehicle dynamics information, the road description file and the target information into the responsibility sensitive safety model to obtain the position information, the kinematic parameters and the transverse and longitudinal distances of the target vehicle; performing scene judgment on the generalized scene according to the position information, the kinematic parameters and the transverse and longitudinal distances to obtain an extreme driving scene; the purpose is to filter the generalized intelligent driving scene to obtain the required extreme driving scene; and collecting each extreme driving scene to obtain an intelligent driving scene library for simulation test, so that the intelligent driving scene library is used for simulation test, the safety of an intelligent driving system is improved, and the intelligent driving scene library can be dynamically updated and managed to continuously improve the scene generalization capability of the system.

Further, after the driver information, the initial vehicle dynamics information, the road description file and the target information are input into the responsibility sensitive security model, the responsibility sensitive security model initializes the initial dynamics information, the road description file and the target information to obtain initialization information; creating a target scene according to the initialization information through an ad_rss_lib interface, and acquiring a world model (the world model refers to simulation and expression of the real world constructed by a computer or an artificial intelligence system, and is a method for comprehensively describing and predicting the environment); and processing the target scene based on the world model to obtain a processing result, namely, passing through, and acquiring the position information, the kinematic parameters and the transverse and longitudinal distances of the target vehicle according to the processing result.

That is, the embodiment of the application may initialize the initial dynamics information, the road description file and the target information to obtain initialization information; creating a target scene according to the initialization information, and acquiring a world model; and processing the target scene based on the world model to obtain a processing result, acquiring the position information, the kinematic parameters and the transverse and longitudinal distances of the target vehicle according to the processing result, and more accurately judging which generalized scenes are extreme driving scenes through the position information, the kinematic parameters and the transverse and longitudinal distances.

Further, the responsibility sensitive safety model calculates a minimum safety distance according to the speed reaction time of the front and rear vehicles, a minimum braking acceleration, a maximum acceleration, a running direction of the vehicles and the like, compares the minimum safety distance with the transverse and longitudinal distances through the preset safety distance by taking the minimum safety distance as a threshold value and the preset safety distance, and judges the generalized scene as a safe driving scene to be removed if the transverse and longitudinal distances are smaller than the preset safety distance, for example, the transverse and longitudinal distances are 0; if the transverse and longitudinal distances are larger than the preset safety distance, judging whether the information of the kinematic parameters is dangerous or not; if the information of the kinematic parameters is not dangerous, determining that the generalized scene is a safe driving scene, and removing the safe driving scene; if the information of the kinematic parameters is dangerous, determining that the generalized scene is an extreme driving scene; and then collecting the obtained extreme driving scenes to obtain an intelligent driving scene library for simulation test.

That is, the embodiment of the present application may determine, according to the position information, whether the transverse-longitudinal distance is greater than a preset safety distance; if the transverse and longitudinal distances are preset safe distances, removing the generalized scene so as to reduce the interference of the non-extreme driving scene; if the transverse and longitudinal distances are larger than the preset safety distance, judging whether the information of the kinematic parameters is dangerous or not; if the information of the kinematic parameters is dangerous, the generalized scene is determined to be an extreme driving scene, so that the extreme driving scene can be determined more accurately, and the scene generalization capability of the intelligent driving system is improved.

The following is further a whole implementation procedure of the intelligent driving scene processing method of the vehicle, as shown in fig. 2:

step S1, starting;

step S2, acquiring an existing driving scene and associated parameters, and generalizing the driving scene according to the associated parameters to obtain a generalized scene; acquiring an xodr file of the generalization scene, namely a road description file, according to a first preset format, and acquiring an xosc file of the generalization scene, namely a target vehicle information file, according to a second preset format;

step S3, obtaining a target vehicle, an initialization element, scene contents and an action set of the target vehicle information file, and processing the initialization element, the scene contents and the action set according to object-oriented programming to obtain a point track of the target vehicle; acquiring rectangular coordinates of the point track, converting the rectangular coordinates to obtain longitude and latitude coordinates, obtaining longitude and latitude information of the point track based on the longitude and latitude coordinates, extracting a configuration file path corresponding to the target vehicle, and obtaining target information of the target vehicle according to the longitude and latitude information and the configuration file path;

S4, acquiring driver information and initial vehicle dynamics information, and creating an RSS safe distance model, namely a responsibility sensitive safe model; inputting the driver information, the initial vehicle dynamics information, the road description file and the target information into the responsibility sensitive safety model to obtain the position information, the kinematic parameters and the transverse and longitudinal distances of the target vehicle; performing scene judgment on the generalized scene according to the position information, the kinematic parameters and the transverse and longitudinal distances;

step S5, if the generalized scene is judged to be a safe driving scene, executing a step S6; if the generalized scene is judged to be the extreme driving scene, executing a step S7;

step S6, if the generalized scene is judged to be the safe driving scene, the generalized scene is removed, and an intelligent driving scene library is not added;

step S7, if the generalized scene is judged to be an extreme driving scene, adding the generalized scene into an intelligent driving scene library;

step S8, ending.

In summary, the embodiment of the application can enumerate the associated parameters to generalize the collected scenes by collecting the appropriate scene library data to obtain a large number of generalized scenes, and acquire the road description file and the target vehicle information file in the generalized scenes; analyzing the road description file to obtain target information of a target vehicle, judging the generalization scene by using the RSS safe distance model to obtain an extreme driving scene, collecting the obtained extreme driving scene to form an intelligent driving scene library so as to facilitate the subsequent corresponding testing, evaluation and other purposes of the intelligent driving mode, and dynamically updating and managing the intelligent driving scene library to continuously improve the generalization capability of the intelligent driving scene.

Next, an intelligent driving scenario processing system of a vehicle according to an embodiment of the present application will be described with reference to the accompanying drawings.

Fig. 3 is a block schematic diagram of an intelligent driving scenario processing system of a vehicle according to an embodiment of the present application.

As shown in fig. 3, the intelligent driving scenario processing system 10 of the vehicle includes: a generalization analysis module 100 and a driving scenario determination module 200.

Specifically, the generalization analysis module 100 is configured to obtain a driving scene, generalize the driving scene to obtain a generalization scene, obtain a road description file and a target vehicle information file of the generalization scene, and analyze the target vehicle information file to obtain target information of a target vehicle.

And the driving scene judging module 200 is used for judging the generalized scene according to the road description file and the target information to obtain an extreme driving scene, and collecting the extreme driving scene to obtain an intelligent driving scene library for simulation test.

Optionally, in one embodiment of the present application, the generalization and analysis module 100 includes: the system comprises a scene generalization unit, a file acquisition unit, an information processing unit, a file analysis unit and a data extraction unit.

The scene generalization unit is used for acquiring the existing driving scene and the related parameters, and generalizing the driving scene according to the related parameters to obtain a generalization scene.

The file acquisition unit is used for acquiring the road description file of the generalization scene according to a first preset format and acquiring the target vehicle information file of the generalization scene according to a second preset format.

The information processing unit is used for acquiring a target vehicle, an initialization element, scene contents and an action set of the target vehicle information file, and processing the initialization element, the scene contents and the action set according to object-oriented programming to obtain a point track of the target vehicle.

The file analysis unit is used for acquiring rectangular coordinates of the point track, converting the rectangular coordinates to obtain longitude and latitude coordinates, and obtaining longitude and latitude information of the point track based on the longitude and latitude coordinates;

the data extraction unit is used for extracting a configuration file path corresponding to the target vehicle and obtaining target information of the target vehicle according to the longitude and latitude information and the configuration file path.

Optionally, in one embodiment of the present application, the driving scenario determination module 200 includes: the system comprises a model creation unit, a data processing sub-module and a scene judging sub-module.

The system comprises a model creation unit, a control unit and a control unit, wherein the model creation unit is used for acquiring driver information and initial vehicle dynamics information and creating a responsibility sensitive safety model.

And the data processing sub-module is used for inputting the driver information, the initial vehicle dynamics information, the road description file and the target information into the responsibility sensitive safety model to obtain the position information, the kinematic parameters and the transverse and longitudinal distances of the target vehicle.

And the scene judging sub-module is used for judging the generalized scene according to the position information, the kinematic parameters and the transverse and longitudinal distances to obtain an extreme driving scene, and collecting the extreme driving scene to obtain an intelligent driving scene library for simulation test.

Optionally, in one embodiment of the present application, the data processing submodule includes: the system comprises a data initialization unit, a scene creation unit and a result processing unit.

The data initializing unit is used for initializing the initial dynamics information, the road description file and the target information to obtain initialization information.

And the scene creation unit is used for creating a target scene according to the initialization information and acquiring a world model.

And the result processing unit is used for processing the target scene based on the world model to obtain a processing result, and acquiring the position information, the kinematic parameters and the transverse and longitudinal distances of the target vehicle according to the processing result.

Optionally, in one embodiment of the present application, the scene determination submodule includes: the device comprises a first judging unit, a second judging unit and a scene determining unit.

The first judging unit is used for judging whether the transverse and longitudinal distances are larger than a preset safety distance according to the position information.

And the second judging unit is used for judging whether the information of the kinematic parameters is dangerous or not if the transverse and longitudinal distances are larger than the preset safety distance.

And the scene determining unit is used for determining that the generalized scene is an extreme driving scene if the information of the kinematic parameters is dangerous.

It should be noted that the foregoing explanation of the embodiment of the method for processing an intelligent driving scenario of a vehicle is also applicable to the intelligent driving scenario processing system of a vehicle in this embodiment, and will not be repeated here.

According to the intelligent driving scene processing system of the vehicle, which is provided by the embodiment of the application, collected scenes can be generalized by collecting proper scene library data and enumerating associated parameters, so that a large number of generalized scenes are obtained, and road description files and target vehicle information files in the generalized scenes are obtained; analyzing the road description file to obtain target information of a target vehicle, judging the generalization scene by using the RSS safe distance model to obtain an extreme driving scene, collecting the obtained extreme driving scene to form an intelligent driving scene library so as to facilitate the subsequent corresponding testing, evaluation and other purposes of the intelligent driving mode, and dynamically updating and managing the intelligent driving scene library to continuously improve the generalization capability of the intelligent driving scene.

Therefore, the problem that the scene generalization capability of the existing intelligent driving system is low, and the extreme use case scene cannot be accurately judged is solved.

Fig. 4 is a schematic structural diagram of a terminal according to an embodiment of the present application. The terminal may include:

memory 501, processor 502, and a computer program stored on memory 501 and executable on processor 502.

The processor 502 implements the intelligent driving scenario processing method of the vehicle provided in the above embodiment when executing a program.

Further, the terminal further includes:

a communication interface 503 for communication between the memory 501 and the processor 502.

Memory 501 for storing a computer program executable on processor 502.

Memory 501 may comprise high-speed RAM memory and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.

If the memory 501, the processor 502, and the communication interface 503 are implemented independently, the communication interface 503, the memory 501, and the processor 502 may be connected to each other via a bus and perform communication with each other. The bus may be an Industry Standard Architecture (ISA) bus, an external device interconnect (PCI) bus, an extended industry standard architecture (EIS) bus, or the like. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in fig. 4, but not only one bus or one type of bus.

Alternatively, in a specific implementation, if the memory 501, the processor 502, and the communication interface 503 are integrated on a chip, the memory 501, the processor 502, and the communication interface 503 may perform communication with each other through internal interfaces.

The processor 502 may be a Central Processing Unit (CPU) or an Application Specific Integrated Circuit (ASIC) or one or more integrated circuits configured to implement embodiments of the present application.

The present embodiment also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the intelligent driving scenario processing method of a vehicle as above.

In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or N embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.

Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "N" is at least two, such as two, three, etc., unless explicitly defined otherwise.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and additional implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order from that shown or discussed, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present application.

Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable storage medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable storage medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection (electronic device) having one or N wires, a portable computer cartridge (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable storage medium may even be paper or other suitable medium upon which the program is printed, as the program may be electronically captured, via optical scanning of the paper or other medium, then compiled, interpreted, or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.

It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the N steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As with the other embodiments, if implemented in hardware, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.

Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.

In addition, each functional unit in each embodiment of the present application may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.

The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like. Although embodiments of the present application have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the application, and that variations, modifications, alternatives, and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the application.

It is to be understood that the application of the present application is not limited to the examples described above, but that modifications and variations can be made by a person skilled in the art from the above description, all of which modifications and variations are intended to fall within the scope of the claims appended hereto.

Claims (10)

1. The intelligent driving scene processing method of the vehicle is characterized by comprising the following steps of: obtaining a driving scene, generalizing the driving scene to obtain a generalization scene, obtaining a road description file and a target vehicle information file of the generalization scene, and analyzing the target vehicle information file to obtain target information of a target vehicle;

and performing scene judgment on the generalized scene according to the road description file and the target information to obtain an extreme driving scene, and collecting the extreme driving scene to obtain an intelligent driving scene library for simulation test.

2. The method for processing the intelligent driving scene of the vehicle according to claim 1, wherein the steps of obtaining the driving scene, generalizing the driving scene to obtain a generalization scene, and obtaining a road description file and a target vehicle information file of the generalization scene specifically include:

acquiring an existing driving scene and associated parameters, and generalizing the driving scene according to the associated parameters to obtain a generalization scene; and acquiring a road description file of the generalization scene according to a first preset format, and acquiring a target vehicle information file of the generalization scene according to a second preset format.

3. The method for processing the intelligent driving scene of the vehicle according to claim 1, wherein the analyzing the target vehicle information file to obtain the target information of the target vehicle specifically includes:

acquiring a target vehicle, an initialization element, scene contents and an action set of the target vehicle information file, and processing the initialization element, the scene contents and the action set according to object-oriented programming to obtain a point track of the target vehicle;

acquiring rectangular coordinates of the point track, converting the rectangular coordinates to obtain longitude and latitude coordinates, and obtaining longitude and latitude information of the point track based on the longitude and latitude coordinates;

And extracting a configuration file path corresponding to the target vehicle, and obtaining target information of the target vehicle according to the longitude and latitude information and the configuration file path.

4. A method of intelligent driving scenario processing of a vehicle according to claim 1 or 3, wherein the target information includes target vehicle track information and speed information.

5. The method for processing the intelligent driving scene of the vehicle according to claim 1, wherein the scene determination is performed on the generalized scene according to the road description file and the target information to obtain an extreme driving scene, and the extreme driving scene is collected to obtain an intelligent driving scene library for simulation test, and the method specifically comprises:

acquiring driver information and initial vehicle dynamics information, and creating a responsibility sensitive safety model;

inputting the driver information, the initial vehicle dynamics information, the road description file and the target information into the responsibility sensitive safety model to obtain the position information, the kinematic parameters and the transverse and longitudinal distances of the target vehicle;

and performing scene judgment on the generalized scene according to the position information, the kinematic parameters and the transverse and longitudinal distances to obtain an extreme driving scene, and collecting the extreme driving scene to obtain an intelligent driving scene library for simulation test.

6. The method for intelligent driving scenario processing of a vehicle according to claim 5, wherein the inputting the driver information, the initial vehicle dynamics information, the road description file and the target information into the responsibility sensitive security model, obtaining the position information, the kinematic parameters and the lateral-longitudinal distance of the target vehicle, specifically comprises:

initializing the initial dynamics information, the road description file and the target information to obtain initialization information;

creating a target scene according to the initialization information, and acquiring a world model;

and processing the target scene based on the world model to obtain a processing result, and acquiring the position information, the kinematic parameters and the transverse and longitudinal distances of the target vehicle according to the processing result.

7. The method for processing the intelligent driving scene of the vehicle according to claim 5, wherein the scene determination is performed on the generalized scene according to the position information, the kinematic parameters and the lateral-longitudinal distance to obtain an extreme driving scene, specifically comprising: judging whether the transverse and longitudinal distances are larger than a preset safety distance according to the position information;

If the transverse and longitudinal distances are larger than the preset safety distance, judging whether the information of the kinematic parameters is dangerous or not;

and if the information of the kinematic parameters is dangerous, determining that the generalized scene is an extreme driving scene.

8. An intelligent driving scenario processing system of a vehicle, characterized in that the intelligent driving scenario processing system of a vehicle comprises: the generalization analysis module is used for acquiring a driving scene, generalizing the driving scene to obtain a generalization scene, acquiring a road description file and a target vehicle information file of the generalization scene, and analyzing the target vehicle information file to obtain target information of a target vehicle;

and the driving scene judging module is used for judging the generalized scene according to the road description file and the target information to obtain an extreme driving scene, and collecting the extreme driving scene to obtain an intelligent driving scene library for simulation test.

9. A terminal, the terminal comprising: memory, a processor and a smart driving scenario processing program of a vehicle stored on the memory and executable on the processor, which when executed by the processor, implements the steps of the smart driving scenario processing method of a vehicle as claimed in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores an intelligent driving scenario processing program of a vehicle, which when executed by a processor, implements the steps of the intelligent driving scenario processing method of a vehicle according to any one of claims 1-7.