A simulation scene setting method, device, equipment and storage medium

Abstract

The present application discloses a simulation scene setting method, apparatus, device and storage medium, the method comprising: reading in a scene configuration in an exported target format, obtaining a test parameter list of the scene, and modifying the test parameters in the test parameter list through a script to generate a simulation scene sequence; when the simulation scene sequence is legal, publishing the simulation scene sequence to a target scene warehouse. The present application can edit and modify the autonomous driving simulation scene based on a script editor, supporting the operator to describe the modification logic, facilitating the generalization of the autonomous driving simulation scene. At the same time, without the need for user interface editing, the data of the attributes to be edited can be updated in real time during the iteration process of the autonomous driving algorithm, thereby ensuring the consistency of the autonomous driving simulation scene.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a simulation scene setting method, device, equipment and storage medium. Background Art

[0002] As the output of autonomous driving algorithm simulation, autonomous driving simulation scenarios play a vital role in algorithm simulation. How to effectively edit the output autonomous driving simulation scenarios, or even based on an autonomous driving simulation scenario as a template, modify several groups of attributes, and generate multiple new autonomous driving simulation scenarios for generalization, has become an important part of the autonomous driving simulation process.

[0003] Currently, editing autonomous driving simulation scenarios is accomplished by providing a user interface that lists all attributes to be edited, and then allowing engineers or operators to edit the attributes within the user interface. However, this approach has the following issues:

[0004] 1. During the iteration of the autonomous driving algorithm, the attributes to be edited are constantly added, deleted, checked, and modified. The corresponding user editing interface also needs to be updated synchronously to ensure the consistency of the autonomous driving simulation scene. However, this process is often difficult to synchronize, resulting in the corresponding user editing interface not being updated in a timely manner.

[0005] 2. The user interface editing method is difficult to support generalization, and the user interface editing method is difficult to support the operator to modify the description of the logic. Summary of the Invention

[0006] To this end, the technical problem solved by the embodiments of the present application is to provide a simulation scene setting method, device, equipment and storage medium, which can edit and modify the autonomous driving simulation scene based on a script editor without the need for user interface editing.

[0007] In order to solve the above technical problems, the technical solutions adopted in this application are as follows:

[0008] In a first aspect, an embodiment of the present application provides a simulation scene setting method, comprising:

[0009] Read the exported target format scenario configuration, obtain the scenario test parameter list, and modify the test parameters in the test parameter list through the script to generate a simulation scenario sequence;

[0010] When the simulation scene sequence is legal, the simulation scene sequence is published to the target scene warehouse.

[0011] Furthermore, before the step of publishing the simulation scene sequence to the target scene warehouse, the following steps are also included:

[0012] Custom syntax checking scripts;

[0013] Based on the syntax check script, determining whether the output data format of the simulation scenario sequence conforms to the target format;

[0014] When the output data format of the simulation scenario sequence conforms to the target format, the simulation scenario sequence is legal.

[0015] Furthermore, before the step of publishing the simulation scene sequence to the target scene warehouse, the following steps are also included:

[0016] Custom logic test scripts;

[0017] Based on the logic check script, determining whether the content of the configuration field of the simulation scenario sequence meets the preset conditions;

[0018] When the content of the configuration field of the simulation scenario sequence meets a preset condition, the simulation scenario sequence is legal.

[0019] Furthermore, the step of modifying the test parameters in the test parameter list by using a script to generate a simulation scenario sequence includes:

[0020] Build a JavaScript runtime environment;

[0021] Import the test parameter list of any scenario into the JavaScript runtime environment;

[0022] The test parameter list of any scenario and the edited script are imported into the script engine, the attribute relationship between the test parameters is constructed in the javascript running environment, and a simulation scenario sequence is generated.

[0023] Furthermore, the test parameters include vehicle test parameters and environment test parameters; and according to the test parameter list of any scenario, an attribute relationship between the test parameters is constructed in the JavaScript runtime environment, including:

[0024] Construct attribute relationships between vehicle test parameters and environmental test parameters.

[0025] Alternatively, the test parameters include at least two different environment test parameters; and according to the test parameter list of any scenario, an attribute relationship between the test parameters is constructed in the JavaScript runtime environment, including:

[0026] Construct attribute relationships between test parameters in different environments.

[0027] Furthermore, the logic of editing the test parameters in the test parameter list, after generating the simulation scenario sequence, further includes:

[0028] According to the simulation scenario sequence, a matrix table is output.

[0029] In a second aspect, an embodiment of the present application provides a simulation scene setting device, comprising:

[0030] Scenario configuration module, used to configure the scene based on the scenario editor;

[0031] The scenario editing module is used to parse the configuration scenario based on the script editor, obtain the test parameter list of the scenario, and edit the logic of the test parameters in the test parameter list to generate a simulation scenario sequence;

[0032] The scene publishing module is used to publish the simulation scene sequence to the target scene warehouse when the simulation scene sequence is legal.

[0033] Furthermore, the simulation scene setting device provided in the embodiment of the present application further includes:

[0034] The output module is used to output a matrix table according to the simulation scenario sequence.

[0035] In a third aspect, an embodiment of the present application provides a device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor implements the steps of any one of the above-described simulation scene setting methods when executing the computer program.

[0036] In a fourth aspect, an embodiment of the present application provides a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the simulation scene setting method described in any one of the above are implemented.

[0037] In summary, compared with the prior art, the technical solutions provided by the embodiments of the present application have at least the following beneficial effects:

[0038] In an embodiment of the present application, a scenario editor is used to configure a scenario to obtain configuration information of a basic autonomous driving scenario for subsequent parsing by a script editor. The script editor is used to parse the configured scenario, obtain a test parameter list for the scenario, and edit the logic of the test parameters within the test parameter list to generate a simulation scenario sequence to support users in writing corresponding logic, thereby facilitating the generalization of autonomous driving simulation scenarios. The added, deleted, checked, and modified attributes to be edited do not need to be synchronously updated through a user editing interface. By updating the data of the attributes to be edited in real time during the iteration of the autonomous driving algorithm, the consistency of the autonomous driving simulation scenario is ensured. At the same time, the legitimacy of the simulation scenario sequence is verified to ensure that the regenerated configuration scenario and content are legal and have application value that meets design requirements. When the simulation scenario sequence is legal, the simulation scenario sequence is published to a target scenario repository. Furthermore, a simulation scenario setting method can edit and modify the autonomous driving simulation scenario based on a script editor to support operators in describing modification logic, thereby facilitating the generalization of the autonomous driving simulation scenario. At the same time, the data of the attributes to be edited in real time during the iteration of the autonomous driving algorithm is updated without the need for user interface editing, thereby ensuring the consistency of the autonomous driving simulation scenario.

[0039] In the embodiment of the present application, two methods of verifying the legitimacy of the simulation scenario sequence are set up: a syntax check script and a logic check script. Only when the scenario is generalized, the preset logical conditions are set to control the boundaries of the generalization; conversely, the legitimacy of certain scenarios can be tested through generalization without limiting conditions, and then the constraints of the scenario can be deduced. In the embodiment of the present application, a javascript runtime environment is first constructed; secondly, a test parameter list of any scenario is imported into the javascript runtime environment; then, based on the test parameter list of any scenario, the attribute relationship between the test parameters is constructed in the javascript runtime environment; finally, a simulation scenario sequence is generated based on the script logic and the attribute relationship between the test parameters. In the embodiment of the present application, the attribute relationship between the test parameters is realized online through the javascript runtime environment in conjunction with the script logic, thereby improving the work efficiency of engineers.

[0040] The embodiments of the present application can intuitively present the specific content of the simulation scenario sequence to the engineer by outputting a matrix table according to the simulation scenario sequence. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a schematic diagram of the overall flow of the simulation scene setting method provided by the first exemplary embodiment of the present application.

[0042] Figure 2 This is a workflow diagram of the script editor.

[0043] Figure 3 It is a flowchart of editing the logic of the test parameters in the test parameter list to generate a simulation scenario sequence.

[0044] Figure 4 It is a flowchart of the simulation scene setting method provided by the twelfth exemplary embodiment of the present application.

[0045] Figure 5 It is a structural diagram of a simulation scene setting device provided in one embodiment of the present application.

[0046] Figure 6 It is a structural diagram of a simulation scene setting device provided by the twenty-third exemplary embodiment of the present application.

[0047] Figure 7 It is a structural schematic diagram of the device provided by the twenty-fifth exemplary embodiment of the present application. DETAILED DESCRIPTION

[0048] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, those skilled in the art may make non-creative modifications to the present embodiment as needed, but as long as they are within the scope of the claims of the present application, they are protected by the patent law.

[0049] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0050] The term "comprise" and any variations thereof in the specification and claims of this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus that includes a series of steps or units is not necessarily limited to those steps or units expressly listed, but may include other steps or units not expressly listed or inherent to such process, method, product or apparatus.

[0051] In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0052] The embodiments of the present application are described in further detail below with reference to the accompanying drawings.

[0053] Reference Figure 1 ,The main steps of the simulation scene setting method are described as follows:

[0054] Based on the scene editor, configure the scene and export the scene configuration to the target format;

[0055] Based on the script editor, read the exported target format scenario configuration, obtain the scenario test parameter list, and modify the test parameters in the test parameter list through the script to generate a simulation scenario sequence;

[0056] Verify the legitimacy of the simulation scenario sequence;

[0057] When the simulation scene sequence is legal, the simulation scene sequence is published to the target scene warehouse.

[0058] The target formats for exporting scene configurations include Json and Protobuf.

[0059] Reference Figure 2 , the script editor workflow includes:

[0060] 1.1 Basic scenario configuration to obtain configuration scenario information;

[0061] 1.2 Script editor parsing and editing to perform logical editing of configuration scenarios;

[0062] 1.3 script engine execution;

[0063] 1.4 Scenario verification: verify the logic of the configuration scenario;

[0064] 1.5 scene released.

[0065] Specifically, the user opens the autonomous driving scenario editor, configures the scenario based on the scenario editor to create a basic scenario, and exports the scenario configuration to the target format for parsing when the script editor is executed later. When the user creates the basic scenario, all elements of the entire autonomous driving simulation scenario are defined, and all elements are summarized to form a list of test parameters for the scenario. The defined elements include the properties of the main vehicle itself, the interactive objects placed in the autonomous driving scene, such as information about obstacle vehicles, pedestrians, traffic lights, etc., trigger settings, map information, etc. For example, build a main vehicle a and a front vehicle b on the scenario editor.

[0066] The script editor is integrated with the scenario editor. Based on the script editor, it reads in the exported target format scenario configuration, obtains the scenario's test parameter list, and modifies the test parameters within the test parameter list through scripts to generate a simulation scenario sequence. By obtaining the configuration scenario information, the script editor executes a preset, engine-executable script, reads in the exported target format scenario configuration information, and modifies it to generate a corresponding new configuration scenario, or generalizes a series of new configuration scenarios. This allows real-time updates of the data of the attributes to be edited during the iteration of the autonomous driving algorithm, helping to ensure the consistency of the autonomous driving simulation scenario.

[0067] Modifications can be made to any group or groups of elements within all defined elements. For example, the configured scene information for vehicle A and vehicle B is automatically exported to the script editor, where the user can configure the logic between vehicle A and vehicle B, such as the distance between them.

[0068] The steps for verifying the legitimacy of the simulation scenario sequence include:

[0069] Customize validation scripts to predefine legal autonomous driving simulation scenarios. Specifically, customize syntax validation scripts and logic validation scripts.

[0070] Based on the syntax check script, it is determined whether the output data format of the simulation scenario sequence conforms to the target format; and when the output data format of the simulation scenario sequence conforms to the target format, the simulation scenario sequence is legal.

[0071] Alternatively, a logic check script is used to determine whether the contents of the configuration fields of the simulation scenario sequence meet preset conditions. If the contents of the configuration fields of the simulation scenario sequence meet the preset conditions, the simulation scenario sequence is considered legal. The preset conditions are the threshold ranges within which legal values ​​of the contents of the configuration fields of the scenarios can be reached.

[0072] Alternatively, when the output data format of the simulation scenario sequence conforms to the target format and the legal value of the content of the configuration field of the scene is within the preset threshold range, the simulation scenario sequence is legal; when the output data format of the simulation scenario sequence does not conform to the target format, or the legal value of the content of the configuration field of the scene is outside the preset threshold range, the simulation scenario sequence is illegal.

[0073] For example, in a scene where a pedestrian suddenly jumps out, physical calculations can be performed in advance to calculate the speed relationship that may lead to a collision, that is, the boundary conditions, and then the boundary conditions can be used to control the generalized scene; or direct generalization can be performed without restrictions, and then the conditions that will cause a collision can be summarized.

[0074] In this embodiment, a series of verification scripts are written to verify the configuration scenario generated by the script editor, that is, scenario verification is generated to determine whether the configuration scenario is legal.

[0075] Verify the legitimacy of the simulation scenario sequence to ensure the legality of the autonomous driving simulation scenario. Traditional scripting languages ​​lack compilation checking capabilities, and the legitimacy of the scenario configuration content modified by traditional scripting languages ​​cannot be guaranteed. Therefore, the legitimacy of the simulation scenario sequence must be verified to ensure that the output data format of the re-edited configuration scenario conforms to the target format, thereby obtaining the data input format required by the autonomous driving algorithm simulation execution platform. Furthermore, the content of the re-generated configuration fields must be verified to be legal, that is, to meet design expectations, to ensure that the simulation scenario has the application value that meets the design requirements.

[0076] Then, by setting up two methods to verify the legitimacy of the simulation scenario sequence: syntax check script and logic check script, only when generalizing the scenario will the preset logical conditions be set to control the boundaries of generalization; conversely, the legitimacy of certain scenarios can be tested through generalization without any restrictions, and then the constraints of the scenario can be inferred.

[0077] Furthermore, in this embodiment, the script editor may support Javascript or Python language.

[0078] Because the basic scene configuration information is exported in the form of Javascript script objects, a script editor using the Javascript language can directly parse the exported basic scene configuration information, that is, natively use the exported basic scene configuration information, which is more convenient to operate.

[0079] If you use the Python script editor, you must first convert the basic scene configuration information into a JSON object, then pass it into the script editor to obtain the final result list, and then convert the result list into a JavaScript object for use in scene publishing.

[0080] Then, by pre-defining a legal autonomous driving simulation scenario, and inputting the obtained configuration scenario information as a specific input into the script editor, the preset editing script is executed on the script editor to finally output an object that conforms to the target data format, so as to obtain a data format that meets the requirements of the input autonomous driving algorithm simulation execution platform.

[0081] Figure 3 This is a simulation scenario setting method provided by the first exemplary embodiment of the present application. The main steps of generating a simulation scenario sequence by modifying the test parameters in the test parameter list through a script are described as follows:

[0082] Build a JavaScript runtime environment;

[0083] Import the test parameter list of any scenario into the JavaScript runtime environment;

[0084] The test parameter list of any scenario and the edited script are imported into the script engine, the attribute relationship between the test parameters is constructed in the javascript running environment, and a simulation scenario sequence is generated.

[0085] The first exemplary embodiment of the present application first constructs a JavaScript runtime environment; secondly, imports a list of test parameters for any scenario into the JavaScript runtime environment; then, based on the list of test parameters for any scenario, constructs attribute relationships between the test parameters within the JavaScript runtime environment; and finally, generates a simulation scenario sequence based on the script logic and the attribute relationships between the test parameters. The first exemplary embodiment of the present application utilizes the JavaScript runtime environment in conjunction with script logic to implement online compilation of attribute relationships between test parameters, thereby improving the work efficiency of engineers.

[0086] The simulation scene setting method provided by the second exemplary embodiment of the present application is Figure 1 Further improvements are made based on the first exemplary embodiment shown, and the specific improvements are as follows:

[0087] The test parameters include vehicle test parameters and environment test parameters; according to the test parameter list of any scenario, an attribute relationship between the test parameters is constructed in the JavaScript runtime environment, including:

[0088] Construct attribute relationships between vehicle test parameters and environmental test parameters.

[0089] It should be noted that the self-vehicle test parameters include the self-vehicle attributes, which include but are not limited to the self-vehicle position, self-vehicle speed, self-vehicle acceleration and self-vehicle front wheel direction; the environmental test parameters include but are not limited to obstacle vehicle attributes, pedestrian attributes and surrounding environment attributes; the obstacle vehicle attributes include but are not limited to obstacle vehicle position, obstacle vehicle speed, obstacle vehicle acceleration and obstacle vehicle front wheel direction; the pedestrian attributes include but are not limited to pedestrian position, pedestrian speed and the relative distance between the pedestrian and the roadside; the surrounding environment attributes include but are not limited to lane traffic light position, lane traffic light status, trigger time of the trigger and trigger position of the trigger.

[0090] In order to test the braking scenario, the simulation scenario setting method provided by the third exemplary embodiment of the present application is further improved on the basis of the second exemplary embodiment. The specific improvements are as follows:

[0091] The self-vehicle test parameters include self-vehicle speed; the environmental test parameters include obstacle vehicle speed. The attribute relationship between the self-vehicle test parameters and the environmental test parameters is: self-vehicle speed = a × obstacle vehicle speed, where a is any value that can achieve a braking test interval for both the self-vehicle and obstacle vehicles. In this embodiment, the braking test interval for both the self-vehicle and obstacle vehicles is [1.2, 1.6], so the value range of a is: 1.2 ≤ a ≤ 1.6.

[0092] When a is less than 1.2, the vehicle can definitely brake behind the obstacle vehicle. Such an attribute relationship has no testing significance and must be filtered out.

[0093] When a>1.6, such a situation almost never occurs, so such attribute relationships have no testing significance and must be filtered out.

[0094] Therefore, when the value range of a is 1.2≤a≤1.6, it is reasonable and has test significance.

[0095] In order to ensure the implementation of the braking scenario, the simulation scenario setting method provided in the fourth exemplary embodiment of the present application is further improved on the basis of the second exemplary embodiment, and the specific improvements are as follows:

[0096] The ego vehicle test parameters include the ego vehicle's position; the environmental test parameters include the position of the obstructing vehicle. The attribute relationship between the ego vehicle test parameters and the environmental test parameters is: ego vehicle position = obstructing vehicle position - relative distance between the ego vehicle and the obstructing vehicle. The relative displacement between the ego vehicle and the obstructing vehicle = relative direction between the ego vehicle and the obstructing vehicle × distance between the ego vehicle and the obstructing vehicle.

[0097] In order to test the possibility of collision between the vehicle and the pedestrian, the fifth exemplary embodiment of the present application is further improved on the basis of the second exemplary embodiment, and the specific improvements are as follows:

[0098] The vehicle test parameters include the vehicle's position and speed; the environmental test parameters include the pedestrian's position, pedestrian's speed, and the pedestrian's relative distance from the roadside. The relative distance between the vehicle and pedestrian is determined based on the vehicle's position and pedestrian's position. The relationship between the vehicle test parameters and the environmental test parameters is: relative distance between the vehicle and pedestrian / vehicle speed = (relative distance between the pedestrian and the roadside / pedestrian speed) × b, where b is any value within the range of possible collisions between the vehicle and pedestrian. In this embodiment, the range of possible collisions between the vehicle and pedestrian is [0, +∞], so the value range of b is: b>0.

[0099] As a further improvement of the fifth exemplary embodiment of the present application, b=0.9, thereby ensuring that the vehicle has almost every chance of encountering a pedestrian.

[0100] In order to test the state switching of lane traffic lights, the simulation scene setting method provided by the sixth exemplary embodiment of the present application is further improved on the basis of the second exemplary embodiment. The specific improvements are as follows:

[0101] The ego vehicle test parameters include the ego vehicle position; the environmental test parameters include the lane traffic light position; the distance between the ego vehicle and the lane traffic light is obtained based on the ego vehicle position and the lane traffic light position; the attribute relationship between the ego vehicle test parameters and the environmental test parameters is: the distance between the ego vehicle and the lane traffic light is less than m, where m is any value within the testable lane traffic light state transition range. In this embodiment, the testable lane traffic light state transition range is [0, +∞], so the value range of m is: m>0. When the distance between the ego vehicle and the lane traffic light is less than m, the lane traffic light is set to red, and when the distance between the ego vehicle and the lane traffic light is greater than or equal to m, the lane traffic light is set to green.

[0102] In order to examine whether the vehicle can successfully bypass the slowly starting obstacle vehicle and continue to move forward, the simulation scene setting method provided by the seventh exemplary embodiment of this application is further improved on the basis of the second exemplary embodiment. The specific improvements are as follows:

[0103] The self-vehicle test parameters include the self-vehicle position; the environmental test parameters include the trigger position of the trigger; the distance between the self-vehicle and the trigger position is obtained based on the self-vehicle position and the trigger position of the trigger; the attribute relationship between the self-vehicle test parameters and the environmental test parameters is: the distance between the self-vehicle and the trigger position = 0.

[0104] When the distance between the ego vehicle and the trigger position = 0, the obstacle vehicle in front of the ego vehicle is triggered to start slowly, so as to examine whether the ego vehicle can successfully bypass the slowly starting obstacle vehicle and move forward.

[0105] In order to test the trigger, the simulation scene setting method provided by the eighth exemplary embodiment of the present application is further improved on the basis of the second exemplary embodiment, and the specific improvements are as follows:

[0106] The test parameters include at least two different environment test parameters; and according to the test parameter list of any scenario, an attribute relationship between the test parameters is constructed in the JavaScript runtime environment, including:

[0107] Construct attribute relationships between test parameters in different environments.

[0108] It should be noted that the environmental test parameters include but are not limited to the attributes of the obstacle vehicle, pedestrians and surrounding environment attributes; the attributes of the obstacle vehicle include but are not limited to the position of the obstacle vehicle and the speed of the obstacle vehicle; the attributes of the pedestrian include but are not limited to the position of the pedestrian and the speed of the pedestrian; the attributes of the surrounding environment include but are not limited to the status of the lane traffic light, the trigger time of the trigger, and the status of the sidewalk traffic light.

[0109] In order to test whether the vehicle can maintain safety when the obstacle vehicle brakes, the simulation scene setting method provided in the ninth exemplary embodiment of the present application is further improved on the basis of the eighth exemplary embodiment. The specific improvements are as follows:

[0110] The environmental test parameters include the starting braking position of the obstacle vehicle and the trigger time of the trigger; the attribute relationship of the different environmental test parameters is: when the timing reaches the trigger time preset by the trigger, the obstacle vehicle is triggered to start braking from the current position (i.e. the starting braking position of the obstacle vehicle).

[0111] By recording the time when the obstacle vehicle starts braking, the time when it stops completely, and the position from when the obstacle vehicle starts braking to when it stops completely, we can examine whether the vehicle behind the obstacle vehicle can maintain safety from the time the obstacle vehicle starts braking to when it stops completely.

[0112] In order to examine whether the vehicle can correctly handle the sudden merging behavior, the simulation scenario setting method provided in the tenth exemplary embodiment of the present application is further improved on the basis of the eighth exemplary embodiment. The specific improvements are as follows:

[0113] The environmental test parameters include the lane traffic light status and the speed of the obstructing vehicle. The attribute relationship between these different environmental test parameters is as follows: when the lane traffic light status changes from red to green, the speed of the obstructing vehicle changes from 0 m / s to N m / s, where N is any value within a range that can be used to test whether the ego vehicle can correctly handle sudden merging. In this embodiment, the range that can be used to test whether the ego vehicle can correctly handle sudden merging is [0, +∞], and the value range of N is: N>0.

[0114] At this time, after the obstacle vehicle gains speed, it changes its original driving lane to the same driving lane as the vehicle.

[0115] In order to examine whether the vehicle can handle pedestrian violations, the simulation scenario setting method provided in the eleventh exemplary embodiment of this application is further improved on the basis of the eighth exemplary embodiment. The specific improvements are as follows:

[0116] The environmental test parameters include the pedestrian traffic light status and pedestrian speed. The attribute relationship between the different environmental test parameters is as follows: when the pedestrian traffic light status changes from green to red, the pedestrian speed changes from 0 meters per second to N meters per second, where N is any value within a range that can be used to determine whether the vehicle can respond to pedestrian violations. In this embodiment, the range that can be used to determine whether the vehicle can respond to pedestrian violations is [0, +∞], and the value range of N is: N>0.

[0117] The pedestrian traffic light turns red and a pedestrian violates the rules by running the red light. At this time, the vehicle is in the starting state, and the vehicle is tested to see if it can handle the violation.

[0118] In order to intuitively display the specific content of the simulation scene sequence, the simulation scene setting method provided in the twelfth to twenty-second exemplary embodiments of the present application is further improved on the basis of the first to eleventh exemplary embodiments described above, and the specific improvements are as follows:

[0119] Edit the logic of the test parameters in the test parameter list. After generating the simulation scenario sequence, it also includes:

[0120] Output a matrix table according to the simulation scenario sequence to intuitively present the specific content of the simulation scenario sequence.

[0121] and Figure 4 It is a flowchart of a simulation scene setting method provided by the twelfth exemplary embodiment of the present application.

[0122] Here, taking the example of constructing the attribute relationship between the vehicle test parameter and the environmental test parameter where the vehicle speed = a × the obstacle vehicle speed (where 1.2≤a≤1.6), the code for implementing the attribute relationship between the vehicle test parameter and the environmental test parameter using the JavaScript runtime environment and script logic is described as follows:

[0123]

[0124]

[0125] Therefore, a simulation scene setting method can edit and modify the autonomous driving simulation scene based on a script editor to support the operator to describe the modification logic, which is conducive to the generalization of the autonomous driving simulation scene. At the same time, there is no need to use the user interface editing method. By updating the data of the attributes to be edited in real time during the iteration process of the autonomous driving algorithm, it is conducive to ensuring the consistency of the autonomous driving simulation scene, and solves the problem of untimely synchronization update of the user interface when the autonomous driving simulation scene is constantly added, deleted, checked and modified during the iteration process of the autonomous driving algorithm, and the problem of inability to effectively generalize the scene using the user interface editing method; through the javascript runtime environment and script logic to realize the online compilation of the attribute relationship between test parameters, thereby improving the work efficiency of engineers; by outputting a matrix table according to the simulation scene sequence, the specific content of the simulation scene sequence can be intuitively presented to engineers.

[0126] Figure 5 The simulation scene setting device provided by this application includes:

[0127] The scene configuration module is used to configure the scene based on the scene editor and export the scene configuration to the target format;

[0128] The scenario editing module is used to read the exported target format scenario configuration based on the script editor, obtain the test parameter list of the scenario, and modify the test parameters in the test parameter list through the script to generate a simulation scenario sequence;

[0129] Scenario verification module, used to verify the legitimacy of simulation scenario sequences;

[0130] The scenario publishing module is used to publish the simulation scenario sequence to the target scenario warehouse when the simulation scenario sequence is legal.

[0131] Figure 6 The simulation scene setting device provided by the twenty-third exemplary embodiment of the present application has a scene editing module including:

[0132] The first submodule is used to build the JavaScript runtime environment;

[0133] Import submodule, used to import the test parameter list of any scenario into the JavaScript runtime environment;

[0134] A second construction submodule is configured to construct an attribute relationship between test parameters in the JavaScript runtime environment according to the test parameter list of any scenario;

[0135] The generation submodule is used to generate a simulation scenario sequence according to the script logic and the attribute relationship between the test parameters.

[0136] In order to intuitively display the specific content of the simulation scene sequence, the simulation scene setting device provided in the twenty-fourth exemplary embodiment of the present application is further improved on the basis of the twenty-third exemplary embodiment of the present application. The specific improvements are as follows:

[0137] The simulation scene setting device further includes an output module, and the output module is used to output a matrix table according to the simulation scene sequence.

[0138] Each module of the above-mentioned simulation scene setting device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0139] Figure 4 A device is provided in the twenty-fifth exemplary embodiment of the present application, which is an electronic device. The electronic device may be a server. The device includes a processor, a memory, and a communication interface connected via a system bus. The processor of the device is used to provide computing and control capabilities. The memory of the device may be implemented by any type of volatile or non-volatile storage device or a combination thereof, and volatile or non-volatile storage devices include but are not limited to: magnetic disks, optical disks, EEPROMs, EPROMs, SRAMs, ROMs, magnetic memories, flash memories, and PROMs. The memory of the device provides an environment for the operation of the operating system and computer programs stored therein. The communication interface of the device is a network interface, which is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the steps of the simulation scene setting method described in the above embodiment are implemented.

[0140] In another embodiment of the present application, a storage medium is provided, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the simulation scene setting method described in the above embodiment are implemented. The storage medium includes, but is not limited to, ROM, RAM, CD-ROM, magnetic disk, and floppy disk.

[0141] Those skilled in the art will clearly understand that for the sake of convenience and conciseness of description, the division of the above-mentioned functional units and modules is only used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device described in this application is divided into different functional units or modules to complete all or part of the functions described above.

[0142] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms without departing from the purpose of this application and the scope of protection of the claims, all of which are within the protection of this application.

Claims

1. A simulation scene setting method, characterized in that: include: Read the exported target format scenario configuration, obtain the scenario test parameter list, and modify the test parameters in the test parameter list through the script to generate a simulation scenario sequence; The step of modifying the test parameters in the test parameter list by using a script to generate a simulation scenario sequence includes: Build a JavaScript runtime environment; Import the test parameter list of any scenario into the JavaScript runtime environment; Importing the test parameter list of any scenario and the edited script into the script engine, constructing the attribute relationship between the test parameters in the JavaScript runtime environment, and generating a simulation scenario sequence; The test parameters include vehicle test parameters and environmental test parameters; According to the test parameter list of any scenario, an attribute relationship between the test parameters is constructed in the JavaScript runtime environment, including constructing an attribute relationship between the vehicle test parameters and the environment test parameters, including: The self-vehicle test parameters include the self-vehicle speed and the self-vehicle position; the environmental test parameters include the obstacle vehicle speed and the obstacle vehicle position; the attribute relationship between the self-vehicle test parameters and the environmental test parameters is: Self-vehicle speed = a × obstacle vehicle speed, where a is in the range of 1.2≤a≤1.6; Own vehicle position = obstacle vehicle position - relative distance between owing vehicle and obstacle vehicle, wherein the relative distance between owing vehicle and obstacle vehicle = relative direction between owing vehicle and obstacle vehicle × distance between owing vehicle and obstacle vehicle; When the simulation scene sequence is legal, the simulation scene sequence is published to the target scene warehouse.

2. The simulation scene setting method according to claim 1, characterized in that: Before the step of publishing the simulation scene sequence to the target scene warehouse, the following steps are also included: Custom syntax checking scripts; Based on the syntax check script, determining whether the output data format of the simulation scenario sequence conforms to the target format; When the output data format of the simulation scenario sequence conforms to the target format, the simulation scenario sequence is legal.

3. The simulation scene setting method according to claim 2, characterized in that: Before the step of publishing the simulation scene sequence to the target scene warehouse, the following steps are also included: Custom logic test scripts; Based on the logic check script, determining whether the content of the configuration field of the simulation scenario sequence meets the preset conditions; When the content of the configuration field of the simulation scenario sequence meets a preset condition, the simulation scenario sequence is legal.

4. The simulation scene setting method according to claim 1, wherein: The test parameters include at least two different environmental test parameters; According to the test parameter list of any scenario, the attribute relationship between the test parameters is constructed in the JavaScript runtime environment, including: Construct attribute relationships between test parameters in different environments.

5. The simulation scene setting method according to any one of claims 1 to 4, characterized in that: After modifying the test parameters in the test parameter list through the script and generating the simulation scenario sequence, it also includes: According to the simulation scenario sequence, a matrix table is output.

6. A simulation scene setting device, characterized in that: include: Scenario configuration module, used to configure the scene based on the scenario editor; The scenario editing module is used to parse the configuration scenario based on the script editor, obtain the test parameter list of the scenario, and modify the test parameters in the test parameter list through the script to generate a simulation scenario sequence; The step of modifying the test parameters in the test parameter list by using a script to generate a simulation scenario sequence includes: building a JavaScript runtime environment; importing the test parameter list of any scenario into the JavaScript runtime environment; importing the test parameter list of any scenario and the edited script into a script engine, constructing an attribute relationship between the test parameters in the JavaScript runtime environment, and generating a simulation scenario sequence; the test parameters include vehicle test parameters and environmental test parameters; constructing an attribute relationship between the test parameters in the JavaScript runtime environment based on the test parameter list of any scenario, including constructing an attribute relationship between the vehicle test parameters and the environmental test parameters, including: The self-vehicle test parameters include the self-vehicle speed and the self-vehicle position; the environmental test parameters include the obstacle vehicle speed and the obstacle vehicle position; the attribute relationship between the self-vehicle test parameters and the environmental test parameters is: Self-vehicle speed = a × obstacle vehicle speed, where a is in the range of 1.2≤a≤1.6; Own vehicle position = obstacle vehicle position - relative distance between owing vehicle and obstacle vehicle, wherein the relative distance between owing vehicle and obstacle vehicle = relative direction between owing vehicle and obstacle vehicle × distance between owing vehicle and obstacle vehicle; The scene publishing module is used to publish the simulation scene sequence to the target scene warehouse when the simulation scene sequence is legal.

7. The simulation scene setting device according to claim 6, characterized in that: Also includes: The output module is used to output a matrix table according to the simulation scenario sequence.

8. A device, characterized in that The method comprises a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein when the processor executes the computer program, the steps of the simulation scene setting method according to any one of claims 1 to 5 are implemented.

9. A storage medium, characterized in that: The storage medium stores a computer program, which, when executed by a processor, implements the steps of the simulation scene setting method according to any one of claims 1 to 5.

Images