CN115577130A - Scene library construction method and device for vehicle simulation test and vehicle - Google Patents

Abstract

The invention discloses a method and a device for constructing a scene library for vehicle simulation test and a vehicle. Wherein, the method comprises the following steps: acquiring an original scene file corresponding to a vehicle simulation test scene, wherein static information and dynamic information of the vehicle simulation test scene are stored in the original scene file; extracting elements of an original scene file to obtain test scene elements, wherein the test scene elements comprise static scene elements and dynamic scene elements; analyzing and labeling the test scene elements in multiple dimensions to obtain a target label set, wherein the target label set comprises static element labels, dynamic element labels and test target labels; and constructing a target scene library of the vehicle simulation test scene based on the original scene file and the target label set. The invention solves the technical problems of low efficiency of scene library classification management, high maintenance cost and high difficulty of scene library construction caused by a large number of scene libraries.

Description

Scene library construction method and device for vehicle simulation test and vehicle

Technical Field

The invention relates to the field of automobiles, in particular to a method and a device for constructing a scene library of a vehicle simulation test and a vehicle.

Background

In order to ensure the safety of the automobile, in the development stage of the automobile, technicians perform real-vehicle tests and virtual simulation tests on the automobile. The construction and management of the simulation test scene library are important components of a vehicle virtual simulation test process, influence the efficiency and cost of the vehicle virtual simulation test, and play a key role in a vehicle test evaluation system. Due to the continuity of scene parameter distribution and the diversity of scene factor arrangement combination, the number of simulation test scene libraries is huge, and the prior art does not form a unified standard for constructing and classifying the simulation test scene libraries, so that the classification methods of the scene libraries are uneven, and further the management difficulty, the retrieval difficulty and the maintenance cost of the scene libraries are high.

In view of the above problems, no effective solution has been proposed.

Disclosure of Invention

The embodiment of the invention provides a method and a device for constructing a scene library for vehicle simulation test and a vehicle, which at least solve the technical problems of low efficiency of scene library classification management, high maintenance cost and high difficulty in scene library construction caused by a large number of scene libraries.

According to an aspect of an embodiment of the present invention, a method for constructing a scene library for a vehicle simulation test is provided, including:

acquiring an original scene file corresponding to a vehicle simulation test scene, wherein static information and dynamic information of the vehicle simulation test scene are stored in the original scene file; extracting elements of an original scene file to obtain test scene elements, wherein the test scene elements comprise static scene elements and dynamic scene elements; analyzing and labeling the test scene elements in multiple dimensions to obtain a target label set, wherein the target label set comprises static element labels, dynamic element labels and test target labels; and constructing a target scene library of the vehicle simulation test scene based on the original scene file and the target label set.

Optionally, performing element extraction on the original scene file to obtain a test scene element includes: splitting the original scene file to obtain static information and dynamic information of a vehicle simulation test scene; static scene elements are extracted from the static information, and dynamic scene elements are extracted from the dynamic information.

Optionally, the static information is road network information corresponding to a vehicle simulation test scenario, and extracting static scenario elements from the static information includes: automatically screening element fields in the road network information to obtain a first screening result; and extracting elements based on the first screening result to obtain static scene elements.

Optionally, the dynamic information includes traffic participant information and environmental information corresponding to the vehicle simulation test scenario, and extracting the dynamic scenario element from the dynamic information includes: automatically screening element fields in the traffic participant information and the environmental information to obtain a second screening result; and extracting elements based on the second screening result to obtain dynamic scene elements.

Optionally, analyzing and labeling the test scene elements in multiple dimensions, and obtaining the target tag set includes: analyzing and labeling feature dimensions of the test scene elements to obtain static element labels and dynamic element labels; and analyzing and labeling the target dimension of the test scene element to obtain a test target label.

Optionally, labeling the feature dimension of the test scene element to obtain a static element label and a dynamic element label includes: analyzing a plurality of static elements in the static scene elements, and determining at least one first feature corresponding to each static element in the plurality of static elements; labeling each static element by using at least one first characteristic to obtain a static element label; analyzing a plurality of dynamic elements in the dynamic scene elements, and determining at least one second characteristic corresponding to each dynamic element in the plurality of dynamic elements; and labeling each dynamic element by using at least one second characteristic to obtain a dynamic element label.

Optionally, the test target label includes a first test label and a second test label, and analyzing and labeling the target dimension on the test scene element to obtain the test target label includes: carrying out scene test target analysis on the test scene elements to obtain a plurality of categories of scene test targets; marking the test scene elements by using the scene test targets of a plurality of categories to obtain a first test label; performing driving function test target analysis on the scene test targets of a plurality of categories to obtain at least one category of driving function test target; and marking the test scene elements by using at least one type of driving function test target to obtain a second test label.

Optionally, constructing a target scene library of the vehicle simulation test scene based on the original scene file and the target label set includes: and classifying and summarizing the original scene files according to the target label set, and constructing a target scene library of the vehicle simulation test scene.

According to another aspect of the embodiments of the present invention, there is also provided a scene library construction apparatus for vehicle simulation testing, including:

the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring an original scene file corresponding to a vehicle simulation test scene, and the original scene file stores static information and dynamic information of the vehicle simulation test scene;

the extraction module is used for extracting elements of the original scene file to obtain test scene elements, wherein the test scene elements comprise static scene elements and dynamic scene elements;

optionally, the extracting module is further configured to: the element extraction is carried out on the original scene file, and the obtaining of the test scene element comprises the following steps: splitting the original scene file to obtain static information and dynamic information of a vehicle simulation test scene; static scene elements are extracted from the static information, and dynamic scene elements are extracted from the dynamic information.

Optionally, the extracting module is further configured to: the static information is road network information corresponding to a vehicle simulation test scene, and the extraction of static scene elements from the static information comprises the following steps: automatically screening element fields in the road network information to obtain a first screening result; and extracting elements based on the first screening result to obtain static scene elements.

Optionally, the extracting module is further configured to: the dynamic information comprises traffic participant information and environmental information corresponding to a vehicle simulation test scene, and the extraction of dynamic scene elements from the dynamic information comprises the following steps: automatically screening the element fields in the traffic participant information and the environment information to obtain a second screening result; and extracting elements based on the second screening result to obtain dynamic scene elements.

The labeling module is used for analyzing and labeling the test scene elements in multiple dimensions to obtain a target label set, wherein the target label set comprises static element labels, dynamic element labels and test target labels;

optionally, the labeling module is further configured to: analyzing and labeling the test scene elements in multiple dimensions to obtain a target label set, wherein the target label set comprises the following steps: analyzing and labeling feature dimensions of the elements of the test scene to obtain static element labels and dynamic element labels; and analyzing and labeling the target dimension of the test scene element to obtain a test target label.

Optionally, the labeling module is further configured to: labeling feature dimensions of the test scene elements to obtain static element labels and dynamic element labels comprises the following steps: analyzing a plurality of static elements in the static scene elements, and determining at least one first feature corresponding to each static element in the plurality of static elements; labeling each static element by using at least one first characteristic to obtain a static element label; analyzing a plurality of dynamic elements in the dynamic scene elements, and determining at least one second characteristic corresponding to each dynamic element in the plurality of dynamic elements; and labeling each dynamic element by using at least one second characteristic to obtain a dynamic element label.

Optionally, the labeling module is further configured to: the test target label comprises a first test label and a second test label, and the analysis and labeling of the target dimension is carried out on the test scene element to obtain the test target label comprises the following steps: carrying out scene test target analysis on the test scene elements to obtain a plurality of categories of scene test targets; marking the test scene elements by using the scene test targets of a plurality of categories to obtain a first test label; performing driving function test target analysis on the scene test targets of a plurality of categories to obtain at least one category of driving function test target; and marking the test scene elements by using at least one type of driving function test target to obtain a second test label.

And the construction module is used for constructing a target scene library of the vehicle simulation test scene based on the original scene file and the target label set.

Optionally, the building module is further configured to: based on the original scene file and the target label set, constructing a target scene library of the vehicle simulation test scene comprises the following steps: and classifying and summarizing the original scene files according to the target label set, and constructing a target scene library of the vehicle simulation test scene.

According to another aspect of the embodiments of the present invention, there is also provided a vehicle, including an onboard memory and an onboard processor, the onboard memory storing therein a computer program, the onboard processor being configured to run the computer program to execute the scene library construction method of any one of the vehicle simulation tests.

In the embodiment of the invention, an original scene file corresponding to a vehicle simulation test scene is firstly obtained, wherein the original scene file stores static information and dynamic information of the vehicle simulation test scene, element extraction is carried out on the original scene file to obtain a test scene element, the test scene element comprises a static scene element and a dynamic scene element, analysis and marking of multiple dimensions are carried out on the test scene element to obtain a target label set, the target label set comprises a static element label, a dynamic element label and a test target label, and the target scene library of the vehicle simulation test scene is constructed based on the original scene file and the target label set, so that the aim of constructing the target scene library based on analysis and marking of the test scene element of the vehicle simulation test scene is fulfilled, thereby achieving the technical effects of improving the classification management efficiency of the scene library, reducing the maintenance cost of the scene library and reducing the construction difficulty of the scene library, and further solving the technical problems of low classification management efficiency, high maintenance cost and high construction difficulty of the scene library caused by a large number of the scene libraries.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and not to limit the invention. In the drawings:

FIG. 1 is a flow chart of a scene library construction method for vehicle simulation testing according to an embodiment of the invention;

FIG. 2 is a schematic diagram of a static information partitioning and labeling process in an alternative method for constructing a scene library for vehicle simulation testing according to an embodiment of the present invention;

FIG. 3 is a schematic diagram illustrating a dynamic information partitioning and labeling process in an alternative method for constructing a scene library for vehicle simulation testing according to an embodiment of the present invention;

FIG. 4 is a schematic diagram of an alternative scenario library construction process for vehicle simulation testing according to an embodiment of the present invention;

fig. 5 is a block diagram of a scene library construction device for vehicle simulation testing according to an embodiment of the present invention.

Detailed Description

In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

In accordance with an embodiment of the present invention, there is provided an embodiment of a scenario library construction method for vehicle simulation testing, it is noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions, and that while a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than here.

The method embodiments may be performed in an electronic device or similar computing device that includes a memory and a processor in a vehicle. Taking the example of operating on an electronic device of a vehicle, the electronic device of the vehicle may include one or more processors (which may include, but are not limited to, processing devices such as Central Processing Units (CPUs), graphics Processing Units (GPUs), digital Signal Processing (DSP) chips, microprocessors (MCUs), programmable logic devices (FPGAs), neural Network Processors (NPUs), tensor Processors (TPUs), artificial Intelligence (AI) type processors, etc.) and memory for storing data. Optionally, the electronic device of the automobile may further include a transmission device for a communication function, an input-output device, and a display device. It will be understood by those skilled in the art that the foregoing structural description is merely illustrative and not restrictive on the structure of the electronic device of the vehicle. For example, the electronic device of the vehicle may also include more or fewer components than described above, or have a different configuration than described above.

The memory may be used to store a computer program, for example, a software program and a module of application software, such as a computer program corresponding to the vehicle charging prompting method in the embodiment of the present invention, and the processor executes various functional applications and data processing by running the computer program stored in the memory, so as to implement the vehicle charging prompting method described above. The memory may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory may further include memory located remotely from the processor, and these remote memories may be connected to the mobile terminal through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The transmission device is used for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device includes a Network adapter (NIC), which can be connected to other Network devices through a base station so as to communicate with the internet. In one example, the transmission device may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.

The display device may be, for example, a touch screen type Liquid Crystal Display (LCD) and a touch display (also referred to as a "touch screen" or "touch display screen"). The liquid crystal display may enable a user to interact with a user interface of the mobile terminal.

In an embodiment of the present invention, a method for constructing a scene library for a vehicle simulation test of an electronic device running on a vehicle is provided, and fig. 1 is a flowchart of a method for constructing a scene library for a vehicle simulation test according to an embodiment of the present invention, as shown in fig. 1, the method includes the following steps:

s11, acquiring an original scene file corresponding to a vehicle simulation test scene, wherein the original scene file stores static information and dynamic information of the vehicle simulation test scene;

the vehicle can be an automobile with an intelligent internet function and can comprise an unmanned automobile.

The vehicle simulation test can simulate the real use environment of the vehicle, perform simulation detection on the functions of the vehicle (such as environmental perception, planning decision, multi-level auxiliary driving and the like), and can be used for verifying whether the execution process and the execution result of the functions of the vehicle are in accordance with expectations.

The vehicle simulation test scenario may be a scenario in which the vehicle needs to be tested in the vehicle simulation test process, and may be used to perform a simulation test on the vehicle.

The original scene may be the original vehicle simulation test scene before a series of processing operations are performed on the vehicle simulation test scene, and may be used to obtain a series of basic scene information (e.g., road information, traffic participant information, environmental information, etc.).

The original scene file is a file extracted from the original scene and containing a series of basic scene information, and can be used for analyzing and explaining the original scene where the vehicle is located.

The manner of obtaining the original scene file corresponding to the vehicle simulation test scene may be: collecting from sensors of an existing vehicle; obtaining from existing simulation data; obtained from data summarized by experts according to personal experience.

It should be noted here that the vehicle may be equipped with devices such as vehicle-mounted sensors, controllers, actuators, etc., and may integrate modern communication and network technologies to implement intelligent information exchange and sharing between the vehicle and people, roads, backgrounds, etc.

Step S12, element extraction is carried out on the original scene file to obtain a test scene element, wherein the test scene element comprises a static scene element and a dynamic scene element;

the test scenario elements may be scenario information related to scenario test requirements in the vehicle simulation test scenario, and may be used to represent the test requirements of the test scenario.

The static scene element may be an object or thing in a static state in the test scene.

The dynamic scene element may be an object or thing that is in a dynamic change in the test scene.

The element extraction of the original scene file may be performed by retrieving and extracting a field representing the test scene element from the original scene file.

It should be noted here that the static scene elements may include roads, traffic facilities, obstacles, and the like.

It should be further noted herein that the dynamic scene element may include a dynamic indication facility, communication environment information, and the like.

Step S13, analyzing and labeling the test scene elements in multiple dimensions to obtain a target label set, wherein the target label set comprises static element labels, dynamic element labels and test target labels;

the dimensions may be angles for analyzing and labeling the test scenario elements, and may be used to comprehensively characterize the characteristics of the test scenario elements.

The target label set may be a set of identifiers obtained after the analysis labeling of the test scenario elements in the multiple dimensions is performed, and the identifiers are used for summarizing and characterizing scenario test requirements.

The static element label may be an identifier obtained after performing the analysis labeling of the multiple dimensions on the static scene element, and is used to summarize and characterize a static test requirement of a scene.

The dynamic element label may be an identifier obtained after performing the analysis labeling of the multiple dimensions on the dynamic scene element, and is used to summarize and characterize a dynamic test requirement of a scene.

The test target label may be an identifier obtained after performing the analysis labeling of the multiple dimensions on the test scenario element, and is used to summarize and characterize scenario test requirements.

And S14, constructing a target scene library of the vehicle simulation test scene based on the original scene file and the target label set.

The target scene library may be a set of scenes meeting various scene test requirements, which are obtained after the plurality of original scenes are processed through the steps.

And constructing the vehicle simulation test scene based on the original scene file and the target label set, so as to obtain the target scene library meeting the scene test requirements.

In the embodiment of the invention, an original scene file corresponding to a vehicle simulation test scene is firstly obtained, wherein the original scene file stores static information and dynamic information of the vehicle simulation test scene, element extraction is carried out on the original scene file to obtain a test scene element, the test scene element comprises a static scene element and a dynamic scene element, analysis and marking of multiple dimensions are carried out on the test scene element to obtain a target label set, the target label set comprises a static element label, a dynamic element label and a test target label, and a target scene library of the vehicle simulation test scene is constructed based on the original scene file and the target label set, so that the aim of constructing the target scene library based on the analysis and marking of the test scene element of the vehicle simulation test scene is fulfilled, thereby realizing the technical effects of improving the classification management efficiency of the scene library, reducing the maintenance cost of the scene library and reducing the construction difficulty of the scene library, and further solving the technical problems of low classification management efficiency, high maintenance cost and high construction difficulty of the scene library caused by a large number of the scene libraries.

The above-described method of the above-described embodiment of the present invention is further described below.

In an alternative embodiment, in step S12, performing element extraction on the original scene file to obtain the test scene element may include the following steps:

step S121, splitting the original scene file to obtain static information and dynamic information of the vehicle simulation test scene;

step S122, extracting static scene elements from the static information, and extracting dynamic scene elements from the dynamic information.

The static information may be information of an object or thing in a static state in the vehicle simulation test scenario, and may be used to characterize the state of the object or thing in a static state in the vehicle simulation test scenario.

The dynamic information may be information of an object or thing that is in a dynamic change in the vehicle simulation test scenario, and may be used to characterize a state of the object or thing that is in a dynamic change in the vehicle simulation test scenario.

The scene splitting may be to split the original scene file into a static scene file and a dynamic scene file based on objects or things in different states (including static state and dynamic state) in the original scene.

The static scene element may be extracted from the static information by retrieving and extracting a field representing the static scene element from the static information.

The static scene element may be extracted from the static information by retrieving and extracting a field representing the dynamic scene element from the dynamic information.

The static scene element may include road network information.

The dynamic scene element may include traffic participant information and environment information.

It can also be understood that, according to the abstraction level of the scenario, the vehicle simulation test scenario may be divided into: a functional scene, a logical scene, and a specific scene; according to the source of the scene data, the vehicle simulation test scene can be divided into: natural driving scenes, dangerous working condition scenes, standard regulation scenes and parameter recombination scenes.

It is also understood that the dynamic scene element may further include the vehicle information, for example: basic attributes, location information, motion status, etc.

In an alternative embodiment, in step S122, the static information is road network information corresponding to a vehicle simulation test scenario, and extracting static scenario elements from the static information may include the following steps:

step S1221, automatically screening the element fields in the road network information to obtain a first screening result;

step S1222, performing element extraction based on the first screening result to obtain a static scene element.

The road network information may be information of various roads included in the vehicle simulation test scenario, and may include lanes, road sizes, sidewalks, bus stations, and the like.

The element field may be a field for characterizing the road network information in the static scene file.

The first filtering result may be a specific element field filtered from the road network information.

The specific element field may be a field that meets a requirement of a scenario test and is selected from the element fields.

The automatic screening may be to automatically search and select the specific element field from the element fields.

The static scene element may be a scene element in a static state corresponding to the specific element field, which is extracted from the first filtering result.

In the above alternative embodiment, the technical effects that can be achieved are: the road network information contained in the static information in the vehicle simulation test scene is screened and extracted to obtain the static scene elements meeting the scene test requirements, so that the accuracy of screening and extracting the vehicle road network information can be improved, the difficulty of constructing a target scene library is reduced, the efficiency of classifying and managing the scene library is improved, and the management cost of the scene library is reduced.

In an optional embodiment, in step S122, the dynamic information includes transportation participant information and environment information corresponding to the vehicle simulation test scenario, and extracting the dynamic scenario element from the dynamic information may include performing the following steps:

step S1223, automatically screening the element fields in the traffic participant information and the environment information to obtain a second screening result;

and step S1224, performing element extraction based on the second screening result to obtain dynamic scene elements.

The traffic participant information may be object information that affects decision planning of the vehicle in the vehicle simulation test scenario, and may include a vehicle speed of a surrounding vehicle, a motion state of a surrounding non-vehicle, a driving speed of a surrounding pedestrian, and the like.

The environmental information may be objective environmental information of the vehicle simulation test scene, and may include an environmental temperature, a weather condition, a lighting condition, and the like.

The element field may be a field in the dynamic scene file for representing the traffic participant information and the environment information.

The second filtering result may be a specific element field filtered from the traffic participant information and the environment information.

The specific element field may be a field that meets a requirement of a scenario test and is selected from the element fields.

The automatic screening may be to automatically search and select the specific element field from the element fields.

The dynamic scene element may be a scene element that is dynamically changed and that is extracted from the second filtering result and corresponds to the specific element field.

In the above alternative embodiment, the technical effects that can be achieved are: the method and the device have the advantages that traffic participant information and environmental information contained in the dynamic information in the vehicle simulation test scene are screened and extracted, dynamic scene elements meeting the scene test requirements are obtained, the accuracy of screening and extracting the traffic participant information and the environmental information of the vehicle can be improved, the difficulty of constructing a target scene library is reduced, the efficiency of classification management of the scene library is improved, and the management cost of the scene library is reduced.

In an optional embodiment, in step S13, performing analysis labeling on the test scenario elements in multiple dimensions to obtain a target tag set may include the following steps:

step S131, analyzing and labeling feature dimensions of the elements of the test scene to obtain static element labels and dynamic element labels;

step S132, analyzing and labeling the target dimension of the test scene element to obtain a test target label.

The test scenario elements may be the static scenario elements and the dynamic scenario elements in the vehicle simulation test scenario, and may be used to represent scenario test requirements of the vehicle simulation test.

The characteristic dimension may be a specific attribute category of the static element and the dynamic element in the vehicle simulation test scenario, and may be used to characterize a specific state of the static element and the dynamic element in the vehicle simulation test scenario.

The static element label may be an identifier for analyzing and labeling the static scene element based on the characteristic dimension, and may be used to represent the characteristic dimension to which the static scene element in the vehicle simulation test scene belongs.

The dynamic element tag may be an identifier for analyzing and labeling the dynamic scene element based on the characteristic dimension, and may be used to characterize the characteristic dimension to which the dynamic scene element in the vehicle simulation test scene belongs.

The target dimension may be a specific attribute type corresponding to a test purpose of the vehicle simulation test, which the static element and the dynamic element have, and may be used to characterize the test purpose of the vehicle simulation test.

The test target label may be a mark for analyzing and labeling the static scene element and the dynamic scene element based on the target dimension, and may be used for a test purpose of characterizing a vehicle simulation test.

The analyzing and labeling of the feature dimension of the test scene element may be to mark feature dimension identifiers to which the static scene element and the dynamic scene element belong.

The analyzing and labeling of the target dimension for the test scene element may be marking the target dimension identifier to which the static scene element and the dynamic scene element belong.

In an alternative embodiment, in step S131, labeling the feature dimension of the test scenario element to obtain the static element label and the dynamic element label may include the following steps:

step 1311, analyzing a plurality of static elements in the static scene elements, and determining at least one first feature corresponding to each static element in the plurality of static elements;

step S1312, labeling each static element by using at least one first feature to obtain a static element label;

step 1313, analyzing the plurality of dynamic elements in the dynamic scene element, and determining at least one second feature corresponding to each dynamic element in the plurality of dynamic elements;

step S1314, labeling each dynamic element with at least one second feature to obtain a dynamic element label.

The at least one first feature may be an attribute of at least one of the static elements, and may include at least a lane line color, a lane line pattern, a lane number, a length, a width, and the like, and may be used to characterize a state of the static element.

The static element tag may be a mark for marking the static element and representing the at least one first feature of the static element, and may be used to characterize the characteristic of the static element.

The at least one second characteristic may be an attribute of at least one of the dynamic elements, including at least a lane line color, a number, a driving state of the vehicle, a lateral behavior, a longitudinal behavior, and the like, and may be used to characterize a state of the dynamic element.

The dynamic element tag may be a label that marks the dynamic element and represents the at least one second feature of the dynamic element, and may be used to characterize the feature of the dynamic element.

In the above alternative embodiment, the technical effects that can be achieved are: the method has the advantages that a plurality of static elements and dynamic elements in the vehicle simulation test scene are analyzed, the characteristics of each static element and each dynamic element are determined, the static elements and the dynamic elements are labeled to obtain static element labels and dynamic element labels, deep analysis and understanding of the static elements and the dynamic elements can be achieved, accurate static element labels and dynamic element labels are obtained, accuracy of classification of a scene library is improved, and accuracy and efficiency of classification management of the scene library are improved.

In an alternative embodiment, in step S132, performing analysis labeling on the target dimension on the test scenario element to obtain a test target label may include the following steps:

step S1321, carrying out scene test target analysis on the test scene elements to obtain a plurality of categories of scene test targets;

step S1322, marking the test scene elements by using the scene test targets of a plurality of categories to obtain a first test label;

step S1323, performing driving function test target analysis on the scene test targets of multiple categories to obtain at least one category of driving function test target;

and step S1324, marking the test scene element by using at least one type of driving function test target to obtain a second test label.

The scenario test target may be a basic attribute of the scenario element related to a scenario test purpose.

The first test tag may be an action feature corresponding to the basic attribute, which the scene element has, and may include recognizing lane marking change, recognizing slope change, recognizing a bus stop, and the like.

The driving function may be the capability of the vehicle during driving, and may include light control, vehicle speed control, fault processing, vehicle surrounding environment monitoring, and the like.

The second test tag may be a capability feature corresponding to the driving function, which is obtained by abstracting the motion feature, and may include a road event response capability, a dynamic object recognition capability, an environmental response capability, and the like.

The labeling of the test scenario elements with the scenario test targets of the multiple categories may be an automated labeling of the test scenario elements in a vehicle simulation test system.

The labeling of the test scenario elements with the at least one category of driving function test targets may be an automatic labeling of the test scenario elements in a vehicle simulation test system.

Fig. 2 is a schematic diagram of a static information partitioning and labeling process in the optional vehicle simulation test scene library construction method according to the embodiment of the present invention, and as shown in fig. 2, static scene elements including road attributes and model attributes are extracted from map information included in the static information, where the road attributes include three scene elements of a lane, a road size, and a road elevation, and the model attributes include three scene elements of a sidewalk, a bus station, a bridge, and a tunnel.

As shown in fig. 2, the lane, road size, road elevation, sidewalk, and bus station are analyzed in detail to obtain more specific element attributes, wherein the lane includes lane color, lane style, and lane number; the road size comprises length and width; road elevation includes grade; the sidewalk comprises a width and a line shape; the bus station comprises patterns and images.

Still as shown in fig. 2, for the purpose of testing, the motion characteristics of the six scene elements are analyzed, and then motion characteristic labels are labeled for the six scene elements, where the motion characteristic label corresponding to the lane is to identify lane line changes, the motion characteristic label corresponding to the road size is to identify road changes, the motion characteristic label corresponding to the road elevation is to identify slope changes, the motion characteristic label corresponding to the sidewalk is to identify pedestrian crossings, the motion characteristic label corresponding to the bus stops is to identify bus stops, and the motion characteristic label corresponding to the bridge and the tunnel is to identify a bridge tunnel area.

As still shown in fig. 2, based on the driving function of the vehicle, analyzing and summarizing the capability feature corresponding to the action feature, and labeling a capability feature label for the static scene element, where the capability feature label corresponding to the road attribute is a road event response capability, and the capability feature label corresponding to the model attribute is a transportation facility response capability.

Fig. 3 is a schematic diagram of a dynamic information partitioning and labeling process in the optional scene library construction method for vehicle simulation testing according to the embodiment of the present invention, and as shown in fig. 3, dynamic scene elements including traffic participants and an environment are extracted from dynamic information, where the traffic participants include three scene elements of traffic vehicle characteristics, and traffic signal characteristics, and the environment includes two scene elements of weather and illumination.

As shown in fig. 3, the traffic vehicle characteristics, the vehicle characteristics, and the traffic signal characteristics are analyzed in detail to obtain more specific element attributes, wherein the traffic vehicle characteristics include lane line color, number, and vehicle driving state; the self-vehicle characteristics comprise transverse behaviors and longitudinal behaviors; traffic signal features include static signal lights, temporary traffic barriers.

Still as shown in fig. 3, based on the driving function of the vehicle, analyzing and summarizing the capability feature corresponding to the scene element, and labeling a capability feature tag for the dynamic scene element, where the capability feature tag for the traffic vehicle feature is a dynamic object recognition capability, the capability feature tag for the self vehicle feature is an automatic driving strategy capability, the capability feature tag for the static signal feature is a traffic signal recognition capability, and the capability feature tag for the environment is an environment response capability.

In the above alternative embodiment, the technical effects that can be achieved are: based on the category of the test scene element and the scene test target, the action characteristics and the capability characteristics of the test scene element are analyzed, the test scene element is labeled, the action characteristic label and the capability characteristic label which accord with the test target are obtained, deep analysis and understanding of the scene element can be achieved, the accurate capability label is obtained, the accuracy of classification of the scene library is improved, and therefore the accuracy and the efficiency of scene library management and scene library construction are improved.

In an alternative embodiment, in step S14, building a target scenario library of the vehicle simulation test scenario based on the original scenario file and the target tag set may include the following steps:

and step S141, classifying and summarizing the original scene files according to the target label set, and constructing a target scene library of the vehicle simulation test scene.

The target label set is a set of labels corresponding to the scene test target and labeling the test scene elements, and can be used for representing the test purpose.

The target scene library is a set of target scenes obtained after labeling the test scenes based on the target label set.

The classifying and summarizing of the original scene files refers to classifying the test scene files based on the types of the test scenes contained in the original scene and summarizing the test scene files of the same type.

It should be further noted here that the classifying and summarizing the original scene files may be an automatic classifying and summarizing of the original scene files in a vehicle simulation test system.

Fig. 4 is a schematic diagram of a scene library construction process for an optional vehicle simulation test according to an embodiment of the present invention, and as shown in fig. 4, an original scene file of a vehicle simulation test scene is first obtained, the original scene file is divided into static information and dynamic information, static element fields and dynamic element fields included in the static information and the dynamic information are respectively and automatically screened, static scene elements and dynamic scene elements are respectively extracted from the static element fields and the dynamic element fields, then the static scene elements and the dynamic scene elements are respectively labeled, characteristics of the static scene elements and the dynamic scene elements are determined, the test scene elements are labeled to obtain a test scene with a target capability label, and finally, the analysis and labeling of the above steps are performed on a plurality of test scenes to obtain a standard target scene library.

In the above alternative embodiment, the technical effects that can be achieved are: based on the target label set, a large number of original scene files are classified and summarized to obtain test scene files with clear categories, then a large number of test scenes are labeled to realize construction of a target scene library, accuracy of classification and construction of the scene library can be improved, and accordingly classification management efficiency of the scene library is improved.

In this embodiment, a scene library construction device for vehicle simulation testing is further provided, and the device is used for implementing the above embodiments and preferred embodiments, and the description of the device is omitted. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware or a combination of software and hardware is also possible and contemplated.

Fig. 5 is a block diagram of a scene library construction apparatus for vehicle simulation testing according to an embodiment of the present invention, as shown in fig. 5, the apparatus includes:

the acquiring module 51 is configured to acquire an original scene file corresponding to a vehicle simulation test scene, where the original scene file stores static information and dynamic information of the vehicle simulation test scene;

an extracting module 52, configured to perform element extraction on the original scene file to obtain a test scene element, where the test scene element includes a static scene element and a dynamic scene element;

the labeling module 53 is configured to perform analysis labeling on multiple dimensions on the test scene element to obtain a target label set, where the target label set includes a static element label, a dynamic element label, and a test target label;

and the building module 54 is used for building a target scene library of the vehicle simulation test scene based on the original scene file and the target label set.

Optionally, the extracting module 52 is further configured to: the element extraction is carried out on the original scene file, and the obtaining of the test scene element comprises the following steps: splitting the original scene file to obtain static information and dynamic information of a vehicle simulation test scene; static scene elements are extracted from the static information, and dynamic scene elements are extracted from the dynamic information.

Optionally, the extracting module 52 is further configured to: the static information is road network information corresponding to a vehicle simulation test scene, and the extraction of static scene elements from the static information comprises the following steps: automatically screening element fields in the road network information to obtain a first screening result; and extracting elements based on the first screening result to obtain static scene elements.

Optionally, the extracting module 52 is further configured to: the dynamic information comprises traffic participant information and environmental information corresponding to a vehicle simulation test scene, and the extraction of dynamic scene elements from the dynamic information comprises the following steps: automatically screening the element fields in the traffic participant information and the environment information to obtain a second screening result; and extracting elements based on the second screening result to obtain dynamic scene elements.

Optionally, the labeling module 53 is further configured to: analyzing and labeling the test scene elements in multiple dimensions to obtain a target label set, wherein the target label set comprises the following steps: analyzing and labeling feature dimensions of the elements of the test scene to obtain static element labels and dynamic element labels; and analyzing and labeling the target dimension of the test scene element to obtain a test target label.

Optionally, the labeling module 53 is further configured to: labeling feature dimensions of the test scene elements to obtain static element labels and dynamic element labels comprises the following steps: analyzing a plurality of static elements in the static scene elements, and determining at least one first feature corresponding to each static element in the plurality of static elements; labeling each static element by using at least one first characteristic to obtain a static element label; analyzing a plurality of dynamic elements in the dynamic scene elements, and determining at least one second characteristic corresponding to each dynamic element in the plurality of dynamic elements; and labeling each dynamic element by using at least one second characteristic to obtain a dynamic element label.

Optionally, the labeling module 53 is further configured to: the test target label comprises a first test label and a second test label, and the analysis and labeling of the target dimension is carried out on the test scene element to obtain the test target label comprises the following steps: carrying out scene test target analysis on the test scene elements to obtain a plurality of categories of scene test targets; marking the test scene elements by using the scene test targets of a plurality of categories to obtain a first test label; performing driving function test target analysis on the scene test targets of a plurality of categories to obtain at least one category of driving function test target; and marking the test scene elements by using at least one type of driving function test target to obtain a second test label.

Optionally, the building module 54 is further configured to: based on the original scene file and the target label set, the method for constructing the target scene library of the vehicle simulation test scene comprises the following steps: and classifying and summarizing the original scene files according to the target label set, and constructing a target scene library of the vehicle simulation test scene.

It should be noted that, the above modules may be implemented by software or hardware, and for the latter, the following may be implemented, but not limited to: the modules are all positioned in the same processor; alternatively, the modules are respectively located in different processors in any combination.

The embodiment of the invention also provides a storage medium which comprises a stored computer program, wherein when the computer program runs, the device where the storage medium is located is controlled to execute the steps in any one of the above-mentioned embodiments of the scene library construction method for the vehicle simulation test.

Alternatively, in the present embodiment, the storage medium may be configured to store a computer program for executing the steps of:

the method comprises the following steps that S1, an original scene file corresponding to a vehicle simulation test scene is obtained, wherein static information and dynamic information of the vehicle simulation test scene are stored in the original scene file;

s2, extracting elements of the original scene file to obtain test scene elements, wherein the test scene elements comprise static scene elements and dynamic scene elements;

s3, analyzing and labeling the test scene elements in multiple dimensions to obtain a target label set, wherein the target label set comprises static element labels, dynamic element labels and test target labels;

and S4, constructing a target scene library of the vehicle simulation test scene based on the original scene file and the target label set.

Optionally, in this embodiment, the storage medium may include, but is not limited to: various media capable of storing computer programs, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.

Embodiments of the present invention further provide a vehicle, including an onboard memory and an onboard processor, where the onboard memory stores a computer program, and the onboard processor is configured to run the computer program to execute any one of the foregoing scene library construction methods for vehicle simulation tests.

Optionally, in this embodiment, the onboard processor may be configured to execute the following steps by a computer program:

the method comprises the following steps that S1, an original scene file corresponding to a vehicle simulation test scene is obtained, wherein static information and dynamic information of the vehicle simulation test scene are stored in the original scene file;

s2, extracting elements of the original scene file to obtain test scene elements, wherein the test scene elements comprise static scene elements and dynamic scene elements;

s3, analyzing and labeling the test scene elements in multiple dimensions to obtain a target label set, wherein the target label set comprises static element labels, dynamic element labels and test target labels;

and S4, constructing a target scene library of the vehicle simulation test scene based on the original scene file and the target label set.

Optionally, for a specific example in this embodiment, reference may be made to the examples described in the above embodiment and optional implementation manners thereof, and this embodiment is not described herein again.

The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.

In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the embodiments provided in the present invention, it should be understood that the disclosed technical contents can be implemented in other manners. The above-described apparatus embodiments are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or may not be executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk, and various media capable of storing program codes.

The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.

Claims (10)

1. A scene library construction method for vehicle simulation test is characterized by comprising the following steps:

acquiring an original scene file corresponding to a vehicle simulation test scene, wherein static information and dynamic information of the vehicle simulation test scene are stored in the original scene file;

element extraction is carried out on the original scene file to obtain a test scene element, wherein the test scene element comprises a static scene element and a dynamic scene element;

analyzing and labeling the test scene element in multiple dimensions to obtain a target label set, wherein the target label set comprises a static element label, a dynamic element label and a test target label;

and constructing a target scene library of the vehicle simulation test scene based on the original scene file and the target label set.

2. The method of claim 1, wherein performing element extraction on the original scene file to obtain the test scene element comprises:

carrying out scene splitting on the original scene file to obtain the static information and the dynamic information of the vehicle simulation test scene;

the static scene element is extracted from the static information, and the dynamic scene element is extracted from the dynamic information.

3. The method of claim 2, wherein the static information is road network information corresponding to the vehicle simulation test scenario, and extracting the static scenario element from the static information comprises:

automatically screening the element fields in the road network information to obtain a first screening result;

and extracting elements based on the first screening result to obtain the static scene elements.

4. The method of claim 2, wherein the dynamic information includes traffic participant information and environmental information corresponding to the vehicle simulation test scenario, and wherein extracting the dynamic scenario element from the dynamic information includes:

automatically screening the element fields in the traffic participant information and the environment information to obtain a second screening result;

and extracting elements based on the second screening result to obtain the dynamic scene elements.

5. The method of claim 1, wherein performing multi-dimensional analysis labeling on the test scenario elements to obtain a target label set comprises:

analyzing and labeling feature dimensions of the test scene elements to obtain static element labels and dynamic element labels;

and analyzing and labeling the target dimension of the test scene element to obtain the test target label.

6. The method of claim 5, wherein labeling feature dimensions of the test scenario element to obtain the static element label and the dynamic element label comprises:

analyzing a plurality of static elements in the static scene elements, and determining at least one first feature corresponding to each static element in the plurality of static elements;

labeling each static element by using the at least one first characteristic to obtain a static element label;

analyzing a plurality of dynamic elements in the dynamic scene elements, and determining at least one second characteristic corresponding to each dynamic element in the plurality of dynamic elements;

and labeling each dynamic element by using the at least one second characteristic to obtain the dynamic element label.

7. The method of claim 5, wherein the test target label comprises a first test label and a second test label, and performing analysis labeling on the test scenario element for a target dimension to obtain the test target label comprises:

performing scene test target analysis on the test scene elements to obtain scene test targets of multiple categories;

marking the test scene elements by using the scene test targets of the multiple categories to obtain the first test label;

performing driving function test target analysis on the scene test targets of the multiple categories to obtain at least one category of driving function test target;

and marking the test scene elements by using the at least one type of driving function test target to obtain the second test label.

8. The method of claim 1, wherein constructing the target scenario library of the vehicle simulation test scenario based on the original scenario file and the target tag set comprises:

and classifying and summarizing the original scene files according to the target label set, and constructing a target scene library of the vehicle simulation test scene.

9. A scene library construction device for vehicle simulation test is characterized by comprising the following steps:

the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring an original scene file corresponding to a vehicle simulation test scene, and the original scene file stores static information and dynamic information of the vehicle simulation test scene;

the extraction module is used for extracting elements of the original scene file to obtain test scene elements, wherein the test scene elements comprise static scene elements and dynamic scene elements;

the labeling module is used for analyzing and labeling the test scene elements in multiple dimensions to obtain a target label set, wherein the target label set comprises static element labels, dynamic element labels and test target labels;

and the construction module is used for constructing a target scene library of the vehicle simulation test scene based on the original scene file and the target label set.

10. A vehicle comprising an onboard memory having a computer program stored therein and an onboard processor arranged to run the computer program to perform the scene library construction method of a vehicle simulation test according to any one of claims 1 to 8.

Images