WO2022037085A1 - 车辆的仿真测试场景的构建方法和装置 - Google Patents

车辆的仿真测试场景的构建方法和装置 Download PDF

Info

Publication number
WO2022037085A1
WO2022037085A1 PCT/CN2021/085990 CN2021085990W WO2022037085A1 WO 2022037085 A1 WO2022037085 A1 WO 2022037085A1 CN 2021085990 W CN2021085990 W CN 2021085990W WO 2022037085 A1 WO2022037085 A1 WO 2022037085A1
Authority
WO
WIPO (PCT)
Prior art keywords
entity
entities
ontology model
association
tested
Prior art date
Application number
PCT/CN2021/085990
Other languages
English (en)
French (fr)
Inventor
张晓毓
覃力
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to EP21857186.7A priority Critical patent/EP4191221A4/en
Publication of WO2022037085A1 publication Critical patent/WO2022037085A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/36—Preventing errors by testing or debugging software
    • G06F11/3668—Software testing
    • G06F11/3672—Test management
    • G06F11/3684—Test management for test design, e.g. generating new test cases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/36—Preventing errors by testing or debugging software
    • G06F11/3668—Software testing
    • G06F11/3696—Methods or tools to render software testable

Definitions

  • the present application relates to the field of autonomous driving, and more particularly, to a method and apparatus for constructing a simulation test scenario for a vehicle.
  • simulation test In the case of road testing, the proportion of driver errors increases with the accumulation of test distance, and many extreme dangerous scenarios are not suitable for human operation. Therefore, compared with a series of limitations such as high test cost, long test period, and many test accidents of road test, simulation test is better than road test to a certain extent.
  • the construction cost of the simulation scene library is low, and it is not restricted by conditions such as weather and region, effectively avoiding personal and property injuries. And pay more attention to the human-vehicle-environment interaction.
  • the simulation test combines the real hardware system with the simulation environment to form a test tool chain, giving full play to the advantages of the simulation environment, such as infinity, scalability, batchization, and automation, to achieve rapid deployment and automated testing of simulation test scenarios.
  • the prior art proposes a method for constructing a simulation test scene based on an ontology model.
  • various entities are provided in the ontology model to represent the traffic elements in the road traffic scene, for example, the obstacle entity that describes the obstacles that the vehicle may encounter during the driving process, the road network that describes the road the vehicle travels on Entities, etc., and road network entities can be divided into regional entities and point entities, where regional entities include lane entities, lane line entities, pedestrian crossing entities, etc., and point entities can include traffic light entities, traffic sign entities, stop line entities, etc. .
  • the tester needs to select the appropriate entity from the thousands of entities provided by the ontology model based on the road traffic scene corresponding to the task to be tested, so as to construct a simulation test scene in the ontology model.
  • the present application provides a method and device for constructing a simulation test scene of a vehicle, so as to improve the accuracy of creating a simulation test scene in an ontology model.
  • a method for constructing a simulation test scene of a vehicle including: acquiring a task to be tested, where the task to be tested is used for instructing to test the function of a target vehicle, and/or to test the driving force of the target vehicle. based on the task to be tested, select a first entity in a preset ontology model, and the ontology model includes multiple entities for describing traffic elements; based on the first entity and preset the entity association relationship, select one or more second entities associated with the first entity from the ontology model, and the entity association relationship represents the relationship between entities in the ontology model; based on the The first entity and the one or more second entities construct a simulated test scenario for testing the task to be tested.
  • one or more entities associated with the first entity are automatically selected from the ontology model based on the entity association relationship preset in the ontology model
  • the second entity constructs a simulation test scenario based on the selected first entity and one or more second entities, which avoids the missed entity selection that occurs in the process of manually selecting entities to construct a simulation test scenario based on testers in the prior art
  • the selecting one or more second entities associated with the first entity from the ontology model based on the first entity and a preset entity association relationship includes: Based on the first entity, the entity association relationship, and a preset entity association degree, the one or more second entities are selected from the ontology model, and the entity association degree represents an entity in the ontology model The degree of association with an entity, wherein the degree of association between each of the one or more second entities and the first entity is higher than that of other entities in the ontology model and the first entity the degree of association, the other entities are entities other than the second entity in the ontology model.
  • one or more second entities are selected from the ontology model based on the preset entity association degree, which is beneficial to limit the number of selected second entities, so as to reduce the occupation of the simulation test of the task to be tested. calculation amount.
  • the method further includes: obtaining an association degree threshold based on the task to be tested, where the association degree threshold is an association degree threshold used to select the one or more second entities from the ontology model; selecting the one or more second entities from the ontology model, including: based on the first entity, the entity association relationship, and the entity association degree, selecting the one or more second entities from the ontology model, and the association degree between the first entity and the one or more second entities above the association degree threshold.
  • the association degree threshold is an association degree threshold used to select the one or more second entities from the ontology model
  • selecting the one or more second entities from the ontology model including: based on the first entity, the entity association relationship, and the entity association degree, selecting the one or more second entities from the ontology model, and the association degree between the first entity and the one or more second entities above the association degree threshold.
  • selecting one or more second entities from the ontology model based on the association degree threshold is beneficial to improve the rationality of selecting the second entities.
  • the constructing, based on the first entity and the one or more second entities, a simulation test scenario for testing the task to be tested includes: based on the first entity properties of the second entity, properties of the second entity, and relationships between the first entity and the second entity, a first instance of the first entity and the one or more second entities are created in the ontology model one or more second instances of an entity; building the simulated test scenario in the ontology model based on the first instance and the one or more second instances.
  • the simulation test scene is constructed in the ontology model based on the first instance and the second instance, which is beneficial to improve the accuracy of constructing the simulation test scene.
  • the method further includes: acquiring attributes of the first entity, properties of the second entity properties and relationships between the first entity and the second entity.
  • the first instance and the second instance are created, which is beneficial to improve the creation of the first instance and the second instance. Rationality of the second instance.
  • the selecting a first entity in a preset ontology model based on the task to be tested includes: acquiring information for describing the content of the task to be tested, the information includes A first traffic element; according to the first traffic element, the first entity is selected from the preset ontology model, and the first entity is used to describe the first traffic element.
  • selecting the first entity based on the information used to describe the content of the task to be tested is beneficial to improve the automated process of selecting the first entity.
  • a method for constructing a simulation test scene for a vehicle including: selecting a first entity from a preset ontology model based on a task to be tested, where the task to be tested is used to indicate a function to be tested for a target vehicle Carry out a test, and/or test the driving scene to be tested in which the target vehicle is driven, the ontology model includes a plurality of entities for describing traffic elements; based on the first entity and the preset entity association relationship, from One or more second entities associated with the first entity are selected in the ontology model, and the entity association relationship represents the relationship between entities in the ontology model; based on the first entity and the One or more second entities update the first simulation test scene constructed in the ontology model to obtain the second simulation test scene in the ontology model, the first simulation test scene and the second simulation test scene
  • the simulation test scenario is a simulation test scenario for testing the to-be-tested task.
  • one or more second entities are selected from the ontology model to update the first simulation test scene to obtain the second simulation test scene, which is conducive to improving the construction of The second simulation tests the accuracy of the scenario.
  • the method of the embodiment of the present application is combined with the construction method according to the traditional simulation scene, that is, the first simulation test scene obtained according to the traditional simulation scene construction method is updated to obtain the second simulation test scene. It is beneficial to improve the compatibility of the method for constructing the simulation scene in the embodiment of the present application.
  • the selecting one or more second entities associated with the first entity from the ontology model based on the first entity and a preset entity association relationship includes: One or more second entities associated with the first entity are selected based on the first entity and the entity association relationship and the entity association degree, where the entity association degree is used to indicate the relationship between the entity and the entity in the ontology model.
  • the degree of association, and the degree of association between each of the one or more second entities and the first entity is higher than the degree of association between other entities and the first entity, and the other entities are the multiple entities. entities other than the second entity among the entities.
  • one or more second entities are selected from the ontology model based on the preset entity association degree, which is beneficial to limit the number of selected second entities, so as to reduce the occupation of the simulation test of the task to be tested. calculation amount.
  • the first simulation test scene constructed in the ontology model is updated based on the first entity and the one or more second entities to obtain a second simulation test
  • the scenario includes: matching the entity to which the instance in the first simulation test scenario belongs with the first entity and the one or more second entities, and determining entities not included in the first simulation test scenario ; Create an instance corresponding to the entity that is not included in the ontology model; add the instance corresponding to the entity that is not included to the first simulation test scene to obtain the second simulation test scene.
  • the first entity and one or more second entities are compared with the entities in the first simulation test scene to obtain entities not included in the first simulation test scene, and the entities not included in the first simulation test scene are obtained. Adding to the first simulation test scene to obtain the second simulation test scene is beneficial to improve the accuracy of constructing the second simulation test scene.
  • the first simulation test scene constructed in the ontology model is updated based on the first entity and the one or more second entities to obtain a second simulation test
  • the scenario includes: matching the entities in the first simulation test scenario with the first entity and the one or more second entities, and determining that the first entity in the first simulation test scenario is excluding the first entity and Redundant entities other than the one or more second entities; the instances corresponding to the redundant entities are deleted from the first simulation test scenario to obtain the second simulation test scenario.
  • the first entity and one or more second entities are compared with the entities in the first simulation test scene to obtain redundant entities included in the first simulation test scene, and the redundant entities are removed from the first simulation test scene. Deleting a simulation test scene to obtain a second simulation test scene is beneficial to improve the accuracy of constructing the second simulation test scene.
  • an apparatus for constructing a simulated test scene of a vehicle including each unit used in the methods in the above aspects.
  • an apparatus for constructing a simulation test scene of a vehicle has the function of implementing the apparatus in the method design of the above aspect.
  • These functions can be implemented by hardware or by executing corresponding software by hardware.
  • the hardware or software includes one or more units corresponding to the above functions.
  • a computing device including an input-output interface, a processor, and a memory.
  • the processor is used to control the input and output interface to send and receive signals or information
  • the memory is used to store a computer program
  • the processor is used to call and run the computer program from the memory, so that the computing device executes the method in the above aspect.
  • a computer program product comprising: computer program code, which, when the computer program code is run on a computer, causes the computer to perform the methods in the above aspects.
  • the above computer program code may be stored in whole or in part on the first storage medium, where the first storage medium may be packaged with the processor or separately packaged with the processor, which is not implemented in this embodiment of the present application. Specific restrictions.
  • a computer-readable medium stores program codes, which, when executed on a computer, cause the computer to perform the methods in the above-mentioned aspects.
  • a chip system in an eighth aspect, includes a processor for a computing device to implement the functions involved in the above aspects, for example, generating, receiving, sending, or processing the data involved in the above methods and/or or information.
  • the chip system further includes a memory for storing necessary program instructions and data of the computing device.
  • the chip system may be composed of chips, or may include chips and other discrete devices.
  • FIG. 1 is a schematic diagram of a suitable simulation test system according to an embodiment of the present application.
  • FIG. 2 is a schematic diagram of the architecture of an ontology model according to an embodiment of the present application.
  • FIG. 3 is a flowchart of a method for constructing a simulation test scene of a vehicle according to an embodiment of the present application.
  • FIG. 4 is a topology diagram of an entity and an association relationship between entities in an ontology model according to an embodiment of the present application.
  • FIG. 5 is a flowchart of a method for constructing a simulation test scene of a vehicle according to another embodiment of the present application.
  • FIG. 6 is a schematic diagram of an apparatus for constructing a simulation test scene of a vehicle according to an embodiment of the present application.
  • FIG. 7 is a schematic diagram of an apparatus for constructing a simulation test scene of a vehicle according to another embodiment of the present application.
  • FIG. 8 is a schematic block diagram of a computing device according to another embodiment of the present application.
  • Ontology model can be understood as a model that abstracts reality according to the concepts in real life, the relationship between concepts, the characteristics (ie attributes) of concepts and the instances of concepts.
  • the ontology model can be understood as describing the traffic elements (ie entities) in the road traffic scene through the ontology model, the classes (ie concepts) to which the traffic elements belong, the relationship between the traffic elements, and the characteristics (attributes) of the traffic elements. Wait.
  • Entities The entities in the ontology model are used to describe the static traffic elements and dynamic traffic elements in the real road traffic scene, and are the basic elements for constructing the simulation test scene. For example, lane entities, lane line entities, pedestrian crossing entities, traffic sign entities, static obstacle entities, dynamic obstacle entities, etc. in the ontology model.
  • the ontology model usually includes self-vehicle class, road network class, obstacle class, behavior class, driving environment class, etc.
  • the self-vehicle class above is used to describe the self-vehicle itself.
  • the road network class is used to describe the connection relationship between roads and can be divided into regional entities and point entities, where regional entities can include lane entities, lane line entities, crosswalk entities, intersection entities, road segment entities, etc.; point entities can include Traffic light entity, traffic sign entity, stop line entity, speed limit sign entity, etc.
  • the obstacle class is used to describe the obstacle entities encountered by the vehicle during driving. Obstacles can be divided into static obstacles and dynamic obstacles. Among them, the static obstacle class can include a variety of static obstacle entities, such as construction signage entities, water horse enclosure entities, etc.; the dynamic obstacle class can include a variety of dynamic obstacle entities, such as pedestrian entities, motor vehicle entities, etc. Vehicle entities, non-motor vehicle entities, etc.
  • the behavior class can be regarded as a collection that describes the self-driving action, for example, it can include acceleration entities, deceleration entities, uniform speed entities, parking entities, lane changing entities to the left, lane changing entities to the right, overtaking entities, merging entities, etc.
  • the driving environment class can be regarded as a collection that describes the driving environment, for example, it can include weather entities, temperature entities, humidity entities, lighting condition entities, and so on.
  • Relationship which is used to describe the relationship between entities and is the basis for determining whether to select the entity as a test variable (entity) in the construction of a simulation test scenario.
  • entity a test variable
  • the relationship between the self-vehicle entity and the road 1 entity may be that the self-vehicle entity drives on road 1; for another example, the relationship between the road segment entity and the intersection entity may be that the road segment entity is connected to the intersection entity.
  • Attribute which refers to the specific state or parameter value of an entity or relationship.
  • the entity After an entity is selected as a test variable in the ontology model, the entity usually has multiple optional states or settable parameter options, and these optional states or settable parameter options are attributes.
  • the properties of the ego vehicle entity include the speed attribute of the ego car.
  • the attributes of the motor vehicle entity include the type of the motor vehicle, the speed of the motor vehicle, the coordinates of the motor vehicle, and the like.
  • the attribute of the acceleration entity in the behavior class is a specific acceleration value.
  • the state attributes of the relationship between different obstacle entities include front, left, left, rear left, rear, rear right, right, front right, etc.
  • the state attributes of the weather entity include sunny, Rain, snow, etc.
  • the simulation test system 100 shown in FIG. 1 includes an input unit 110 , an execution unit 120 , and a storage unit 130 .
  • the input unit 110 is used to obtain the task to be tested.
  • the input unit 110 may be a user interface for acquiring information from a user of the simulation test system.
  • the input unit 110 may include one or more input/output devices, such as a keyboard, a microphone, and the like.
  • the execution unit 120 is configured to run the simulation test software and present an ontology model, so as to construct a simulation test scene for testing the above-mentioned task to be tested in the ontology model.
  • the above-mentioned execution unit 120 may be a processor, and specifically, may be any conventional processor, including a reduced instruction set computing (reduced instruction set computing, RISC) processor, a complex instruction set computing processor, or a combination thereof.
  • the processor may be a dedicated device such as an application specific integrated circuit (ASIC).
  • ASIC application specific integrated circuit
  • the storage unit 130 is used to store the running program of the simulation test software, or the data generated during the use of the simulation test software, the simulation running result, and the like.
  • the storage unit 130 may be a memory, and the memory may be packaged in a chip with the above-mentioned processor, or may be packaged in a different chip with the above-mentioned processor, which is not limited in this embodiment of the present application.
  • the following describes the ontology model of the embodiment of the present application based on the simulation system shown in FIG. 1 and in conjunction with FIG. 2 . It should be noted that the ontology model of the embodiment of the present application may also be other architectures, which are not limited in the embodiment of the present application.
  • the ontology model 200 shown in FIG. 2 includes a self-vehicle class 220 , a road network class 220 , an obstacle class 230 , a behavior class 240 and a driving environment class 250 .
  • the self-vehicle class 220 includes the self-vehicle entity. After the corresponding speed and coordinates are set for the self-vehicle entity, the self-vehicle instance is generated.
  • Behavior classes 240 include accelerating entities, stopping entities, lane changing entities, and overtaking entities.
  • the driving behavior of the self-vehicle can be described by setting parameters for the entities in the behavior class 240 to generate instances corresponding to the entities.
  • the obstacle class 230 includes static obstacle entities and dynamic obstacle entities, wherein the dynamic obstacle entities include: motor vehicle entities, non-motor vehicle entities, and pedestrian entities.
  • a motor vehicle instance can be generated by setting the speed, coordinates, and class of the motor vehicle entity.
  • a non-motor vehicle instance can be generated by setting the speed, coordinates, and class of the non-motor vehicle entity.
  • you can also set the relationship between the obstacle and the self-vehicle for example, set the self-vehicle entity to be located in the front, rear, left front, left rear of the entity in the obstacle class , one of right rear and right front.
  • the road network class 230 includes lane entities, lane line entities, crosswalk entities, stop line entities, road segment entities, intersection entities, traffic light entities, and traffic sign entities.
  • Lane instances can be generated by setting the friction coefficient of the lane entity.
  • An intersection instance can be created by setting the intersection entity to one of intersection, U-junction, and T-junction.
  • the link entity is set to be connected to the intersection entity.
  • set the traffic light entity to be located at the intersection entity.
  • it is set that the traffic sign entity is located at the intersection entity and the road segment entity.
  • set the crosswalk entity to be located at the intersection entity.
  • the relationship between the entities in the obstacle class and the entities in the road network class can also be set.
  • the entities of motor vehicles, non-motor vehicles, static obstacles can be set
  • the object entity is located on the lane entity.
  • the driving environment class 250 includes a weather entity, a temperature entity, and a lighting condition entity. You can get weather instances, temperature instances, and lighting condition instances by setting the specific parameters of the weather entity, temperature entity, and lighting condition entity.
  • the prior art proposes a method for constructing a simulation test scene based on an ontology model.
  • various entities are provided in the ontology model to represent the traffic elements in the road traffic scene, for example, the obstacle entity that describes the obstacles that the vehicle may encounter during the driving process, the road network entity that describes the road the vehicle travels on
  • the road network entities can be divided into regional entities and point entities.
  • the regional entities include lane entities, lane line entities, pedestrian crossing entities, etc.
  • point entities can include traffic light entities, traffic sign entities, and stop line entities.
  • the tester needs to select the appropriate entity from the thousands of entities provided by the ontology model based on the road traffic scene corresponding to the task to be tested, so as to construct a simulation test scene of the road traffic scene in the ontology model.
  • testers usually select entities based on experience. Different testers may choose different entities, and there may be missing entities or multiple-selected entities. In this case, the constructed simulation test scenario is not accurate, which affects the simulation test results of the vehicle.
  • the present application provides a new method for constructing a simulation test scenario, that is, after selecting the first entity from the ontology model based on the task to be tested, based on the entity association relationship in the ontology model, automatically select the first entity from multiple entities
  • One or more second entities associated with the first entity are selected, and a simulation test scenario is constructed based on the selected first entity and the one or more second entities, avoiding the need for manual selection of entities by testers to construct a simulation in the prior art
  • the situation of missing entities or multiple entities being selected is beneficial to improve the accuracy of constructing the simulation test scenario.
  • the following describes a flowchart of a method for constructing a simulation test scene for a vehicle according to an embodiment of the present application with reference to FIG. 3 . It should be understood that the method shown in FIG. 3 may be executed by the simulation test system shown in FIG. 1 , or by other simulation test devices, or by a computing device with a computing function, which is not specifically limited in this embodiment of the present application.
  • the method shown in FIG. 3 includes steps 310 to 340 .
  • the above-mentioned function to be tested of the target vehicle may include testing a specific function of the target vehicle.
  • the function to be tested of the target vehicle may be the target recognition function of the target vehicle.
  • the function to be tested of the target vehicle may also be a function of changing lanes.
  • the function to be tested of the target vehicle may also be a lane keeping function.
  • the to-be-tested functions of the above target vehicle can be used in different scenarios. For example, test the target recognition function of the target vehicle at night. For example, the target recognition function of the target vehicle is tested in rainy days, and the target recognition function of the target vehicle is tested in an urban road scene.
  • the driving scene to be tested in which the target vehicle is driven mainly includes testing the comprehensive ability of the target vehicle in a certain scene.
  • multiple functions of the target vehicle are required to cooperate with each other to complete the driving task of the vehicle.
  • the vehicle needs to pass through the intersection safely, so it is necessary to test the traffic light recognition function, obstacle avoidance function, and vehicle steering function of the target vehicle. That is to say, by testing the target driving scene to be tested, the driving ability of the target vehicle in a specific scene can be obtained.
  • the foregoing first entity may be one or more, which is not specifically limited in this embodiment of the present application.
  • the above-mentioned selecting the first entity based on the task to be tested may include acquiring information for describing the content of the task to be tested, the information includes a first traffic element; according to the first traffic element, from the The first entity is selected from the preset ontology model, and the first entity is used to describe the first traffic element.
  • the tester can input “follow the vehicle ahead” to describe the content of the task to be tested, where the first traffic element can be “vehicle”, then select the entity “vehicle” corresponding to the first traffic element "vehicle” from the ontology model entity” as the first entity.
  • the tester can input "lane line centering driving function" to describe the content of the task to be tested, wherein the first traffic element can be "lane line”, then select the first traffic element "lane line” from the ontology model corresponding to The first entity "lane line entity”.
  • the tester can input "crossroad driving” to describe the content of the task to be tested, wherein the first traffic element can be "junction”, then select the first entity corresponding to the first traffic element "junction” from the ontology model "Intersection Entity".
  • the tester can also directly designate the first entity based on the task to be tested.
  • This embodiment of the present application does not limit the specific manner of acquiring the first entity.
  • description information of the above task to be tested may be manually input by the tester, or may be preset in the simulation test software and then selected by the tester. This embodiment of the present application does not specifically limit this.
  • the scheme of extracting keywords from the description of the above task to be tested can be directly identified from the description of the task to be tested by algorithms such as Natural Language Processing (NLP).
  • NLP Natural Language Processing
  • a corresponding label can be pre-selected for subsequent identification.
  • This embodiment of the present application does not limit the specific method for extracting keywords based on the description of the task to be tested.
  • the foregoing selecting one or more second entities associated with the first entity from the ontology model may include selecting all entities associated with the first entity from the ontology model as the foregoing second entities.
  • this selection method usually results in a large number of selected second entities, which increases the calculation amount and cycle of the simulation test. Therefore, in this embodiment of the present application, the degree of association between entities can also be based on Degree of Entity Association ("%), select the second entity from the ontology model.
  • the above step 330 includes: selecting one or more second entities from the ontology model based on the first entity, the entity association relationship, and the preset entity association degree, and the entity association degree represents the relationship between the entity and the entity in the ontology model.
  • the degree of association between the two entities, and the degree of association between each of the one or more second entities and the first entity is higher than the degree of association between other entities in the multiple entities and the first entity, and the other entities are excluded from the ontology model. an entity other than the second entity.
  • the number of the second entities to be selected may be limited by setting the number of the second entities to be selected, or by setting a threshold of the degree of association.
  • the number of the second entities to be selected can be set to 5, then based on the association relationship between entities and entities and the degree of association between entities, 5 entities associated with the first entity are selected from multiple entities
  • the degree of association between the five second entities and the first entity is higher than the degree of association between other entities among the multiple entities and the first entity.
  • the above method when selecting a second entity by setting an association degree threshold, includes: obtaining an association degree threshold based on the task to be tested, wherein the association degree threshold is an association degree used to select one or more second entities from the ontology model
  • the above step 330 includes: creating one or more second entities in the ontology model based on the first entity, the entity association relationship, and the entity association degree, and the association degree between the first entity and the one or more second entities above the correlation threshold.
  • each task to be tested has its corresponding association degree threshold, and the association degree threshold may be designated by the tester or preset, which is not limited in this embodiment of the present application.
  • the above entity association degree can be represented by a specific association degree value, and can also be represented by a distance N between entities in a topology diagram representing an association relationship between entities.
  • distance refers to the minimum number of lines that must be traversed between jumping from one entity to another in the topology graph. For example, in a topology graph two entities are directly connected, the distance is 1. For another example, if two entities are separated by one entity, the distance between the entities is 2.
  • the value of the distance N between entities is derived from the testing requirements. For example, if you just want to test whether a certain function of the target vehicle is feasible or whether there are obvious loopholes, the value of N can be 1.
  • the larger the value of the distance N between the entities the more comprehensively the task to be tested can be tested. That is, as the value of N increases, the number of entities in the simulation test scene becomes more and more abundant.
  • N>5 the selected second entity has nothing to do with the type of the task to be tested.
  • the following describes the process of selecting the second entity by taking the entity and the association relationship between the entities in the ontology model shown in FIG. 4 as an example.
  • FIG. 4 is a topology diagram of an entity and an association relationship between entities in an ontology model according to an embodiment of the present application. Assuming that the task to be tested is "following the vehicle", the traffic elements can be extracted from the description of the task to be tested as “self-vehicle” and "motor vehicle”. Based on this, the self-vehicle entity 410 and the motor vehicle entity 420 can be selected from the ontology model as the first entity, and an entity with a distance of 1 from the first entity needs to be selected as the second entity. Based on the topology diagram shown in FIG.
  • the second entity with a distance of 1 from the self-vehicle entity 410 includes: the driving environment entity, the motor vehicle entity and the lane entity 1; the second entity with a distance of 1 from the motor vehicle entity 420 includes: the behavior entity 5, the obstacle entity 1 .
  • the above step 340 includes: based on the attributes of the first entity, the attributes of the second entity and the relationship between the first entity and the second entity, creating a first instance of the first entity and one or more entities in the ontology model.
  • One or more second instances of the second entity based on the first instance and the one or more second instances, a simulation test scenario is constructed in the ontology model.
  • the attributes of the first entity, the attributes of the second entity, and the relationship between the first entity and the second entity can be set by the tester based on the task to be tested, or can be directly used in the simulation software.
  • the default value is not limited in this embodiment of the present application.
  • the method for constructing a simulation test scenario according to an embodiment of the present application is described above with reference to FIG. 1 to FIG. 4 .
  • the solutions described above can be used to build new simulated test scenarios.
  • some current simulation test software can directly provide the constructed simulation test scene. Therefore, in order to avoid rebuilding the simulation test scene, the method of the present application can also be used to update the constructed simulation test scene. 4 Introduction is introduced. It should be noted that the terms involved in the method shown in FIG. 4 have the same meanings as those referred to above, and the acquisition method can also be acquired by referring to the method described above. For brevity, details are not repeated below.
  • FIG. 5 is a flowchart of a method for constructing a simulation test scenario according to another embodiment of the present application. It should be understood that the method shown in FIG. 5 can be executed by the simulation test system shown in FIG. 1 , or by other simulation test devices, or by a computing device with a computing function, which is not specifically limited in this embodiment of the present application.
  • the method shown in FIG. 5 includes steps 510 to 530 .
  • the task to be tested Based on the task to be tested, select a first entity from a preset ontology model, and the task to be tested is used to instruct to test the function to be tested of the target vehicle, and/or to test the driving scene to be tested in which the target vehicle is driven , where the ontology model contains multiple entities for traffic elements.
  • the manner of selecting the second entity in step 520 is similar to the manner of selecting the second entity in step 330.
  • the test scenario is a simulated test scenario for testing the task to be tested.
  • the above constructed first simulation test scenario may be constructed based on existing simulation test software.
  • the constructed first simulation test scene may also be constructed based on the entity selected by the tester in the ontology model, and the embodiment of the present application does not limit the construction method of the above-mentioned first simulation test scene.
  • the above step 530 includes: matching the entity to which the instance in the first simulation test scene belongs with the first entity and one or more second entities to determine entities not included in the first simulation test scene; Instances corresponding to entities not included in the model are created; and instances corresponding to entities not included are added to the first simulation test scene to obtain a second simulation test scene.
  • the above creation of an instance corresponding to an entity that is not included in the ontology model can include selecting an entity that is not included in the ontology model, and then creating the entity corresponding to the entity by setting the attributes of the entity that is not included and/or the relationship between the entity and other entities. instance.
  • the above step 530 includes: matching the entities in the first simulation test scenario with the first entity and one or more second entities, and determining that the first entity and one or more second entities in the first simulation test scenario are excluded.
  • the redundant entities other than the two entities; the instances corresponding to the redundant entities are deleted from the first simulation test scene to obtain the second simulation test scene.
  • FIGS. 6 to 8 The methods of the embodiments of the present application are described above with reference to FIGS. 2 to 5 , and the apparatuses of the embodiments of the present application are described below with reference to FIGS. 6 to 8 . It should be understood that it should be noted that the apparatuses shown in FIG. 6 to FIG. 8 can implement each step in the above method, which is not repeated here for brevity.
  • FIG. 6 is a schematic diagram of an apparatus for constructing a simulation test scene of a vehicle according to an embodiment of the present application.
  • the apparatus 600 shown in FIG. 6 includes: an acquisition unit 610 and a processing unit 620 .
  • an acquisition unit 610 configured to acquire a task to be tested, where the task to be tested is used for instructing to test the function of the target vehicle, and/or to test the driving scene in which the target vehicle is driven;
  • a processing unit 620 configured to select a first entity in a preset ontology model based on the task to be tested, where the ontology model includes multiple entities for describing traffic elements;
  • the processing unit 620 is further configured to select one or more second entities associated with the first entity from the ontology model based on the first entity and a preset entity association relationship, and the entities are associated with The relationship represents the relationship between entities in the ontology model;
  • the processing unit 620 is further configured to construct a simulation test scenario for testing the task to be tested based on the first entity and the one or more second entities.
  • the processing unit 620 is further configured to: select the one from the ontology model based on the first entity, the entity association relationship, and a preset entity association degree or multiple second entities, the entity association degree represents the association degree between entities in the ontology model, wherein each second entity in the one or more second entities is associated with the first entity
  • the degree of association is higher than the degree of association between other entities in the ontology model and the first entity, and the other entities are entities other than the second entity in the ontology model.
  • the processing unit 620 is further configured to: obtain an association degree threshold based on the task to be tested, where the association degree threshold is to select the one or more first steps from the ontology model.
  • the processing unit 620 is further configured to: based on the attribute of the first entity, the attribute of the second entity, and the relationship between the first entity and the second entity relationship, creating a first instance of a first entity and one or more second instances of the one or more second entities in the road traffic ontology; based on the first instance and the one or more first instances In the second instance, the simulation test scene is constructed in the ontology model.
  • the processing unit 620 is further configured to: acquire the attribute of the first entity, the attribute of the second entity, and the relationship between the first entity and the second entity relation.
  • the processing unit 620 is further configured to: obtain information for describing the content of the task to be tested, the information includes a first traffic element; according to the first traffic element, The first entity is selected from the preset ontology model, and the first entity is used to describe the first traffic element.
  • FIG. 7 is a schematic diagram of an apparatus for constructing a simulation test scene of a vehicle according to another embodiment of the present application.
  • the apparatus 700 shown in FIG. 7 includes: an acquisition unit 710 and a processing unit 720 .
  • an acquisition unit 710 configured to acquire a task to be tested, where the task to be tested is used for instructing to test the function to be tested of the target vehicle, and/or to test the driving scene to be tested in which the target vehicle is driven;
  • the processing unit 720 is configured to select a first entity from a preset ontology model based on the task to be tested, where the ontology model includes multiple entities for describing traffic elements; based on the first entity and the preset entity an association relationship, one or more second entities associated with the first entity are selected from the ontology model, and the entity association relationship represents the relationship between entities in the ontology model; based on the first entity The entity and the one or more second entities update the first simulation test scene constructed in the ontology model to obtain the second simulation test scene in the ontology model, the first simulation test scene and The second simulation test scenario is a simulation test scenario for testing the to-be-tested task.
  • the processing unit 720 is further configured to: select one or more second entities associated with the first entity based on the association relationship between the first entity and the entity, and the entity association degree Entity, the entity association degree is used to indicate the association degree between entities in the ontology model, and each second entity in the one or more second entities has a higher association degree with the first entity than other entities
  • the degree of association between an entity and the first entity, and the other entities are entities other than the second entity among the multiple entities.
  • the processing unit 720 is further configured to: perform a test between the entity to which the instance in the first simulation test scenario belongs to the first entity and the one or more second entities. Matching, determine the entities not included in the first simulation test scene; create an instance corresponding to the not included entity in the ontology model; add the instance corresponding to the not included entity to the first simulation A test scenario is obtained to obtain the second simulated test scenario.
  • the processing unit 720 is further configured to: match the entities in the first simulation test scenario with the first entity and the one or more second entities, and determine redundant entities other than the first entity and the one or more second entities in the first simulation test scenario; delete the instances corresponding to the redundant entities from the first simulation test scenario to obtain the second simulation test scenario.
  • the processing unit 620 may be a processor 820, the obtaining unit 610 may be a communication interface 830, and the computing device may further include a memory 810, as shown in FIG. 8 .
  • the processing unit 720 may be a processor 820
  • the obtaining unit 710 may be a communication interface 830
  • the computing device may further include a memory 810, as shown in FIG. 8 .
  • FIG. 8 is a schematic block diagram of a computing device according to another embodiment of the present application.
  • the computing device 800 shown in FIG. 8 may include a memory 810 , a processor 820 , and a communication interface 830 .
  • the memory 810, the processor 820, and the communication interface 830 are connected through an internal connection path, the memory 810 is used to store instructions, and the processor 820 is used to execute the instructions stored in the memory 820 to control the input/output interface 830 to receive/send At least part of the parameters of the second channel model.
  • the memory 810 can either be coupled with the processor 820 through an interface, or can be integrated with the processor 820 .
  • the above-mentioned communication interface 830 uses a transceiver such as but not limited to a transceiver to implement communication between the communication device 800 and other devices or communication networks.
  • the above-mentioned communication interface 830 may also include an input/output interface.
  • each step of the above-mentioned method may be completed by an integrated logic circuit of hardware in the processor 820 or an instruction in the form of software.
  • the methods disclosed in conjunction with the embodiments of the present application may be directly embodied as executed by a hardware processor, or executed by a combination of hardware and software modules in the processor.
  • the software modules may be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers and other storage media mature in the art.
  • the storage medium is located in the memory 810, and the processor 820 reads the information in the memory 810, and completes the steps of the above method in combination with its hardware. To avoid repetition, detailed description is omitted here.
  • the processor may be a central processing unit (central processing unit, CPU), and the processor may also be other general-purpose processors, digital signal processors (digital signal processors, DSP), dedicated integrated Circuit (application specific integrated circuit, ASIC), off-the-shelf programmable gate array (field programmable gate array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
  • a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
  • the memory may include a read-only memory and a random access memory, and provide instructions and data to the processor.
  • a portion of the processor may also include non-volatile random access memory.
  • the processor may also store device type information.
  • the size of the sequence numbers of the above-mentioned processes does not mean the sequence of execution, and the execution sequence of each process should be determined by its functions and internal logic, and should not be dealt with in the embodiments of the present application. implementation constitutes any limitation.
  • the disclosed system, apparatus and method may be implemented in other manners.
  • the apparatus embodiments described above are only illustrative.
  • the division of the units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components may be combined or Can be integrated into another system, or some features can be ignored, or not implemented.
  • the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.
  • the functions, if implemented in the form of software functional units and sold or used as independent products, may be stored in a computer-readable storage medium.
  • the technical solution of the present application can be embodied in the form of a software product in essence, or the part that contributes to the prior art or the part of the technical solution.
  • the computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk and other media that can store program codes .

Abstract

一种车辆的仿真测试场景的构建方法和装置，可以为智能汽车、自动驾驶汽车、网联汽车提供仿真测试场景。上述方法包括：基于待测试任务从本体模型中选择第一实体之后，基于本体模型中预设的实体关联关系，自动的从本体模型中选择与第一实体关联的一个或多个第二实体，并基于选择的第一实体和一个或多个第二实体构建仿真测试场景，避免了现有技术中基于测试人员手动选择实体以构建仿真测试场景的过程中，发生的漏选实体或多选实体的情况，有利于提高构建仿真测试场景的准确性。

Description

车辆的仿真测试场景的构建方法和装置
本申请要求于2020年8月21日提交中国专利局、申请号为202010850861.4、发明名称为“车辆的仿真测试场景的构建方法和装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及自动驾驶领域，并且更具体地，涉及车辆的仿真测试场景的构建方法和装置。
背景技术
在道路测试的情况下，驾驶员出错的比例会随着测试距离的积累而增加，并且多种极限危险场景也不适合真人操作。因此，相比于道路测试的测试成本高、测试周期长、测试事故多等一系列的局限性，仿真测试在一定程度上优于道路测试。在仿真测试的情况下，仿真场景库构建成本低，不受天气地域等条件的限制，有效避免人身财产伤害。并且将更多的注意力放在人-车-环境的交互。另外，仿真测试将真实硬件系统与仿真环境结合，形成测试工具链，充分发挥仿真环境的无限性、扩展性、批量化、自动化等优势，实现仿真测试场景的快速部署和自动化测试。
构建车辆的仿真测试场景是目前研究的热点问题之一。目前，现有技术提出一种基于本体模型构建仿真测试场景的方法。这种方法中，本体模型中会提供各种实体以表示道路交通场景中的交通元素，例如，描述车辆行驶过程中可能遇到的障碍物对应的障碍物实体，描述车辆行驶的道路的路网实体等，而路网实体又可以划分为区域实体和点实体，其中区域实体又包含车道实体、车道线实体、人行横道实体等，点实体又可以包含交通灯实体、交通标志实体、停止线实体等。测试人员需要基于待测试任务所对应的道路交通场景，从本体模型提供的成千上万种实体中，选择合适的实体，以在本体模型中构建仿真测试场景。
然而，由于本体模型中提供的实体的数量较多，测试人员在选择实体的时候，通常是基于先前经验进行选择，不同的测试人员选择的实体可能不同，并且会存在漏选实体或多选实体的情况，导致构建的仿真测试场景并不准确，影响车辆的仿真测试结果。
发明内容
本申请提供一种车辆的仿真测试场景的构建方法和装置，以提高在本体模型中创建仿真测试场景的准确性。
第一方面，提供了一种车辆的仿真测试场景的构建方法，包括：获取待测试任务，所述待测试任务用于指示对目标车辆的功能进行测试，和/或对所述目标车辆所行驶的驾驶场景进行测试；基于所述待测试任务，在预设的本体模型中选择第一实体，所述本体模型 中包含用于描述交通元素的多个实体；基于所述第一实体和预设的实体关联关系，从所述本体模型中选择与所述第一实体关联的一个或多个第二实体，所述实体关联关系表示所述本体模型中实体与实体之间的关系；基于所述第一实体和所述一个或多个第二实体，构建用于测试所述待测试任务的仿真测试场景。
在本申请实施例中，在基于待测试任务从本体模型中选择第一实体之后，基于本体模型中预设的实体关联关系，自动的从本体模型中选择与第一实体关联的一个或多个第二实体，并基于选择的第一实体和一个或多个第二实体构建仿真测试场景，避免了现有技术中基于测试人员手动选择实体以构建仿真测试场景的过程中，发生的漏选实体或多选实体的情况，有利于提高构建仿真测试场景的准确性。
在一种可能的实现方式中，所述基于所述第一实体和预设的实体关联关系，从所述本体模型中选择与所述第一实体关联的一个或多个第二实体，包括：基于所述第一实体，所述实体关联关系，以及预设的实体关联程度，从所述本体模型中选择所述一个或多个第二实体，所述实体关联程度表示所述本体模型中实体与实体之间的关联程度，其中，所述一个或多个第二实体中每个第二实体与所述第一实体的关联程度，高于所述本体模型中其他实体与所述第一实体的关联程度，所述其他实体为所述本体模型中除所述第二实体之外的实体。
在本申请实施例中，基于预设的实体关联程度，从本体模型中选择一个或多个第二实体，有利于限制选择的第二实体的数量，以降低对待测任务进行仿真测试时所占用的计算量。
在一种可能的实现方式中，在所述基于所述第一实体，所述实体关联关系，以及预设的实体关联程度，从所述本体模型中选择所述一个或多个第二实体之前，所述方法还包括：基于所述待测试任务获取关联程度阈值，所述关联程度阈值为从所述本体模型中选择所述一个或多个第二实体使用的关联程度阈值；所述基于所述第一实体，所述实体关联关系，以及预设的实体与实体之间的关联程度，从所述本体模型中选择所述一个或多个第二实体，包括：基于所述第一实体，所述实体关联关系，以及所述实体关联程度，从所述本体模型中选择所述一个或多个第二实体，所述第一实体与所述一个或多个第二实体之间的关联程度高于所述关联程度阈值。
在本申请实施例中，基于关联程度阈值从本体模型中选择一个或多个第二实体，有利于提高选择第二实体的合理性。
在一种可能的实现方式中，所述基于所述第一实体和所述一个或多个第二实体，构建用于测试所述待测试任务的仿真测试场景，包括：基于所述第一实体的属性、所述第二实体的属性以及所述第一实体和所述第二实体之间的关系，在所述本体模型中创建第一实体的第一实例以及所述一个或多个第二实体的一个或多个第二实例；基于所述第一实例以及所述一个或多个第二实例，在所述本体模型中构建所述仿真测试场景。
在本申请实施例中，基于第一实例和第二实例在本体模型中构建仿真测试场景，有利于提高构建仿真测试场景的准确性。
在一种可能的实现方式中，在所述基于所述第一实体的属性、所述第二实体的属性以及所述第一实体和所述第二实体之间的关系，在所述本体模型中创建第一实体的第一实例以及所述一个或多个第二实体的一个或多个第二实例之前，所述方法还包括：获取所述第 一实体的属性、所述第二实体的属性以及所述第一实体和所述第二实体之间的关系。
在本申请实施例中，通过获取第一实体的属性、第二实体的属性以及第一实体和第二实体之间的关系，创建第一实例和第二实例，有利于提高创建第一实例和第二实例的合理性。
在一种可能的实现方式中，所述基于所述待测试任务，在预设的本体模型中选择第一实体，包括：获取用于描述所述待测试任务的内容的信息，所述信息包含第一交通元素；根据所述第一交通元素，从所述预设的本体模型中选择所述第一实体，所述第一实体用于描述所述第一交通元素。
在本申请实施例中，基于用于描述所述待测试任务的内容的信息，选择第一实体，有利于提高选择第一实体的自动化过程。
第二方面，提供一种车辆的仿真测试场景的构建方法，包括：基于待测试任务，从预设的本体模型中选择第一实体，所述待测试任务用于指示对目标车辆的待测功能进行测试，和/或对目标车辆所行驶的待测驾驶场景进行测试，所述本体模型中包含用于描述交通元素的多个实体；基于所述第一实体和预设的实体关联关系，从所述本体模型中选择与所述第一实体关联的一个或多个第二实体，所述实体关联关系表示所述本体模型中实体与实体之间的关系；基于所述第一实体以及所述一个或多个第二实体，对所述本体模型中已构建的第一仿真测试场景进行更新，得到所述本体模型中的第二仿真测试场景，所述第一仿真测试场景和所述第二仿真测试场景为用于测试所述待测试任务的仿真测试场景。
在本申请实施例中，基于第一实体和实体关联关系，从本体模型中选择一个或多个第二实体，以对第一仿真测试场景进行更新，得到第二仿真测试场景，有利于提高构建第二仿真测试场景的准确性。
另一方面，本申请实施例的方法与按照传统的仿真场景的构建方法相结合，即对按照传统的仿真场景的构建方法得到的第一仿真测试场景进行更新，得到第二仿真测试场景，有利于提高本申请实施例的仿真场景的构建方法的兼容性。
在一种可能的实现方式中，所述基于所述第一实体和预设的实体关联关系，从所述本体模型中选择与所述第一实体关联的一个或多个第二实体，包括：基于所述第一实体和实体关联关系，以及实体关联程度，选择与所述第一实体关联的一个或多个第二实体，所述实体关联程度用于指示本体模型中实体和实体之间的关联程度，且所述一个或多个第二实体中每个第二实体与所述第一实体的关联程度高于其他实体与所述第一实体的关联程度，所述其他实体为所述多个实体中除所述第二实体之外的实体。
在本申请实施例中，基于预设的实体关联程度，从本体模型中选择一个或多个第二实体，有利于限制选择的第二实体的数量，以降低对待测任务进行仿真测试时所占用的计算量。
在一种可能的实现方式中，所述基于所述第一实体以及所述一个或多个第二实体，对所述本体模型中已构建的第一仿真测试场景进行更新，得到第二仿真测试场景，包括：将所述第一仿真测试场景中的实例所属的实体与所述第一实体、所述一个或多个第二实体进行匹配，确定所述第一仿真测试场景中未包含的实体；在所述本体模型中创建所述未包含的实体对应的实例；将所述未包含的实体对应的实例添加至所述第一仿真测试场景，得到所述第二仿真测试场景。
在本申请实施例中，将第一实体以及一个或多个第二实体，与第一仿真测试场景中的实体进行对比，得到第一仿真测试场景中未包含的实体，并将未包含的实体添加至第一仿真测试场景，得到第二仿真测试场景，有利于提高构建第二仿真测试场景的准确性。
在一种可能的实现方式中，所述基于所述第一实体以及所述一个或多个第二实体，对所述本体模型中已构建的第一仿真测试场景进行更新，得到第二仿真测试场景，包括：将所述第一仿真测试场景中的实体与所述第一实体以及所述一个或多个第二实体进行匹配，确定所述第一仿真测试场景中除所述第一实体以及所述一个或多个第二实体之外的多余实体；将所述多余实体对应的实例从所述第一仿真测试场景中删除，得到所述第二仿真测试场景。
在本申请实施例中，将第一实体以及一个或多个第二实体，与第一仿真测试场景中的实体进行对比，得到第一仿真测试场景中包含的多余实体，并将多余实体从第一仿真测试场景中删除，得到第二仿真测试场景，有利于提高构建第二仿真测试场景的准确性。
第三方面，提供了一种车辆的仿真测试场景的构建装置，所述装置包括用于上述各方面中的方法的各个单元。
第四方面，提供了一种车辆的仿真测试场景的构建装置，所述装置具有实现上述方面的方法设计中的装置的功能。这些功能可以通过硬件实现，也可以通过硬件执行相应的软件实现。所述硬件或软件包括一个或多个与上述功能相对应的单元。
第五方面，提供了一种计算设备，包括输入输出接口、处理器和存储器。该处理器用于控制输入输出接口收发信号或信息，该存储器用于存储计算机程序，该处理器用于从存储器中调用并运行该计算机程序，使得该计算设备执行上述方面中的方法。
第六方面，提供了一种计算机程序产品，所述计算机程序产品包括：计算机程序代码，当所述计算机程序代码在计算机上运行时，使得计算机执行上述各方面中的方法。
需要说明的是，上述计算机程序代码可以全部或者部分存储在第一存储介质上，其中第一存储介质可以与处理器封装在一起的，也可以与处理器单独封装，本申请实施例对此不作具体限定。
第七方面，提供了一种计算机可读介质，所述计算机可读介质存储有程序代码，当所述计算机程序代码在计算机上运行时，使得计算机执行上述各方面中的方法。
第八方面，提供了一种芯片系统，该芯片系统包括处理器，用于计算设备实现上述方面中所涉及的功能，例如，生成，接收，发送，或处理上述方法中所涉及的数据和/或信息。在一种可能的设计中，所述芯片系统还包括存储器，所述存储器，用于保存计算设备必要的程序指令和数据。该芯片系统，可以由芯片构成，也可以包括芯片和其他分立器件。
附图说明
图1是本申请实施例的适用的仿真测试系统的示意图。
图2是是本申请实施例的本体模型的架构的示意图。
图3是本申请实施例的车辆的仿真测试场景的构建方法的流程图。
图4是本申请实施例的本体模型中实体和实体之间关联关系的拓扑图。
图5是本申请另一实施例的车辆的仿真测试场景的构建方法的流程图。
图6是本申请实施例的车辆的仿真测试场景的构建装置的示意图。
图7是本申请另一实施例的车辆的仿真测试场景的构建装置的示意图。
图8是本申请另一实施例的计算设备的示意性框图。
具体实施方式
下面将结合附图，对本申请中的技术方案进行描述。为了便于理解，先介绍本申请实施例涉及的术语。
一、本体模型，本体模型可以理解为按照现实生活中的概念、概念间的关系、概念所具有的特征(即属性)以及概念的实例抽象出现实的模型。
二、本体模型，本体模型可以理解为通过本体模型描述道路交通场景中的交通元素(即实体)，交通元素所属的类(即概念)、交通元素之间的关系，交通元素的特征(属性)等。
三、实体，本体模型中的实体用于描述真实道路交通场景中的静态交通元素和动态交通元素，是构建仿真测试场景的基础元素。例如，本体模型中的车道实体、车道线实体、人行横道实体、交通标志实体、静态障碍物实体、动态障碍物实体等。
四、类，可以视为集合(sets)，用于指示本体模型中实体所属的种类。在本体模型中通常包含自车类、道路路网类、障碍物类、行为类、驾驶环境类等。
上述自车类用于描述自车本身。
道路路网类用于描述道路之间的连接关系，可以分为区域实体和点实体，其中，区域实体可以包括车道实体、车道线实体、人行横道实体、路口实体、路段实体等；点实体可以包括交通灯实体、交通标志实体、停止线实体、限速标志实体等。
障碍物类用于描述自车行驶过程中碰到的障碍物实体。障碍物类可以分为静态障碍物类和动态障碍物类。其中，静态障碍物类可以包含多种静态障碍物实体，例如可以包括施工标示牌实体、水马围挡实体等；动态障碍物类可以包含多种动态障碍物实体，例如可以包括行人实体、机动车辆实体、非机动车辆实体等。
行为类可以视为描述自车驾驶动作的集合，例如，可以包括加速实体、减速实体、匀速实体、停车实体、向左变道实体、向右变道实体、超车实体、汇合实体等。
驾驶环境类可以视为描述驾驶环境的集合，例如，可以包括天气实体、温度实体、湿度实体、光照条件实体等。
五、关系，用于描述实体与实体之间的关系，是构建仿真测试场景中确定是否选择该实体作为某一个测试变量(实体)的依据。例如，自车实体与道路1实体之间的关系可以为自车实体行驶在道路1上；又例如，路段实体与路口实体之间的关系可以为路段实体连接于路口实体。
六、属性(特征)，指实体或者关系的具体的状态或者参数取值。在本体模型中选择实体作为测试变量后，该实体通常会有多种可选的状态或可设定的参数选项，这些可选的状态或者可设置的参数选项即为属性。例如，自车实体的属性包括自车的速度属性。又例如，机动车辆实体的属性包括机动车辆的类别、机动车辆的速度、机动车辆的坐标等。又例如，行为类中加速实体的属性为具体的加速度取值。又例如，不同障碍物实体之间的关系的状态属性包括正前方、左前方、左方、左后方、后方、右后方、右方、右前方等，又例如，天气实体的状态属性包括晴天、下雨、下雪等。
七、实例，状态和参数取值的设定确定了仿真测试场景实例的输入空间，不同的输入组合将生成不同的测试用例，即实例。
下文结合图1介绍本申请实施例的适用的仿真测试系统。图1所示的仿真测试系统100包括输入单元110，执行单元120，以及存储单元130。
输入单元110，用于获取待测试任务。
可选地，输入单元110可以是用户接口，用于从仿真测试系统的用户处获取信息。可选地，输入单元110可包括一个或多个输入/输出设备，例如键盘、麦克风等。
执行单元120，用于运行仿真测试软件，呈现本体模型，以便在本体模型中构建用于测试上述待测任务的仿真测试场景。
可选地，上述执行单元120可以是处理器，具体地，可以是任何传统处理器，包括精简指令集计算(reduced instruction set computing，RISC)处理器、复杂指令集计算处理器或上述的组合。可选地，处理器可以是诸如专用集成电路(application specific integrated circuit，ASIC)的专用装置。
存储单元130用于存储仿真测试软件的运行程序，或者仿真测试软件使用过程中生成的数据，仿真运行结果等。
可选地，存储单元130可以是存储器，该存储器可以与上述处理器封装在一个芯片中，也可以和上述处理器分别封装在不同的芯片中，本申请实施例对此不作限定。
下文基于图1所示的仿真系统，结合图2介绍本申请实施例的本体模型，需要说明的是，本申请实施例的本体模型还可以是其他的架构，本申请实施例对此不作限定。
图2所示的本体模型200包括自车类220、道路路网类220、障碍物类230、行为类240以及驾驶环境类250。
其中，自车类220包括自车实体，当为自车实体设置对应的速度和坐标后，即生成了自车实例。
行为类240包括加速实体、停止实体、变道实体以及超车实体。可以通过为行为类240中的实体设置参数，以生成实体对应的实例，描述自车的驾驶行为。
障碍物类230包括静态障碍物实体以及动态障碍物实体，其中动态障碍物实体包括：机动车辆实体、非机动车辆实体以及行人实体。可以通过设置机动车辆实体的速度、坐标以及类别，生成机动车辆实例。可以通过设置非机动车辆实体的速度、坐标以及类别，生成非机动车辆实例。另外，在对障碍物类中实体实例化的过程中，还可以设置障碍物与自车之间的关系，例如，设置自车实体位于障碍物类中实体的前方、后方、左前方、左后方、右后方以及右前方中的一种。
道路路网类230包括车道实体、车道线实体、人行横道实体、停车线实体、路段实体、路口实体、交通灯实体以及交通标志实体。可以通过设置车道实体的摩擦系数生成车道实例。可以通过设置路口实体为十字路口、U型路口以及T型路口中的一种，以创建路口实例。
在对道路路网类中实体实例化的过程中，还可以设置道路路网类中实体之间的关系，例如，设置车道线实体位于车道实体的中。又例如，设置停止线实体位于车道实体中。又例如，设置路段实体与路口实体向连接。又例如，设置交通灯实体位于路口实体。又例如，设置交通标志实体位于路口实体以及路段实体。又例如，设置人行横道实体位于路口实体。
另外，在对障碍物类中实体实例化的过程中，还可以设置障碍物类中实体与道路路网类中实体之间的关系，例如，可以设置机动车辆实体、非机动车辆实体、静态障碍物实体位于车道实体上。又例如，还可以设置行人位于人行横道实体上。
驾驶环境类250包括天气实体、温度实体以及光照条件实体。可以通过设置天气实体、温度实体以及光照条件实体的具体参数，以得到天气实例、温度实例以及光照条件实例。
目前，现有技术提出一种基于本体模型构建仿真测试场景的方法。这种方法中，本体模型中会提供各种实体以表示道路交通场景中的交通元素，例如，描述车辆行驶过程中可能遇到的障碍物的障碍物实体，描述车辆行驶的道路的路网实体等，而路网实体又可以划分为区域实体和点实体，其中区域实体又包含车道实体、车道线实体、人行横道实体等，点实体又可以包含交通灯实体、交通标志实体、停止线实体等。测试人员需要基于待测试任务所对应的道路交通场景，从本体模型提供的成千上万种实体中，选择合适的实体，以在本体模型中构建道路交通场景的仿真测试场景。
然而，由于本体模型中提供的实体的数量较多，测试人员在选择实体的时候，通常是基于经验进行选择，不同的测试人员选择的实体可能不同，并且会存在漏选实体或多选实体的情况，导致构建的仿真测试场景并不准确，影响车辆的仿真测试结果。
为了避免上述问题，本申请提供一种新的仿真测试场景的构建方法，即在基于待测试任务从本体模型中选择第一实体之后，基于本体模型中实体关联关系，自动的从多个实体中选择与第一实体关联的一个或多个第二实体，并基于选择的第一实体和一个或多个第二实体构建仿真测试场景，避免了现有技术中基于测试人员手动选择实体以构建仿真测试场景的过程中，发生的漏选实体或多选实体的情况，有利于提高构建仿真测试场景的准确性。
下文结合图3介绍本申请实施例的车辆的仿真测试场景的构建方法的流程图。应理解，图3所示的方法可以由图1所示的仿真测试系统执行，或者由其他仿真测试设备执行，又或者由具有计算功能的计算设备执行，本申请实施例对此不作具体限定。图3所示的方法包括步骤310至步骤340。
310，获取待测试任务，待测试任务用于指示对目标车辆(即上文中的自车)的待测功能进行测试，和/或对目标车辆所行驶的待测驾驶场景进行测试。
上述目标车辆的待测功能可以包括对目标车辆的特定功能进行测试。例如，目标车辆的待测功能可以是目标车辆的目标识别功能。又例如，目标车辆的待测功能还可以是变道行驶功能。又例如，目标车辆的待测功能还可以是车道保持功能。当然，可以在不同的场景上述目标车辆的待测试功能。例如，在夜晚测试目标车辆的目标识别功能。例如，在雨天测试目标车辆的目标识别功能，在城市道路场景中测试目标车辆的目标识别功能。
上述目标车辆所行驶的待测驾驶场景主要包括对目标车辆在某一场景下的综合能力进行测试。通常，一个驾驶场景下需要目标车辆的多个功能相互配合，以完成车辆的行驶任务。例如，在十字路口场景下车辆需要安全通过十字路口，那么就需要对目标车辆的红绿灯识别功能、障碍物躲避功能、车辆的转向功能等进行测试。也就是说，通过对目标的待测驾驶场景的测试，可以得到目标车辆在某个特定场景下的行驶能力。
320，基于待测试任务，在预设的本体模型中选择第一实体，其中，本体模型中包含用于描述交通元素的多个实体。
上述第一实体可以是一个或多个，本申请实施例对此不作具体限定。
可选地，上述基于待测试任务选择第一实体，可以包括获取用于描述所述待测试任务的内容的信息，所述信息包含第一交通元素；根据所述第一交通元素，从所述预设的本体模型中选择所述第一实体，所述第一实体用于描述所述第一交通元素。
例如，测试人员可以输入“跟随前方车辆行驶”，以描述待测试任务的内容，其中第一交通元素可以是“车辆”，则从本体模型中选择第一交通元素“车辆”对应的实体“车辆实体”作为第一实体。又例如，测试人员可以输入“车道线居中行驶功能”，以描述待测试任务的内容，其中第一交通元素可以是“车道线”，则从本体模型中选择第一交通元素“车道线”对应的第一实体“车道线实体”。又例如，测试人员可以输入“十字路口驾驶”，以描述待测试任务的内容，其中第一交通元素可以是“路口”，则从本体模型中选择第一交通元素“路口”对应的第一实体“路口实体”。
当然，测试人员还可以基于待测试任务直接指定第一实体。本申请实施例对获取第一实体的具体方式不作限定。
需要说明的是，上述待测试任务的描述信息可以是测试人员人工输入的，也可以是仿真测试软件中预先设置后，再由测试人员选取。本申请实施例对此不作具体限定。
另外，从上述待测试任务的描述中提取关键词的方案，可以通过自然语言处理(Natural Language Processing，NLP)等算法从待测试任务的描述中直接识别。或者可以在待测试任务的描述涉及功能或者驾驶场景的关键因素时预选打上对应的标签，以便后续识别。本申请实施例对上述基于待测试任务的描述提取关键词的具体方法不作限定。
330，基于第一实体和预设的实体关联关系，从本体模型中选择与第一实体关联的一个或多个第二实体，其中，实体关联关系表示本体模型中实体与实体之间的关系。
上述从本体模型中选择与第一实体关联的一个或多个第二实体，可以包括，从本体模型中选择与第一实体关联的全部实体作为上述第二实体。然而，这种选择方式通常导致选择的第二实体的数量较多，增加了仿真测试的计算量和周期，因此，在本申请实施例中，还可以基于实体和实体之间关联程度(即“实体关联程度”)，从本体模型中选择第二实体。
即，上述步骤330，包括：基于第一实体、实体关联关系，以及预设的实体关联程度，从本体模型中选择一个或多个第二实体，上述实体关联程度表示本体模型中实体与实体之间的关联程度，且一个或多个第二实体中每个第二实体与第一实体的关联程度，高于多个实体中其他实体与第一实体的关联程度，其他实体为本体模型中除第二实体之外的实体。
可选地，可以通过设置需要选择的第二实体的数量，或者通过设置关联程度阈值，以限制选择的第二实体的数量。
例如，可以设置需要选择的第二实体的数量为5，则基于实体和实体之间的关联关系，以及实体与实体之间的关联程度，从多个实体中选择5个与第一实体关联的第二实体，这5个第二实体与第一实体的关联程度高于多个实体中其他实体与第一实体之间的关联程度。
又例如，通过设置关联程度阈值选择第二实体时，上述方法包括：基于待测试任务，获取关联程度阈值，其中，关联程度阈值为从本体模型中选择一个或多个第二实体使用的关联程度阈值；上述步骤330包括：基于第一实体、实体关联关系，以及实体关联程度，在本体模型中创建一个或多个第二实体，第一实体与一个或多个第二实体之间的关联程度高于关联程度阈值。
需要说明的是，每种待测试任务都有其对应的关联程度阈值，该关联程度阈值可以是测试人员指定的，也可以是预设的，本申请实施例对此不作限定。
上述实体关联程度可以通过具体的关联程度值表示，还可以在表示实体和实体之间关联关系的拓扑图中，通过实体和实体之间的距离N表示。这里距离指在拓扑图中从一个实体跳到另一个实体之间必须经过的最少的连线数量。例如，在拓扑图中两个实体直接相连，则距离为1。又例如，如果两个实体之间相隔一个实体，则实体与实体之间距离为2。
通常，实体和实体之间的距离N的取值来源于测试的需求。例如，只是想测试目标车辆的某一项功能是否可行或者有无明显的漏洞，则N的取值可以为1。当然，实体和实体之间距离N的取值越大，就可以越全面地测试待测试任务。即随着N的取值越大，仿真测试场景中的实体的数量越来越丰富。一般来说，当N＞5的时候，选取的第二实体已经与待测试任务的类型没有什么关系了。
下文以图4所示的本体模型中实体和实体之间关联关系为例，介绍选择第二实体的过程。
图4是本申请实施例的本体模型中实体和实体之间关联关系的拓扑图。假设待测试任务为“跟随车辆行驶”，则可以从上述待测试任务的描述中提取交通元素为“自车”、“机动车辆”。基于此，可以从本体模型中选择自车实体410，以及机动车辆实体420作为第一实体，且需要选择与第一实体距离为1的实体作为第二实体，则基于图4所示的拓扑图可知，与自车实体410距离为1的第二实体包括：驾驶环境实体、机动车辆实体以及车道实体1；与机动车辆实体420距离为1的第二实体包括：行为实体5、障碍物实体1。
340，基于第一实体以及一个或多个第二实体，构建用于测试待测试任务的仿真测试场景。
可选地，上述步骤340包括：基于第一实体的属性、第二实体的属性以及第一实体和第二实体之间的关系，在本体模型中创建第一实体的第一实例以及一个或多个第二实体的一个或多个第二实例；基于第一实例以及一个或多个第二实例，在本体模型中构建仿真测试场景。
需要说明的是，上述第一实体的属性、第二实体的属性以及第一实体和第二实体之间的关系可以是由测试人员基于待测试任务设定的，也可以直接使用仿真软件中的默认值，本申请实施例对此不作限定。
上文结合图1至图4介绍了本申请实施例的仿真测试场景的构建方法。上文介绍的方案可以用于构建新的仿真测试场景。然而，目前有的仿真测试软件可以直接提供已构建完成的仿真测试场景，因此，为了避免重新构建仿真测试场景，本申请的方法还可以用于对已构建的仿真测试场景进行更新，下文结合图4介绍进行介绍。需要说明的是，图4所示的方法中所涉及的术语与上文涉及术语相同的代表的含义也相同，获取方式也可以参照上文介绍的方式获取，为了简洁，下文不再具体赘述。
图5是本申请另一实施例的仿真测试场景的构建方法的流程图。应理解，图5所示的方法可以由图1所示的仿真测试系统执行，也可以由其他仿真测试设备执行，或者由具有计算功能的计算设备执行，本申请实施例对此不作具体限定。图5所示的方法包括步骤510至步骤530。
510，基于待测试任务，从预设的本体模型中选择第一实体，待测试任务用于指示对 目标车辆的待测功能进行测试，和/或对目标车辆所行驶的待测驾驶场景进行测试，其中，本体模型中包含用于交通元素的多个实体。
520，基于第一实体和预设的实体关联关系，从本体模型中选择与第一实体关联的一个或多个第二实体。
步骤520中选择第二实体的方式与步骤330中选择第二实体的方式类似，为了简洁，请参见上文介绍，本申请在此不再赘述。
530，基于第一实体以及一个或多个第二实体，对本体模型中已构建的第一仿真测试场景进行更新，得到本体模型中的第二仿真测试场景，第一仿真测试场景和第二仿真测试场景为用于测试待测试任务的仿真测试场景。
上述已构建的第一仿真测试场景可以是基于现有的仿真测试软件构建的。或者上述已构建的第一仿真测试场景还可以是基于测试人员在本体模型中选择的实体构建的，本申请实施例对上述第一仿真测试场景的构建方式不作限定。
可选地，上述步骤530包括：将第一仿真测试场景中的实例所属的实体与第一实体、一个或多个第二实体进行匹配，确定第一仿真测试场景中未包含的实体；在本体模型中创建未包含的实体对应的实例；将未包含的实体对应的实例添加至第一仿真测试场景，得到第二仿真测试场景。
上述在本体模型中创建未包含的实体对应的实例，可以包括在本体模型中选择未包含的实体，然后通过设置未包含的实体的属性和/或实体与其他实体之间的关系创建该实体对应的实例。
可选地，上述步骤530包括：将第一仿真测试场景中的实体与第一实体以及一个或多个第二实体进行匹配，确定第一仿真测试场景中除第一实体以及一个或多个第二实体之外的多余实体；将多余实体对应的实例从第一仿真测试场景中删除，得到第二仿真测试场景。
上文结合图2至图5介绍了本申请实施例的方法，下文结合图6至图8介绍本申请实施例的装置。应理解，需要说明的是，图6至图8所示的装置可以实现上述方法中各个步骤，为了简洁，在此不再赘述。
图6是本申请实施例的车辆的仿真测试场景的构建装置的示意图。图6所示的装置600包括：获取单元610和处理单元620。
获取单元610，用于获取待测试任务，所述待测试任务用于指示对目标车辆的功能进行测试，和/或对所述目标车辆所行驶的驾驶场景进行测试；
处理单元620，用于基于所述待测试任务，在预设的本体模型中选择第一实体，所述本体模型中包含用于描述交通元素的多个实体；
所述处理单元620，还用于基于所述第一实体和预设的实体关联关系，从所述本体模型中选择与所述第一实体关联的一个或多个第二实体，所述实体关联关系表示所述本体模型中实体与实体之间的关系；
所述处理单元620，还用于基于所述第一实体和所述一个或多个第二实体，构建用于测试所述待测试任务的仿真测试场景。
可选地，作为一个实施例，所述处理单元620，还用于：基于所述第一实体，所述实体关联关系，以及预设的实体关联程度，从所述本体模型中选择所述一个或多个第二实体，所述实体关联程度表示所述本体模型中实体与实体之间的关联程度，其中，所述一个或多 个第二实体中每个第二实体与所述第一实体的关联程度，高于所述本体模型中其他实体与所述第一实体的关联程度，所述其他实体为所述本体模型中除所述第二实体之外的实体。
可选地，作为一个实施例，所述处理单元620，还用于：基于所述待测试任务获取关联程度阈值，所述关联程度阈值为从所述本体模型中选择所述一个或多个第二实体使用的关联程度阈值；基于所述第一实体，所述实体关联关系，以及所述实体关联程度，从所述多个实体中选择所述一个或多个第二实体，所述第一实体与所述一个或多个第二实体之间的关联程度高于所述关联程度阈值。
可选地，作为一个实施例，所述处理单元620，还用于：基于所述第一实体的属性、所述第二实体的属性以及所述第一实体和所述第二实体之间的关系，在所述道路交通本体中创建第一实体的第一实例以及所述一个或多个第二实体的一个或多个第二实例；基于所述第一实例以及所述一个或多个第二实例，在所述本体模型中构建所述仿真测试场景。
可选地，作为一个实施例，所述处理单元620，还用于：获取所述第一实体的属性、所述第二实体的属性以及所述第一实体和所述第二实体之间的关系。
可选地，作为一个实施例，所述处理单元620，还用于：获取用于描述所述待测试任务的内容的信息，所述信息包含第一交通元素；根据所述第一交通元素，从所述预设的本体模型中选择所述第一实体，所述第一实体用于描述所述第一交通元素。
图7是本申请另一实施例的车辆的仿真测试场景的构建装置的示意图。图7所示的装置700包括：获取单元710和处理单元720。
获取单元710，用于获取待测试任务，所述待测试任务用于指示对目标车辆的待测功能进行测试，和/或对目标车辆所行驶的待测驾驶场景进行测试；
处理单元720，用于基于待测试任务，从预设的本体模型中选择第一实体，所述本体模型中包含用于描述交通元素的多个实体；基于所述第一实体和预设的实体关联关系，从所述本体模型中选择与所述第一实体关联的一个或多个第二实体，所述实体关联关系表示所述本体模型中实体与实体之间的关系；基于所述第一实体以及所述一个或多个第二实体，对所述本体模型中已构建的第一仿真测试场景进行更新，得到所述本体模型中的第二仿真测试场景，所述第一仿真测试场景和所述第二仿真测试场景为用于测试所述待测试任务的仿真测试场景。
可选地，作为一个实施例，所述处理单元720，还用于：基于所述第一实体和实体关联关系，以及实体关联程度，选择与所述第一实体关联的一个或多个第二实体，所述实体关联程度用于指示本体模型中实体和实体之间的关联程度，且所述一个或多个第二实体中每个第二实体与所述第一实体的关联程度高于其他实体与所述第一实体的关联程度，所述其他实体为所述多个实体中除所述第二实体之外的实体。
可选地，作为一个实施例，所述处理单元720，还用于：将所述第一仿真测试场景中的实例所属的实体与所述第一实体、所述一个或多个第二实体进行匹配，确定所述第一仿真测试场景中未包含的实体；在所述本体模型中创建所述未包含的实体对应的实例；将所述未包含的实体对应的实例添加至所述第一仿真测试场景，得到所述第二仿真测试场景。
可选地，作为一个实施例，所述处理单元720，还用于：将所述第一仿真测试场景中的实体与所述第一实体以及所述一个或多个第二实体进行匹配，确定所述第一仿真测试场景中除所述第一实体以及所述一个或多个第二实体之外的多余实体；将所述多余实体对应 的实例从所述第一仿真测试场景中删除，得到所述第二仿真测试场景。
在可选的实施例中，所述处理单元620可以为处理器820，所述获取单元610可以为通信接口830，所述计算设备还可以包括存储器810，具体如图8所示。
在可选的实施例中，所述处理单元720可以为处理器820，所述获取单元710可以为通信接口830，所述计算设备还可以包括存储器810，具体如图8所示。
图8是本申请另一实施例的计算设备的示意性框图。图8所示的计算设备800可以包括：存储器810、处理器820、以及通信接口830。其中，存储器810、处理器820，通信接口830通过内部连接通路相连，该存储器810用于存储指令，该处理器820用于执行该存储器820存储的指令，以控制输入/输出接口830接收/发送第二信道模型的至少部分参数。可选地，存储器810既可以和处理器820通过接口耦合，也可以和处理器820集成在一起。
需要说明的是，上述通信接口830使用例如但不限于收发器一类的收发装置，来实现通信设备800与其他设备或通信网络之间的通信。上述通信接口830还可以包括输入/输出接口(input/output interface)。
在实现过程中，上述方法的各步骤可以通过处理器820中的硬件的集成逻辑电路或者软件形式的指令完成。结合本申请实施例所公开的方法可以直接体现为硬件处理器执行完成，或者用处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器810，处理器820读取存储器810中的信息，结合其硬件完成上述方法的步骤。为避免重复，这里不再详细描述。
应理解，本申请实施例中，该处理器可以为中央处理单元(central processing unit，CPU)，该处理器还可以是其他通用处理器、数字信号处理器(digital signal processor，DSP)、专用集成电路(application specific integrated circuit，ASIC)、现成可编程门阵列(field programmable gate array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
还应理解，本申请实施例中，该存储器可以包括只读存储器和随机存取存储器，并向处理器提供指令和数据。处理器的一部分还可以包括非易失性随机存取存储器。例如，处理器还可以存储设备类型的信息。
应理解，本文中术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另外，本文中字符“/”，一般表示前后关联对象是一种“或”的关系。
应理解，在本申请的各种实施例中，上述各过程的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(read-only memory，ROM)、随机存取存储器(random access memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。

Claims (15)

  1. 一种车辆的仿真测试场景的构建方法，其特征在于，包括：
    获取待测试任务，所述待测试任务用于指示对目标车辆的功能进行测试，和/或对所述目标车辆所行驶的驾驶场景进行测试；
    基于所述待测试任务，在预设的本体模型中选择第一实体，所述本体模型中包含用于描述交通元素的多个实体；
    基于所述第一实体和预设的实体关联关系，从所述本体模型中选择与所述第一实体关联的一个或多个第二实体，所述实体关联关系表示所述本体模型中实体与实体之间的关系；
    基于所述第一实体和所述一个或多个第二实体，构建用于测试所述待测试任务的仿真测试场景。
  2. 如权利要求1所述的方法，其特征在于，所述基于所述第一实体和预设的实体关联关系，从所述本体模型中选择与所述第一实体关联的一个或多个第二实体，包括：
    基于所述第一实体，所述实体关联关系，以及预设的实体关联程度，从所述本体模型中选择所述一个或多个第二实体，其中，所述实体关联程度表示所述本体模型中实体与实体之间的关联程度，所述一个或多个第二实体中每个第二实体与所述第一实体的关联程度，高于所述本体模型中其他实体与所述第一实体的关联程度，所述其他实体为所述本体模型中除所述第二实体之外的实体。
  3. 如权利要求2所述的方法，其特征在于，在所述基于所述第一实体，所述实体关联关系，以及预设的实体关联程度，从所述本体模型中选择所述一个或多个第二实体之前，所述方法还包括：
    基于所述待测试任务获取关联程度阈值，所述关联程度阈值为从所述本体模型中选择所述一个或多个第二实体使用的关联程度阈值；
    所述基于所述第一实体，所述实体关联关系，以及预设的实体与实体之间的关联程度，从所述多个实体中选择所述一个或多个第二实体，包括：
    基于所述第一实体，所述实体关联关系，以及所述实体关联程度，从所述本体模型中选择所述一个或多个第二实体，所述第一实体与所述一个或多个第二实体之间的关联程度高于所述关联程度阈值。
  4. 如权利要求1-3中任一项所述的方法，其特征在于，所述基于所述第一实体和所述一个或多个第二实体，构建用于测试所述待测试任务的仿真测试场景，包括：
    基于所述第一实体的属性、所述第二实体的属性以及所述第一实体和所述第二实体之间的关系，在所述本体模型中创建第一实体的第一实例以及所述一个或多个第二实体的一个或多个第二实例；
    基于所述第一实例以及所述一个或多个第二实例，在所述本体模型中构建所述仿真测试场景。
  5. 如权利要求4所述的方法，其特征在于，在所述基于所述第一实体的属性、所述第二实体的属性以及所述第一实体和所述第二实体之间的关系，在所述本体模型中创建第一实体的第一实例以及所述一个或多个第二实体的一个或多个第二实例之前，所述方法还包 括：
    获取所述第一实体的属性、所述第二实体的属性以及所述第一实体和所述第二实体之间的关系。
  6. 如权利要求1-5中任一项所述的方法，其特征在于，所述基于所述待测试任务，在预设的本体模型中选择第一实体，包括：
    获取用于描述所述待测试任务的内容的信息，所述信息包含第一交通元素；
    根据所述第一交通元素，从所述预设的本体模型中选择所述第一实体，所述第一实体用于描述所述第一交通元素。
  7. 一种车辆的仿真测试场景的构建装置，其特征在于，包括：
    获取单元，用于获取待测试任务，所述待测试任务用于指示对目标车辆的功能进行测试，和/或对所述目标车辆所行驶的驾驶场景进行测试；
    处理单元，用于基于所述待测试任务，在预设的本体模型中选择第一实体，所述本体模型中包含用于描述交通元素的多个实体；
    所述处理单元，还用于基于所述第一实体和预设的实体关联关系，从所述本体模型中选择与所述第一实体关联的一个或多个第二实体，所述实体关联关系表示所述本体模型中实体与实体之间的关系；
    所述处理单元，还用于基于所述第一实体和所述一个或多个第二实体，构建用于测试所述待测试任务的仿真测试场景。
  8. 如权利要求7所述的装置，其特征在于，所述处理单元，还用于：
    基于所述第一实体，所述实体关联关系，以及预设的实体关联程度，从所述本体模型中选择所述一个或多个第二实体，所述实体关联程度表示所述本体模型中实体与实体之间的关联程度，其中，所述一个或多个第二实体中每个第二实体与所述第一实体的关联程度，高于所述本体模型中其他实体与所述第一实体的关联程度，所述其他实体为所述本体模型中除所述第二实体之外的实体。
  9. 如权利要求8所述的装置，其特征在于，所述处理单元，还用于：
    基于所述待测试任务获取关联程度阈值，所述关联程度阈值为从所述本体模型中选择所述一个或多个第二实体使用的关联程度阈值；
    基于所述第一实体，所述实体关联关系，以及所述实体关联程度，从所述本体模型中选择所述一个或多个第二实体，所述第一实体与所述一个或多个第二实体之间的关联程度高于所述关联程度阈值。
  10. 如权利要求7-9中任一项所述的装置，其特征在于，所述处理单元，还用于：
    基于所述第一实体的属性、所述第二实体的属性以及所述第一实体和所述第二实体之间的关系，在所述道路交通本体中创建第一实体的第一实例以及所述一个或多个第二实体的一个或多个第二实例；
    基于所述第一实例以及所述一个或多个第二实例，在所述本体模型中构建所述仿真测试场景。
  11. 如权利要求10所述的装置，其特征在于，所述处理单元，还用于：
    获取所述第一实体的属性、所述第二实体的属性以及所述第一实体和所述第二实体之间的关系。
  12. 如权利要求7-11中任一项所述的装置，其特征在于，所述处理单元，还用于：
    获取用于描述所述待测试任务的内容的信息，所述信息包含第一交通元素；
    根据所述第一交通元素，从所述预设的本体模型中选择所述第一实体，所述第一实体用于描述所述第一交通元素。
  13. 一种计算设备，其特征在于，包括：至少一个处理器和存储器，所述至少一个处理器与所述存储器耦合，用于读取并执行所述存储器中的指令，以执行如权利要求1-6中任一项所述的方法。
  14. 一种计算机可读介质，其特征在于，所述计算机可读介质存储有程序代码，当所述计算机程序代码在计算机上运行时，使得所述计算机执行如权利要求1-6中任一项所述的方法。
  15. 一种芯片，其特征在于，包括：至少一个处理器和存储器，所述至少一个处理器与所述存储器耦合，用于读取并执行所述存储器中的指令，以执行如权利要求1-6中任一项所述的方法。
PCT/CN2021/085990 2020-08-21 2021-04-08 车辆的仿真测试场景的构建方法和装置 WO2022037085A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
EP21857186.7A EP4191221A4 (en) 2020-08-21 2021-04-08 METHOD AND DEVICE FOR CONSTRUCTING A VEHICLE SIMULATION TEST SCENARI

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010850861.4 2020-08-21
CN202010850861.4A CN114077785A (zh) 2020-08-21 2020-08-21 车辆的仿真测试场景的构建方法和装置

Publications (1)

Publication Number Publication Date
WO2022037085A1 true WO2022037085A1 (zh) 2022-02-24

Family

ID=80282519

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/085990 WO2022037085A1 (zh) 2020-08-21 2021-04-08 车辆的仿真测试场景的构建方法和装置

Country Status (3)

Country Link
EP (1) EP4191221A4 (zh)
CN (1) CN114077785A (zh)
WO (1) WO2022037085A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115524996A (zh) * 2022-09-13 2022-12-27 工业和信息化部装备工业发展中心 模拟仿真场景库的边缘场景补充方法及装置
CN115687163A (zh) * 2023-01-05 2023-02-03 中汽智联技术有限公司 场景库构建方法、装置、设备和存储介质
CN116244932A (zh) * 2023-01-28 2023-06-09 芯华章科技(北京)有限公司 对车辆进行安全仿真的方法、电子设备及存储介质

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114486288A (zh) * 2022-01-28 2022-05-13 公安部交通管理科学研究所 用于智能网联汽车测试道路中的交通管理设备布局方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180089154A1 (en) * 2016-09-26 2018-03-29 North America Photon Infotech Limited Computer implemented system and method for transforming web content for display on multiple form factors
CN110232257A (zh) * 2019-07-02 2019-09-13 吉林大学 一种自动驾驶测试场景的构建方法及其难度系数计算方法
CN110307995A (zh) * 2019-05-28 2019-10-08 同济大学 一种用于自动驾驶汽车边缘测试的测试方法
CN110597711A (zh) * 2019-08-26 2019-12-20 湖南大学 一种基于场景和任务的自动驾驶测试用例生成方法
CN110597086A (zh) * 2019-08-19 2019-12-20 深圳元戎启行科技有限公司 仿真场景生成方法和无人驾驶系统测试方法

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108931927B (zh) * 2018-07-24 2019-07-30 百度在线网络技术（北京）有限公司 无人驾驶仿真场景的创建方法及装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180089154A1 (en) * 2016-09-26 2018-03-29 North America Photon Infotech Limited Computer implemented system and method for transforming web content for display on multiple form factors
CN110307995A (zh) * 2019-05-28 2019-10-08 同济大学 一种用于自动驾驶汽车边缘测试的测试方法
CN110232257A (zh) * 2019-07-02 2019-09-13 吉林大学 一种自动驾驶测试场景的构建方法及其难度系数计算方法
CN110597086A (zh) * 2019-08-19 2019-12-20 深圳元戎启行科技有限公司 仿真场景生成方法和无人驾驶系统测试方法
CN110597711A (zh) * 2019-08-26 2019-12-20 湖南大学 一种基于场景和任务的自动驾驶测试用例生成方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4191221A4

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115524996A (zh) * 2022-09-13 2022-12-27 工业和信息化部装备工业发展中心 模拟仿真场景库的边缘场景补充方法及装置
CN115687163A (zh) * 2023-01-05 2023-02-03 中汽智联技术有限公司 场景库构建方法、装置、设备和存储介质
CN115687163B (zh) * 2023-01-05 2023-04-07 中汽智联技术有限公司 场景库构建方法、装置、设备和存储介质
CN116244932A (zh) * 2023-01-28 2023-06-09 芯华章科技(北京)有限公司 对车辆进行安全仿真的方法、电子设备及存储介质

Also Published As

Publication number Publication date
EP4191221A1 (en) 2023-06-07
EP4191221A4 (en) 2024-02-14
CN114077785A (zh) 2022-02-22

Similar Documents

Publication Publication Date Title
WO2022037085A1 (zh) 车辆的仿真测试场景的构建方法和装置
CN108921200B (zh) 用于对驾驶场景数据进行分类的方法、装置、设备和介质
US10599546B1 (en) Autonomous vehicle testing systems and methods
CN111680362B (zh) 一种自动驾驶仿真场景获取方法、装置、设备及存储介质
CN110765661A (zh) 自动驾驶仿真场景生成方法及装置、电子设备、存储介质
JP7220169B2 (ja) 情報処理方法、装置、記憶媒体、及びプログラム
US20230415787A1 (en) Method and apparatus for generating a simulation scene, electronic device and storage medium
JP2023055697A (ja) 自動運転テスト方法、装置、電子機器及び記憶媒体
CN115221722B (zh) 自动驾驶车辆的仿真测试方法、模型训练方法和设备
WO2022041717A1 (zh) 一种仿真交通流的构建方法及仿真设备
CN115016318A (zh) 自动驾驶仿真测试场景描述语言的融合方法及系统
CN113272744A (zh) 用于监测自动驾驶车辆的适当行为的系统及其方法
WO2021146906A1 (zh) 测试场景仿真方法、装置、计算机设备和存储介质
CN114492022A (zh) 路况传感数据处理方法、装置、设备、程序以及存储介质
CN115203969A (zh) 自动驾驶仿真场景的控制方法、装置、设备和存储介质
CN115830399A (zh) 分类模型训练方法、装置、设备、存储介质和程序产品
US11673577B2 (en) System and methods of adaptive relevancy prediction for autonomous driving
CN111381575B (zh) 自动测试方法、装置、服务器、电子设备及存储介质
EP4203442A1 (en) On-board data processing method and device, electronic device and storage medium
WO2023060963A1 (zh) 道路信息的识别方法、装置、电子设备、车辆及介质
WO2022143057A1 (zh) 自动驾驶算法测试方法及相关设备
US20230154127A1 (en) 2-d image reconstruction in a 3-d simulation
CN115543809A (zh) 自动驾驶功能的测试场景库构建方法及装置
CN114973656A (zh) 交通交互性能的评估方法、装置、设备、介质和产品
CN112966565A (zh) 一种物体检测方法、装置、终端设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21857186

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2021857186

Country of ref document: EP

Effective date: 20230301

NENP Non-entry into the national phase

Ref country code: DE