Autonomous driving simulation method and apparatus

Abstract

The present application relates to the field of autonomous driving simulation, and provides an autonomous driving simulation method and an apparatus, achieving improvement of the effectiveness of autonomous driving simulation on the premise of not increasing the scenario design burden. The method comprises: receiving a simulation scenario file comprising non-ego vehicle action information and road condition information; receiving a non-ego vehicle driving strategy; at any moment when an autonomous driving simulation task is executed, on the basis of the non-ego vehicle action information and the current road condition at this moment, obtaining an initial instruction at this moment for indicating a driving behavior of a non-ego vehicle model at this moment under the current road condition; confirming that a driving behavior indicated by an initial instruction at a first moment does not conflict with the non-ego vehicle driving strategy, and executing the initial instruction at the first moment; and confirming that a driving behavior indicated by an initial instruction at a second moment conflicts with the non-ego vehicle driving strategy, generating a first correction instruction on the basis of the non-ego vehicle driving strategy and the current road condition at the second moment so as to correct the driving behavior indicated by the initial instruction at the second moment, and executing the first correction instruction.

Description

An automatic driving simulation method and device

[0001] This application claims priority to Chinese Patent Application No. 202410420201.0, filed on April 7, 2024, entitled "Simulation Method, Device, Computing Device Cluster, and Storage Medium", Chinese Patent Application No. 202411027111.1, filed on July 29, 2024, entitled "An Automatic Driving Simulation Method and Device", the contents of which are incorporated herein by reference in their entirety. TECHNICAL FIELD

[0002] The present application relates to the field of automatic driving simulation, and in particular to an automatic driving simulation method and device. BACKGROUND

[0003] With the development of automatic driving technology, the importance of simulation testing for the safe landing of automatic driving systems is increasingly evident in the development and verification fields.

[0004] Automatic driving simulation is to simulate different traffic scenarios, road conditions, weather and light, and abnormal situations through a virtual environment, to evaluate the function, reaction and decision-making ability of the automatic driving system in various situations. Automatic driving simulation is usually performed on an automatic driving simulation platform, and a simulator in the platform performs automatic driving simulation. The simulator reads an ASAM OpenSCENARIO XML (xosc) file used to define a scenario, and simulates the scenario defined therein. The automatic driving system under test performs driving behavior of a primary vehicle model during the simulation process, and a secondary vehicle driver model in the simulator performs driving behavior of a secondary vehicle model during the simulation process. The secondary vehicle driver model simulates the secondary vehicle model according to the secondary vehicle behavior defined in the xosc file. However, the secondary vehicle behavior defined in the xosc file is usually simple, and there will be a blank period in the simulation process in which the xosc file does not define the secondary vehicle driving behavior. Currently, a simple default driving strategy or random operation is usually performed during the blank period.

[0005] However, the default driving strategy or random operation may not meet the design intent of the scenario, thereby interfering with the automatic driving simulation result, causing the simulation process to not meet the design intent of the scenario, and reducing the effectiveness of the automatic driving simulation. SUMMARY

[0006] The present application provides an automatic driving simulation method and device, which improves the effectiveness of automatic driving simulation without increasing the burden of scenario design.

[0007] To achieve the above object, the embodiments of the present application adopt the following technical solutions:

[0008] In a first aspect, an automatic driving simulation method is provided, which can be applied to an automatic driving simulation platform configured to perform an automatic driving simulation task including at least one secondary vehicle model. The method provided by the present application can include: receiving, from a simulation scenario file configuration interface, a simulation scenario file including secondary vehicle action information and road condition information; receiving, from a secondary vehicle driving strategy configuration interface, a secondary vehicle driving strategy, the secondary vehicle driving strategy being used to describe driving behaviors of the at least one secondary vehicle model in the automatic driving simulation task; at a first time point of performing the automatic driving simulation task, obtaining, based on the secondary vehicle action information and a current road condition at the first time point, a first initial instruction indicating a driving behavior of the secondary vehicle model at the current road condition at the first time point, confirming that the driving behavior indicated by the first initial instruction does not conflict with the secondary vehicle driving strategy, and executing the first initial instruction; at a second time point of performing the automatic driving simulation task, obtaining, based on the secondary vehicle action information and a current road condition at the second time point, a second initial instruction indicating a driving behavior of the secondary vehicle model at the current road condition at the second time point, confirming that the driving behavior indicated by the second initial instruction conflicts with the secondary vehicle driving strategy, generating a first correction instruction based on the secondary vehicle driving strategy and the current road condition at the second time point to correct the driving behavior indicated by the second initial instruction, and executing the first correction instruction.

[0009] In the method provided by the present application, the secondary vehicle driving strategy is input to the automatic driving simulation platform to supplement the secondary vehicle action information defined in the simulation scenario file. On the premise that the driving behaviors defined by the secondary vehicle action information and the secondary vehicle driving strategy do not conflict, the initial instruction determined according to the secondary vehicle action information is executed to control the driving behavior of the secondary vehicle model; on the premise that the driving behaviors defined by the secondary vehicle action information and the secondary vehicle driving strategy conflict, the correction instruction determined according to the secondary vehicle driving strategy is executed to control the driving behavior of the secondary vehicle model. In this way, the secondary vehicle driving strategy that meets the design intention of the scene can be configured according to actual needs to supplement the missing definition of the behavior of the secondary vehicle model in the simulation scenario file, so as to ensure that the automatic driving simulation result is not disturbed and the effectiveness of the automatic driving simulation is ensured. Since the secondary vehicle driving strategy can be input to the automatic driving simulation platform, the secondary vehicle action information in the simulation scenario file can not be required to be too high, and the scene design can not be increased. In addition, the specific content of the secondary vehicle driving strategy can be configured according to actual needs, so that the automatic driving simulation platform can meet the driving needs of different scenes without the need to modify the simulation scenario file too much.

[0010]

[0011] ​The first time and the second time are any time in the process of performing the automatic driving simulation task.

[0012] In a possible implementation, the automatic driving simulation platform can adopt a cloud computing architecture, that is, the automatic driving simulation platform can be a cloud platform.

[0013] In another possible implementation, the secondary vehicle driving strategy can be configured by a user. The user can configure different secondary vehicle driving strategies according to actual needs to meet simulation requirements and avoid interference of the secondary vehicle driving behavior with the design intention of a scene, thereby further reducing the design burden of a scene file.

[0014] In another possible implementation, the method provided in the present application can further include: receiving a secondary vehicle driving strategy input by a user in a configuration interface provided by the automatic driving simulation platform. The automatic driving simulation platform provides an external configuration interface for obtaining a secondary vehicle driving strategy input by a user or another role, thereby improving the flexibility of the automatic driving simulation platform and achieving flexible secondary vehicle driving in the automatic driving simulation process.

[0015] In another possible implementation, the automatic driving simulation platform can be specifically used to perform an automatic driving simulation task including at least one secondary vehicle model and at least one primary vehicle model. Correspondingly, the automatic driving simulation method provided in the present application can further include: receiving a primary vehicle configuration request from a primary vehicle configuration interface, wherein the primary vehicle configuration request is used to determine a primary vehicle algorithm model, and the primary vehicle algorithm model is used to describe the driving behavior of the at least one primary vehicle model in the automatic driving simulation task. After the primary vehicle algorithm model is determined, the performing of the automatic driving simulation task includes: performing the driving behavior of the at least one primary vehicle model at the first time and the second time based on the determined primary vehicle algorithm model. The automatic driving simulation including the primary vehicle model and the secondary vehicle model is achieved.

[0016] The primary vehicle model is an automatic driving system tested by the automatic driving simulation platform.

[0017] In another possible implementation, the method provided by the present application can further include: at a third time point of performing the automatic driving simulation task, confirming that the initial instruction indicating the driving behavior of the secondary vehicle model in the current road condition at the third time point is not obtained based on the secondary vehicle action information and the current road condition at the third time point; generating a second correction instruction based on the secondary vehicle driving strategy and the current road condition at the third time point, and executing the second correction instruction; the second correction instruction is used to indicate the driving behavior of the secondary vehicle model in the current road condition at the third time point. In the case that the secondary vehicle action information does not define the secondary vehicle behavior at the time point, the simulation is performed according to the secondary vehicle driving behavior defined by the secondary vehicle driving strategy, the secondary vehicle driving strategy is supplemented to the secondary vehicle action information, the determined secondary vehicle behavior is ensured to be performed at the time point in the process of performing the automatic driving simulation task, the random operation is replaced, the effectiveness of the automatic driving simulation is improved, and the certainty of the automatic driving simulation result is ensured.

[0018] In another possible implementation, the driving behavior indicated by the initial instruction at the first time point does not conflict with the secondary vehicle driving strategy, and the priority of the driving behavior of the at least one secondary vehicle model defined by the secondary vehicle action information at the first time point is higher than the priority of the driving behavior of the at least one secondary vehicle model defined by the secondary vehicle driving strategy at the first time point. The driving behavior indicated by the initial instruction at the second time point conflicts with the secondary vehicle driving strategy, and the priority of the driving behavior of the at least one secondary vehicle model defined by the secondary vehicle action information at the second time point is lower than the priority of the driving behavior of the at least one secondary vehicle model defined by the secondary vehicle driving strategy at the second time point. The driving behavior of the secondary vehicle model defined by the secondary vehicle action information or the secondary vehicle driving strategy can exist in the case that the scene design intention does not match, and the priority of the driving behavior can be configured. The higher the priority is, the higher the matching degree with the scene design intention is. In the process of performing the automatic driving simulation task, when the plurality of driving behaviors of the secondary vehicle are defined at a time point, the driving behavior with the high priority is executed to control the secondary vehicle, and the effectiveness of the automatic driving simulation and the certainty of the simulation result are ensured as much as possible.

[0019] In another possible implementation, the path planning strategy is used to indicate a priority rule in path planning. The brake speed strategy is used to indicate a brake speed value. The lane changing strategy is used to indicate a lane changing direction. The overtaking strategy is used to indicate a condition for performing an overtaking behavior. The avoidance strategy is used to indicate a condition for performing an avoidance behavior.

[0020] In another possible implementation, the path planning strategy includes any one of the following: nearest distance priority, left priority, or right priority. The overtaking strategy includes that a speed of a front vehicle is less than or equal to a first threshold value. The avoidance strategy includes that a time to collision (TTC) is less than or equal to a second threshold value.

[0021] In another possible implementation, the simulation scenario file can further include side vehicle performance information, the side vehicle performance information being used to indicate side vehicle performance, and the method provided in the application can further include: at a fourth time point of executing the automatic driving simulation task, obtaining initial instructions for the fourth time point based on the side vehicle action information and the current road condition at the fourth time point, the initial instructions being used to indicate driving behaviors of the side vehicle model in the current road condition at the fourth time point; if the side vehicle performance does not support the driving behaviors indicated by the initial instructions at the fourth time point, generating third modified instructions based on the side vehicle driving strategy and the current road condition at the fourth time point, to modify the driving behaviors indicated by the initial instructions at the fourth time point, and executing the third modified instructions. That is, the side vehicle driving strategy is used to replace the side vehicle action information in the simulation scenario file, and the implementability of the simulation scenario file is improved.

[0022] In another possible implementation, the method provided in the application can further include: in response to a preview request sent by a user, executing an automatic driving simulation preview task including at least one vehicle model, where executing the automatic driving simulation preview task specifically includes: executing driving behaviors of the vehicle model at different time points in the automatic driving simulation preview task according to the side vehicle action information and the side vehicle driving strategy. A preview interface is provided, and the preview interface is used to show a simulation process of the automatic driving simulation preview task, the simulation process including the driving behaviors of the vehicle model. The preview function is implemented in the automatic driving simulation platform, the driving behaviors of the side vehicle model are simulated in the preview to simulate all vehicles in the preview scenario, the simulation effect provided by the platform can be previewed before the platform is used, and user experience is improved.

[0023] In another possible implementation, the method provided in the application can further include: providing a task interface, the task interface being used to display driving strategy configuration information, the driving strategy configuration information being used to indicate the side vehicle driving strategy. The side vehicle driving strategy is used to control driving behaviors of at least one side vehicle model in the automatic driving simulation task. The task interface is used for intuitive display, so that the user can conveniently know the side vehicle driving strategy used in the current simulation process, and user experience is improved.

[0024] In another possible implementation, the automatic driving simulation platform can include an interface and a simulator. The simulator is used to implement simulation of a scenario. A host vehicle model (a measured automatic driving system) accesses the simulator through the interface of the simulator, and driving behaviors of the host vehicle model are executed in the simulator. A side vehicle model can be built in the simulator. Alternatively, the side vehicle model can access the simulator through the interface of the simulator to control the side vehicle.

[0025] In another possible implementation, the input and output of the automatic driving simulation platform are data defined in an open simulation interface (OSI) standard of an association of standardization of automation and measuring systems (ASAM); and the simulation scenario file can be an xosc file.

[0026] The secondary vehicle behavior information can be information transmitted by an OSI_TrafficCommand interface defined in the ASAM OSI.

[0027] In a second aspect, an automatic driving simulation device is provided, which is applied to an automatic driving simulation platform used to execute an automatic driving simulation task including at least one secondary vehicle model. The automatic driving simulation device can include a simulation scenario file receiving interface, a secondary vehicle driving strategy configuration interface, and a first simulation unit. The simulation scenario file receiving interface is configured to receive a simulation scenario file including secondary vehicle action information and road condition information, the secondary vehicle action information being used to describe driving behavior of the at least one secondary vehicle model in the automatic driving simulation task, and the road condition information being used to describe a road condition of the automatic driving simulation task.

[0028] The simulation scenario file receiving interface is configured to receive a simulation scenario file including secondary vehicle action information and road condition information, the secondary vehicle action information being used to describe driving behavior of the at least one secondary vehicle model in the automatic driving simulation task, and the road condition information being used to describe a road condition of the automatic driving simulation task.

[0029] The secondary vehicle driving strategy configuration interface is configured to receive a secondary vehicle driving strategy used to describe driving behavior of the at least one secondary vehicle model in the automatic driving simulation task.

[0030] The first simulation unit is configured to, at a first time point of executing the automatic driving simulation task, obtain an initial instruction at the first time point based on the secondary vehicle action information and a current road condition at the first time point, the initial instruction at the first time point being used to indicate driving behavior of the secondary vehicle model in the current road condition at the first time point, and confirm that the driving behavior indicated by the initial instruction at the first time point does not conflict with the secondary vehicle driving strategy, and execute the initial instruction at the first time point.

[0031] The first simulation unit is further configured to, at a second time point of executing the automatic driving simulation task, obtain an initial instruction at the second time point based on the secondary vehicle action information and a current road condition at the second time point, the initial instruction at the second time point being used to indicate driving behavior of the secondary vehicle model in the current road condition at the second time point, confirm that the driving behavior indicated by the initial instruction at the second time point conflicts with the secondary vehicle driving strategy, generate a first correction instruction based on the secondary vehicle driving strategy and the current road condition at the second time point to correct the driving behavior indicated by the initial instruction at the second time point, and execute the first correction instruction.

[0032] It should be noted that the automatic driving simulation device provided in the second aspect is used to implement the automatic driving simulation method provided in the first aspect or any possible implementation manner, and the specific implementation can refer to the first aspect or any possible implementation manner of the first aspect, which will not be described here.

[0033] In a third aspect, a computing device cluster is provided, including at least one computing device, each computing device including a processor and a memory, the processor of the at least one computing device being configured to execute instructions stored in the memory of the at least one computing device to cause the computing device cluster to perform operations of the method described in the first aspect or any possible implementation manner.

[0034] In a fourth aspect, a computer program product including instructions that, when executed by a computing device cluster, cause the computing device cluster to perform operations of the method described in the first aspect or any possible implementation manner.

[0035] In a fifth aspect, a computer-readable storage medium includes computer program instructions that, when executed by a computing device cluster, cause the computing device cluster to perform operations of the method described in the first aspect or any possible implementation manner.

[0036] It should be noted that any of the various possible implementation manners of the above aspects can be combined, provided that the schemes are not contradictory. BRIEF DESCRIPTION OF DRAWINGS

[0037] FIG. 1 is a schematic diagram of an architecture of an automatic driving simulation system according to an embodiment of the present application;

[0038] FIG. 2 is a schematic diagram of an automatic driving simulation scenario according to an embodiment of the present application;

[0039] FIG. 3 is a schematic diagram of another automatic driving simulation scenario according to an embodiment of the present application;

[0040] FIG. 4 is a schematic diagram of a flow of an automatic driving simulation method according to an embodiment of the present application;

[0041] FIG. 5 is a schematic diagram of a flow of another automatic driving simulation method according to an embodiment of the present application;

[0042] FIG. 6 is a schematic diagram of a configuration interface of a secondary vehicle driving strategy according to an embodiment of the present application;

[0043] FIG. 7 is a schematic diagram of an editing interface according to an embodiment of the present application;

[0044] FIG. 8 is a schematic diagram of another configuration interface of a secondary vehicle driving strategy according to an embodiment of the present application;

[0045] FIG. 9 is a schematic diagram of an input and output scene of a secondary vehicle model according to an embodiment of the present application;

[0046] FIG. 10 is a schematic diagram of a preview interface of an automatic driving simulation platform according to an embodiment of the present application;

[0047] FIG. 11 is a schematic diagram of a simulation interface of an automatic driving simulation platform according to an embodiment of the present application;

[0048] FIG. 12 is a schematic diagram of a structure of an automatic driving simulation device according to an embodiment of the present application;

[0049] FIG. 13 is a schematic diagram of a structure of a computing device according to an embodiment of the present application;

[0050] FIG. 14 is a schematic diagram of a structure of a computing device cluster according to an embodiment of the present application;

[0051] FIG. 15 is a schematic diagram of a structure of another computing device cluster according to an embodiment of the present application. DETAILED DESCRIPTION

[0052] In the embodiments of the present application, in order to clearly describe the technical solutions of the embodiments of the present application, the same items or similar items with basically the same functions and effects are distinguished by using "first", "second", etc. The skilled in the art can understand that "first", "second", etc. do not limit the quantity and execution order, and "first", "second", etc. also do not limit the difference.

[0053] In the embodiments of the present application, the words "exemplary" or "for example" are used to mean serving as an example, instance, or illustration. Any embodiment or design presented as "exemplary" or "for example" in the embodiments of the present application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of "exemplary" or "for example" is intended to present concepts in a concrete manner, and to facilitate understanding.

[0054] In the embodiments of the present application, at least one can also be described as one or more, and the plurality can be two, three, four, or more, which is not limited by the present application.

[0055] In addition, the network architecture and scenarios described in the embodiments of the present application are used to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. The skilled in the art can know that, with the evolution of network architecture and the appearance of new business scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0056] For ease of understanding, the terms involved in the embodiments of the present application are first explained.

[0057] Autonomous driving simulation: It is to move all the contents involved in autonomous driving to a virtual environment to simulate the entire process of autonomous driving. The autonomous driving simulation system includes a scene module that reacts to actual traffic characteristics, a perception, decision, planning, and control module of the autonomous driving system, and a vehicle dynamics module that reacts to the execution result. Simulation testing realizes closed-loop simulation testing of autonomous driving perception, decision planning, control, and other algorithms in the constructed virtual scene, meeting the requirements of autonomous driving testing. The OpenDRIVE, OpenSCENARIO, OSI, and other standards drafted by ASAM are important cornerstones in the field of autonomous driving simulation system integration, testing, and evaluation, and have received widespread attention worldwide. They have gradually become the unified standard for data formats used by various vehicle manufacturers, suppliers, and simulation tool vendors.

[0058] xosc file: also known as simulation scenario file, or simply scenario file, with.xosc as the file name suffix. It is a file that needs to be read by the simulator before each run, which contains dynamic information (such as road condition information) for this simulation. The xosc file is a data format defined by OpenSCENARIO, mainly describing dynamic information in autonomous driving simulation testing. For vehicle driving, the scenario is to describe when and where the driving vehicle is driving on the road under what weather conditions, and may encounter various other traffic participants (secondary vehicles, people) or dynamic changes of roadside facilities.

[0059] The xosc file is the basis of autonomous driving simulation. In the field of autonomous driving simulation, the simulator of the autonomous driving simulation platform reads the xosc file and simulates the road conditions defined in it. The purpose of simulation is to hope that the ego vehicle (or can be called the host vehicle Ego) controlled by the external algorithm (the autonomous driving system being tested, which can be called the host vehicle model) can complete the preset driving purpose under the interference of the secondary vehicle (in the autonomous driving simulation task, the vehicle other than the host vehicle). Usually, the driver model (a kind of secondary vehicle model, which can be built-in in the simulator) performs the driving behavior defined by the secondary vehicle behavior information in the xosc file to complete the driving simulation of the secondary vehicle. However, since the secondary vehicle behavior defined in the xosc file is usually simple, there will be a blank period of time in the simulation process when the xosc file does not define the secondary vehicle driving behavior. In the blank period of time, the driver model performs a simple default driving strategy or a driving behavior defined by random operation to simulate the secondary vehicle.

[0060] As described above, the purpose of the simulation is to complete the preset driving purpose, but the default driving strategy or random operation may interfere with the design intention of the simulation scene and the result of the simulation, resulting in that the automatic driving simulation process does not meet the design intention of the scene, the result of the simulation cannot achieve the expected effect, and the effectiveness of the automatic driving simulation is reduced. Therefore, in order to ensure the effectiveness of the automatic driving simulation, higher requirements are inevitably put forward for the simulation scene design, and it is hoped that the situation of undefined secondary vehicle driving behavior in the simulation scene file is reduced as much as possible, but this increases the burden of scene design.

[0061] Based on this, the application provides an automatic driving simulation method. An automatic driving simulation platform provides an interface for configuring a secondary vehicle driving strategy, and the secondary vehicle driving strategy can be configured as needed through the interface. The secondary vehicle driving strategy is used to supplement the secondary vehicle behavior information in the simulation scene file. On the premise that the driving behaviors defined by the secondary vehicle action information and the secondary vehicle driving strategy do not conflict, the driving behavior of the secondary vehicle model is executed according to the initial instruction determined according to the secondary vehicle action information; on the premise that the driving behaviors defined by the secondary vehicle action information and the secondary vehicle driving strategy conflict, the driving behavior of the secondary vehicle model is executed according to the correction instruction determined according to the secondary vehicle driving strategy. In this way, the secondary vehicle driving strategy that meets the design intention of the scene can be configured according to actual needs to supplement the lack of definition of the secondary vehicle model behavior in the simulation scene file, so as to ensure that the automatic driving simulation result is not disturbed and the effectiveness of the automatic driving simulation is ensured. Since the secondary vehicle driving strategy can be input to the automatic driving simulation platform, the secondary vehicle action information in the simulation scene file can not be required too high, and the scene design can not be increased. In addition, the specific content of the secondary vehicle driving strategy can be configured according to actual needs, so that the automatic driving simulation platform can meet the driving needs of different scenes without the need to modify the simulation scene file too much.

[0062] The embodiments of the application will be described in detail below with reference to the accompanying drawings.

[0063] The scheme provided by the application can be applied to the automatic driving simulation system shown in FIG. 1. As shown in FIG. 1, the automatic driving simulation system includes a simulator 101, a primary vehicle model 102, a secondary vehicle model 103, a simulation scene file configuration interface 104, and a secondary vehicle driving strategy configuration interface 105.

[0064] The automatic driving simulation system shown in FIG. 1 is used to simulate and test the ability of the primary vehicle model 102 to control the vehicle in a virtual environment.

[0065] As shown in FIG. 1, the simulator 101, the secondary vehicle model 103, the simulation scenario file configuration interface 104, and the secondary vehicle driving strategy configuration interface 105 constitute an automatic driving simulation platform, and the host vehicle model 102 is connected to the simulator 101 through an interface provided by the platform, and the simulation capability of the automatic driving simulation platform is used to test the capability of the host vehicle model 102 to control a vehicle.

[0066] The host vehicle model 102 can be understood as an automatic driving system to be tested by the automatic driving simulation platform, and the secondary vehicle model 103 can be understood as a model for performing a driving behavior of a secondary vehicle, which can be generally referred to as a driver model.

[0067] The simulator 101 is configured to perform an automatic driving simulation task including at least one secondary vehicle model 103 and at least one host vehicle model 102. When performing the automatic driving simulation task, the automatic driving simulation system reads a simulation scenario file (for example, an xosc file) and a map file (for example, an xodr file, an OpenDRIVE format uses an extensible markup language (XML) with a file extension of xodr as a basis for describing a road network) through the simulation scenario file configuration interface 104, simulates a scenario, and obtains a virtual scenario of a driving vehicle.

[0068] The host vehicle model 102 is connected to the simulator 101 through an interface (which can be understood as a host vehicle configuration interface, not shown in FIG. 1), controls the host vehicle in the virtual scenario simulated by the simulator 101, and performs a driving behavior of the host vehicle model 102.

[0069] The secondary vehicle model 103 is configured to control a secondary vehicle in the virtual scenario simulated by the simulator 101, and perform a driving behavior of the secondary vehicle model. The secondary vehicle model 103 can be deployed inside the simulator 101 (i.e., built-in the simulator 101). Alternatively, the secondary vehicle model 103 can be independently deployed outside the simulator 101, and the secondary vehicle model 103 is connected to the simulator 101 through an interface provided by the simulator 101, controls the secondary vehicle in the virtual scenario simulated by the simulator 101, and performs a driving behavior of the secondary vehicle model 103. The embodiments of the present application do not limit the deployment relationship between the secondary vehicle model 103 and the simulator 101. In FIG. 1, the secondary vehicle model 103 is only shown as being deployed inside the simulator 101, which is only an example and does not constitute a specific limitation.

[0070] For example, in a scenario where the secondary vehicle model 103 is independently deployed outside the simulator 101, the secondary vehicle model 103 and the simulator 101 can be designed by different providers.

[0071] Further, the side car driving strategy configuration interface 105 is configured to obtain an input side car driving strategy, and the side car model 103 can determine and execute the driving behavior of the side car model 103 in the autonomous driving simulation task according to the side car driving strategy and the side car action information in the simulation scenario file. The specific implementation of executing the driving behavior of the side car model 103 can refer to the process of executing the driving behavior of the side car model in the method embodiment described below.

[0072] For example, the side car model 103 can be used in a back-end server environment to execute the driving behavior of the side car model in the process of executing the autonomous driving simulation task. As shown in the autonomous driving simulation scenario in FIG. 2, according to the simulation scenario file, the simulation scenario includes a host car (Ego in FIG. 2) and two side cars (vehicle 1 and vehicle 0 in FIG. 2). The host car model 102 (Algorithm) controls the host car to execute the driving behavior of the host car model 102, and the side car model 103 controls the vehicle 1 and the vehicle 0 to execute the driving behavior of the side car model 103. Then, the simulator 101 outputs a traffic state file meeting the OSI standard, which is used to record the execution process of the autonomous driving simulation task.

[0073] Further, the architecture of the autonomous driving simulation system can also provide a preview function for executing an autonomous driving simulation preview task, which is used to simulate the execution of the autonomous driving simulation task before the autonomous driving system is connected to display the content of the simulation scenario file. The autonomous driving simulation preview task includes at least one side car model to control all vehicles in the preview scenario (including the host car controlled by the host car model in the autonomous driving simulation task and the side car controlled by the side car model). The preview scenario is a front-end scenario. The simulator 101 reads the simulation scenario file through the simulation scenario file configuration interface 104 to build a virtual scenario for preview, which includes at least one vehicle. The side car model 103 communicates with the simulator 101 to control all vehicles in the virtual scenario to execute the driving behavior of the side car model 103 and simulate the driving process of the vehicle. Specifically, the side car model 103 can determine and execute the driving behavior of the side car model 103 in the autonomous driving simulation task according to the side car driving strategy and the side car action information in the simulation scenario file. Finally, the simulation process is presented on the preview interface.

[0074] Exemplarily, the secondary vehicle model 103 can be used in a front-end previewer environment, in which the secondary vehicle model 103 is used to control all vehicles to perform the driving behavior of the secondary vehicle model 103 in the process of performing an autonomous driving simulation preview task. As shown in the autonomous driving simulation scenario in FIG. 3, the virtual scene constructed by reading the simulation scenario file includes multiple vehicles (Ego, vehicle 1 and vehicle 0 in FIG. 3). The secondary vehicle model 103 is responsible for controlling all vehicles (Ego, vehicle 1 and vehicle 0) in the preview scene to perform the driving behavior of the secondary vehicle model 103 to perform the autonomous driving simulation preview task. Then, a traffic state file meeting the OSI standard is output, which indicates the execution process of the simulation preview task. The user can be presented with the execution process of the simulation preview task indicated by the traffic state file.

[0075] Further, the autonomous driving simulation platform in the autonomous driving simulation system shown in FIG. 1 can be deployed in the form of a cloud platform in a cloud manner, of course, it can also be deployed locally or in other locations, and the embodiments of the present application do not limit the deployment manner of the autonomous driving simulation platform.

[0076] Exemplarily, the primary vehicle model 102 in the autonomous driving simulation system described above can run in a desktop system of a cloud machine when accessing the simulator 101 to perform the driving behavior in the autonomous driving simulation task, or it can also run in the local device of the user.

[0077] Exemplarily, the primary vehicle model 102 in the autonomous driving simulation system described above can run in a container and have multiple copies when accessing the simulator to perform the driving behavior in the autonomous driving simulation task in batches (for example, concurrently performing multiple autonomous driving simulation tasks).

[0078] In one aspect, the embodiments of the present application provide an autonomous driving simulation method, which is applied to an autonomous driving simulation platform. The autonomous driving simulation platform can be the autonomous driving simulation platform in the autonomous driving simulation system shown in FIG. 1.

[0079] As shown in FIG. 4, the vehicle driving method provided by the embodiments of the present application can include:

[0080] S401, receiving a simulation scenario file from a simulation scenario file configuration interface.

[0081] The simulation scenario file is used to describe dynamic information in a simulation scenario. Exemplarily, the simulation scenario file can include secondary vehicle action information and road condition information. Exemplarily, the simulation scenario file can be an xosc file.

[0082] Specifically, the sub-vehicle action information is used to describe the driving behavior of the at least one sub-vehicle model in the automatic driving simulation task. The driving behavior can be understood as a specific operation when driving a vehicle. The specific content of the sub-vehicle action information is not limited by the embodiments of the present application, and can be configured according to the content defined in the ASAM standard.

[0083] The road condition information is used to describe the road condition of the automatic driving simulation task.

[0084] As a possible implementation manner, the road condition information can also be used to describe dynamic information such as weather, pedestrians, and signal lights when performing the automatic driving simulation task. Of course, the specific content of the road condition information is not limited by the embodiments of the present application, and can be configured according to the content defined in the ASAM standard.

[0085] S402, receiving a sub-vehicle driving strategy from a sub-vehicle driving strategy configuration interface, the sub-vehicle driving strategy being used to describe the driving behavior of the at least one sub-vehicle model in the automatic driving simulation task.

[0086] The content of the sub-vehicle driving strategy can be configured according to actual needs, and the embodiments of the present application are not limited thereto.

[0087] Specifically, the sub-vehicle driving strategy configuration interface is used for the outside world (user or other role) to configure the sub-vehicle driving strategy to the automatic driving simulation platform.

[0088] Further, the sub-vehicle driving strategy can have initial default content, which can be configured according to actual needs. When the sub-vehicle driving strategy is received from the sub-vehicle driving strategy configuration interface in S402, the received sub-vehicle driving strategy can be used to replace the original internally stored sub-vehicle driving strategy, so that the latest sub-vehicle driving strategy can be used in subsequent simulation. The process of replacement is not limited by the embodiments of the present application.

[0089] Exemplarily, the sub-vehicle driving strategy can include one or more of the following strategies: path planning strategy, brake speed strategy, lane changing strategy, overtaking strategy, or avoidance strategy.

[0090] The path planning strategy is used to indicate the priority rule when planning the path. Exemplarily, the path planning strategy can include any of the following: nearest distance priority, left priority, or right priority.

[0091] The brake speed strategy is used to indicate the brake speed value.

[0092] The lane changing strategy is used to indicate the lane changing direction.

[0093] The overtaking strategy is used to indicate the condition for performing the overtaking behavior. Exemplarily, the overtaking strategy includes that the speed of the front vehicle is less than or equal to a first threshold value. The value of the first threshold value can be configured according to actual needs, and the embodiments of the present application are not limited thereto.

[0094] The avoidance strategy is used to indicate the condition of performing the avoidance behavior. For example, the avoidance strategy includes that the TTC is less than or equal to a second threshold value. The second threshold value can be configured according to actual needs, and embodiments of the present application are not limited thereto.

[0095] For example, Table 1 shows the specific content of several secondary vehicle driving strategies. In Table 1, an option is a set of secondary vehicle driving strategies, and the secondary vehicle driving strategies received by the automatic driving simulation platform can be a column of content in Table 1.

[0096] Table 1

[0097] It should be noted that Table 1 is only an example of secondary vehicle driving strategies in the form of a table, and is not a specific limitation on the storage form and content of the secondary vehicle driving strategies.

[0098] For example, in the case of the avoidance strategy, the driving behavior defined by the secondary vehicle action information in the xosc file is often very specific, such as accelerating to 10 m / s, driving to a certain point, etc. However, from the actual traffic scene, the driving behavior of the secondary vehicle model often needs to avoid actively colliding with the primary vehicle model or other secondary vehicle models, and the xosc file description is difficult to clearly describe the avoidance. Therefore, the avoidance strategy in the secondary vehicle driving strategy described in the present application can well make up for the lack of description of the avoidance driving behavior in the xosc file. In addition, the avoidance behavior is complex, and different scenarios may also require different avoidance strategies. The amount of TTC will determine whether the driver model is aggressive or moderate. The configurable secondary vehicle driving strategy provided by the present application can well implement different avoidance strategies and effectively supplement the content of the xosc file, reducing the burden of scene design.

[0099] Of course, other strategies in the secondary vehicle driving strategy have a similar effect of supplementing the simulation scene file as the avoidance strategy described above, which will not be described here.

[0100] After receiving the secondary vehicle driving strategy in S402, the automatic driving simulation platform can combine the secondary vehicle action information in the simulation scene file and the secondary vehicle driving strategy to perform the automatic driving simulation task to execute the driving behavior of the secondary vehicle model in the automatic driving simulation task. Specifically, according to the content of the driving behavior defined by the secondary vehicle action information and the secondary vehicle driving strategy, it is determined how to execute the driving behavior of the secondary vehicle model in the automatic driving simulation task. The specific process can be shown in S403 or S404.

[0101] S403, at the first time point of executing the automatic driving simulation task, based on the secondary vehicle action information and the current road condition at the first time point, obtaining an initial instruction at the first time point; confirming that the driving behavior indicated by the initial instruction at the first time point does not conflict with the secondary vehicle driving strategy, and executing the initial instruction at the first time point.

[0102] The first time point is any time point of executing the automatic driving simulation task.

[0103] The initial instruction at the first time point is used to indicate the driving behavior of the secondary vehicle model under the current road condition at the first time point. Specifically, the initial instruction at the first time point is used to indicate the driving behavior of the secondary vehicle model described by the secondary vehicle action information under the current road condition at the first time point. Executing the first instruction is equivalent to executing the driving behavior of the secondary vehicle model according to the description of the secondary vehicle action information.

[0104] The driving behavior indicated by the initial instruction at the first time point does not conflict with the secondary vehicle driving strategy, which can be understood as that the driving behavior indicated by the initial instruction at the first time point does not conflict with the driving behavior defined by the secondary vehicle driving strategy at the first time point.

[0105] In a possible implementation, the driving behavior indicated by the initial instruction at the first time point does not conflict with the driving behavior defined by the secondary vehicle driving strategy at the first time point, which can be understood as that the driving behavior indicated by the initial instruction at the first time point is within the range of the driving behavior defined by the secondary vehicle driving strategy at the first time point, or meets the requirements of the driving behavior defined by the secondary vehicle driving strategy at the first time point.

[0106] For example, assuming that the driving behavior described by the secondary vehicle action information at a certain time point is to go to position A according to navigation, and the driving behavior defined by the secondary vehicle driving strategy at the first time point plans a path according to the nearest principle, then the two do not conflict.

[0107] In another possible implementation, the driving behavior indicated by the initial instruction at the first time point does not conflict with the driving behavior defined by the secondary vehicle driving strategy at the first time point, which includes that the secondary vehicle driving strategy does not define any driving behavior at the first time point.

[0108] In a possible implementation, the priority of the driving behavior can be used to evaluate whether the driving behavior conflicts. The driving behavior does not conflict with the driving behavior with lower priority, and conflicts with the driving behavior with higher priority.

[0109] For example, the priority of the driving behavior of at least one secondary vehicle model defined by the secondary vehicle action information at the first time point is higher than the priority of the driving behavior of at least one secondary vehicle model defined by the secondary vehicle driving strategy at the first time point.

[0110] Specifically, generating an initial instruction based on the auxiliary vehicle's action information and road condition information, or generating a revised instruction based on the auxiliary vehicle's driving strategy and path information, can be a process of converting an intention into a driving instruction. The specific implementation of this conversion process is not limited in this embodiment of the present application. For example, the instruction generation process can be completed with reference to the description in the relevant ASAM standards.

[0111] S404. At the second moment of executing the autonomous driving simulation task, an initial instruction at the second moment is obtained based on the auxiliary vehicle action information and the current road condition at the second moment; it is confirmed that the driving behavior indicated by the initial instruction at the second moment conflicts with the auxiliary vehicle driving strategy, and a first correction instruction is generated based on the auxiliary vehicle driving strategy and the current road condition at the second moment to correct the driving behavior indicated by the initial instruction at the second moment, and the first correction instruction is executed.

[0112] The second moment is any moment other than the first moment during the execution of the autonomous driving simulation task.

[0113] The initial instruction at the second moment is used to instruct the driving behavior of the auxiliary vehicle model under the current road conditions at the second moment. Specifically, the initial instruction at the second moment is used to instruct the driving behavior of the auxiliary vehicle model under the current road conditions at the second moment described by the auxiliary vehicle action information.

[0114] Among them, the driving behavior indicated by the initial instruction at the second moment conflicts with the driving strategy of the auxiliary vehicle, which can be understood as the driving behavior indicated by the initial instruction at the second moment conflicts with the driving behavior defined by the driving strategy of the auxiliary vehicle at the second moment.

[0115] In one possible implementation, the driving behavior indicated by the initial instruction at the second moment conflicts with the driving behavior defined by the secondary vehicle driving strategy at the second moment. This can be understood as: the driving behavior indicated by the initial instruction at the first moment does not fall within the scope of the driving behavior defined by the secondary vehicle driving strategy at the second moment, or does not meet the requirements of the driving behavior defined by the secondary vehicle driving strategy at the second moment, or contradicts the driving behavior defined by the secondary vehicle driving strategy at the second moment.

[0116] For example, suppose that at a certain moment, the auxiliary vehicle model is about to collide with the vehicle in front. The driving behavior described by the auxiliary vehicle action information at this moment is constant speed driving, while the auxiliary vehicle driving strategy is to decelerate when a collision occurs within 10 seconds. The driving behavior defined by the auxiliary vehicle driving strategy at this time is deceleration, and constant speed driving conflicts with deceleration.

[0117] In a possible implementation, the priority of the driving behavior of at least one auxiliary vehicle model defined by the auxiliary vehicle action information at the second moment is lower than the driving behavior of at least one auxiliary vehicle model defined by the auxiliary vehicle driving strategy at the second moment.

[0118] In the scheme provided in the application, the secondary vehicle driving strategy is input to the automatic driving simulation platform to supplement the secondary vehicle action information defined in the simulation scenario file. On the premise that the driving behaviors defined by the secondary vehicle action information and the secondary vehicle driving strategy do not conflict, the initial instruction determined according to the secondary vehicle action information is executed to simulate the secondary vehicle model; on the premise that the driving behaviors defined by the secondary vehicle action information and the secondary vehicle driving strategy conflict, the correction instruction determined according to the secondary vehicle driving strategy is executed to simulate the secondary vehicle model. In this way, the secondary vehicle driving strategy that meets the scene design intention can be configured according to actual needs to supplement the missing definition of the secondary vehicle model behavior in the simulation scenario file, so as to ensure that the automatic driving simulation result is not disturbed and the effectiveness of the automatic driving simulation is ensured. Since the secondary vehicle driving strategy can be input to the automatic driving simulation platform, the secondary vehicle action information in the simulation scenario file can not be required too high, and the scene design can not be increased. In addition, the specific content of the secondary vehicle driving strategy can be configured according to actual needs, so that the automatic driving simulation platform can meet the driving needs of different scenes without too many modifications to the simulation scenario file.

[0119] Further, as shown in FIG. 5, the automatic driving simulation method provided by the embodiment of the application can further include S405.

[0120] S405, at a third time point of executing the automatic driving simulation task, confirming that the initial instruction indicating the driving behavior of the secondary vehicle model under the current road condition at the third time point is not obtained based on the secondary vehicle action information and the current road condition at the third time point; generating a second correction instruction based on the secondary vehicle driving strategy and the current road condition at the third time point, and executing the second correction instruction.

[0121] The second correction instruction is used to instruct the driving behavior of the secondary vehicle model under the current road condition at the third time point. The third time point is any time point in the process of executing the automatic driving simulation task, except the first time point and the second time point.

[0122] Specifically, in S405, at the time point when the secondary vehicle action definition does not define the driving behavior, the secondary vehicle model is controlled according to the driving behavior defined by the secondary vehicle driving strategy.

[0123] For example, it is assumed that the current time point of the secondary vehicle model controlling the vehicle 1 is driving at a speed of 30 km / h to the B position, the front vehicle speed is 10 km / h, and there is a risk of collision, but the driving behavior at the current time point is not defined in the secondary vehicle action information, but the overtaking strategy of the secondary vehicle driving strategy defines that overtaking is performed when the front vehicle speed is less than 15 km / h. At this time, the correction instruction for overtaking can be generated and executed according to the secondary vehicle driving strategy and the current road condition, and overtaking is performed to avoid interference with the front vehicle.

[0124] Further, the processes of S403, S404 or S405 can be specifically executed by the vice vehicle model in the automatic driving simulation platform. The vice vehicle model executes the driving behavior of the vice vehicle model in the automatic driving simulation task at different time according to the processes of S403, S404 or S405 based on the vice vehicle action information and the vice vehicle driving strategy, and controls the vice vehicle.

[0125] Further, the automatic driving simulation platform is specifically used for executing the automatic driving simulation task including the at least one vice vehicle model and the at least one main vehicle model, that is, the automatic driving simulation platform is also used for simulating the driving process of the main vehicle model controlled by the automatic driving system connected to the automatic driving simulation platform. As shown in FIG. 5, the automatic driving simulation method provided by the embodiments of the present application can further include the process of S406.

[0126] S406, receiving a main vehicle configuration request from a main vehicle configuration interface, the main vehicle configuration request being used for determining a main vehicle algorithm model.

[0127] The main vehicle algorithm model is used for describing the driving behavior of the at least one main vehicle model in the automatic driving simulation task.

[0128] In a possible implementation manner, the main vehicle algorithm model can be imported from a model library, or input to the main vehicle configuration interface in an application programming interface (API) mode.

[0129] The above execution of the automatic driving simulation task includes: executing the driving behavior of the at least one main vehicle model at the first time and the second time based on the main vehicle algorithm model. For the process of executing the driving behavior of the main vehicle model, the embodiments of the present application do not limit and elaborate on the protocol configuration of the automatic driving simulation.

[0130] Further, the simulation scene file can further include vice vehicle performance information used for indicating the vice vehicle performance. As shown in FIG. 5, the automatic driving simulation method provided by the embodiments of the present application can further include the process of S407.

[0131] S407, obtaining an initial instruction at a fourth time in the execution of the automatic driving simulation task based on the vice vehicle action information and the current road condition at the fourth time. If the vice vehicle performance does not support the driving behavior indicated by the initial instruction at the fourth time, generating a third correction instruction based on the vice vehicle driving strategy and the current road condition at the fourth time to correct the driving behavior indicated by the initial instruction at the fourth time, and executing the third correction instruction.

[0132] The initial instruction of the fourth moment is used to indicate the driving behavior of the secondary vehicle model in the current road condition at the fourth moment. The fourth moment is any moment in the process of executing the automatic driving simulation task, except the first moment, the second moment, and the third moment.

[0133] For example, assuming that the brake speed of the secondary vehicle described in the secondary vehicle action information in the simulation scene file at a certain moment is -6 (m / s 2 ), the brake speed defined by the secondary vehicle driving strategy at the moment is -2 (m / s 2 ), but the performance parameter of the secondary vehicle determines that the brake speed of the secondary vehicle can at most be -2 (m / s 2 ), that is, the performance of the vehicle does not support the driving behavior described in the secondary vehicle action information, at this time, a correction instruction can be generated according to the secondary vehicle driving strategy, the correction instruction is executed, and the driving is simulated according to the brake speed of -2 (m / s 2 ), so as to ensure the safety of the vehicle driving.

[0134] In a possible implementation manner, the above-mentioned secondary vehicle driving strategy can be configured by a user.

[0135] For example, the automatic driving simulation platform can provide a configuration interface, the user customizes the secondary vehicle driving strategy in the configuration interface, and the secondary vehicle driving strategy input on the configuration interface is received by the secondary vehicle driving strategy configuration interface of the automatic driving simulation.

[0136] The configuration interface can be a web version or a client version, and the embodiments of the present application do not limit this.

[0137] For example, FIG. 6 illustrates a configuration interface of a secondary vehicle driving strategy. As shown in FIG. 6, in the custom secondary vehicle driving strategy configuration area in the configuration interface, the configured secondary vehicle driving strategy in the automatic driving simulation platform is displayed, and the user can select each secondary vehicle driving strategy operation option to reconfigure the content of the configured secondary vehicle driving strategy. Alternatively, the user can select the “add” option to add a new secondary vehicle driving strategy.

[0138] In the configuration interface illustrated in FIG. 6, when the user clicks the “edit” option corresponding to a certain secondary vehicle driving strategy, the editing interface illustrated in FIG. 7 can be entered. In the editing interface illustrated in FIG. 7, the specific content of the secondary vehicle driving strategy can be adjusted, for example, by manually inputting or selecting by a drop-down menu. In the editing interface illustrated in FIG. 7, the entire secondary vehicle driving strategy can be deleted. Finally, “save” is clicked to make the operation in the interface illustrated in FIG. 7 effective to the automatic driving simulation platform, or “cancel” is clicked to cancel the operation in the interface illustrated in FIG. 7.

[0139] For example, FIG. 8 schematically shows a configuration interface of another side car driving strategy, which provides a way of importing a file to input the side car driving strategy. In the interface shown in FIG. 8, the user clicks the "Import" option, selects a target file recording the side car driving strategy to be input, and imports the target file into the automated driving simulation platform. The automated driving simulation platform identifies the content in the target file to obtain the side car driving strategy input by the user. It should be noted that the format of recording the side car driving strategy in the target file is a format supported by the automated driving simulation platform.

[0140] Of course, the forms of the configuration interfaces of the side car driving strategies in FIGS. 6, 7 and 8 are examples, and the content and form of the configuration interface can be configured according to actual needs, which is not limited in the embodiments of the present application.

[0141] Further, the input of the side car model can be side car action information for describing the driving behavior of the virtual vehicle and environment information for describing the environment in the scene. The side car action information includes action information or a scene file. The output of the side car model is state information for describing the traffic update state.

[0142] For example, as shown in FIG. 9, the input and output of the side car model can be data defined in the ASAM OSI standard. The side car action information can be information transmitted by the OSI_TrafficCommand interface defined in the ASAM OSI, the environment information can be information transmitted by the OSI_GroundTruth interface defined in the ASAM OSI, and the state information can be information transmitted by the OSI_TrafficUpdate interface defined in the ASAM OSI.

[0143] Further, the automated driving simulation platform can also provide a preview function for showing the user the process of simulating based on the scene and showing the road condition information described in the simulation scene file.

[0144] For example, the automated driving simulation platform can provide the preview function in the form of a Previewer. The Previewer can read the simulation scene file, perform an automated driving simulation task including at least one vehicle, execute the driving behavior of the side car model, control all vehicles, finally generate an OSI data stream, convert the OSI data stream into a 3D dynamic interactive scene, and present the scene to the front end to show the road condition information described in the xosc file.

[0145] For example, as shown in FIG. 5, the automated driving simulation method provided by the embodiments of the present application can further include the processes of S408 and S409.

[0146] S408, in response to the preview request sent by the user, performing an autonomous driving simulation preview task including at least one secondary vehicle model.

[0147] The performing of the autonomous driving simulation preview task specifically includes: performing driving behaviors of the secondary vehicle model at different time points in the autonomous driving simulation preview task according to the secondary vehicle action information and the secondary vehicle driving strategy.

[0148] For example, in S408, the performing of the autonomous driving simulation preview task can be performed according to the secondary vehicle action information and the secondary vehicle driving strategy at different time points in the autonomous driving simulation preview task as described in S403, S404 and S405.

[0149] S409, providing a preview interface for showing a simulation process of the autonomous driving simulation preview task.

[0150] The simulation process can include driving behaviors of the secondary vehicle model. The simulation process can also include road condition information.

[0151] For example, FIG. 10 shows a preview interface of an autonomous driving simulation platform. As shown in FIG. 10, the preview interface includes a preview result display area, in which the simulation process of the autonomous driving simulation preview task is displayed in a 3D manner. The user can repeatedly play the content of the preview result display area through the “playback” option.

[0152] In another possible implementation, the method provided by the present application can further include: providing a task interface for displaying driving strategy configuration information, the driving strategy configuration information being used to indicate the secondary vehicle driving strategy. The secondary vehicle driving strategy is used to control the driving behaviors of the at least one secondary vehicle model in the autonomous driving simulation task.

[0153] In a possible implementation, the task interface can be a simulation interface of the autonomous driving simulation platform.

[0154] FIG. 11 shows a simulation interface of an autonomous driving simulation platform. As shown in FIG. 11, the simulation interface includes a simulation parameter area and a simulation result area.

[0155] The simulation parameter area displays simulation-related parameter content, such as the name of the simulation scenario file, the version of the simulation scenario file, the update time of the simulation scenario file, and the content of the secondary vehicle driving strategy.

[0156] The simulation result area displays a simulation video link and simulation result information. Clicking the simulation video link is used to enter an interface for displaying the simulation process. The simulation result information is used to display the result of the simulation, which can include the score of the simulation, whether the simulation is successful, detailed information of the simulation, or other information.

[0157] In another possible implementation, the task interface can be a preview interface of the autonomous driving simulation platform. The preview interface shown in FIG. 10 demonstrates the content of the secondary vehicle driving strategy.

[0158] The above describes the scheme provided by the embodiments of the present application mainly from the perspective of the working principle of the computing device. It can be understood that, in order to implement the above functions, the autonomous driving simulation platform comprises a hardware structure and / or a software module for executing each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of the examples described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is implemented in hardware or computer software driven hardware depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0159] The embodiments of the present application can divide the functional modules of the autonomous driving simulation device of the autonomous driving simulation platform for executing the scheme of the present application according to the above method examples. For example, each functional module can be divided according to each function, or two or more functions can be integrated in one processing module. The above integrated module can be implemented in the form of hardware or software functional module. It should be noted that the division of the modules in the embodiments of the present application is illustrative, and is only a logical functional division. There can be another division manner in actual implementation.

[0160] The present application also provides an autonomous driving simulation device 120 deployed in an autonomous driving simulation platform. As shown in FIG. 12, the autonomous driving simulation device 120 can comprise a simulation scenario file receiving interface 1201, a secondary vehicle driving strategy configuration interface 1202, and a first simulation unit 1203. Wherein:

[0161] The simulation scenario file receiving interface 1201 is configured to receive a simulation scenario file, the simulation scenario file comprising secondary vehicle action information and road condition information, the secondary vehicle action information being used to describe the driving behavior of at least one secondary vehicle model in an autonomous driving simulation task, and the road condition information being used to describe the road condition of the autonomous driving simulation task.

[0162] The secondary vehicle driving strategy configuration interface 1202 is configured to receive a secondary vehicle driving strategy, the secondary vehicle driving strategy being used to describe the driving behavior of at least one secondary vehicle model in an autonomous driving simulation task.

[0163] The first simulation unit 1203 is configured to, at a first time point of performing the automatic driving simulation task, obtain an initial instruction at the first time point based on the secondary vehicle action information and a current road condition at the first time point, the initial instruction at the first time point being used to instruct a driving behavior of the secondary vehicle model under the current road condition at the first time point; and confirming that the driving behavior instructed by the initial instruction at the first time point does not conflict with the secondary vehicle driving strategy, and executing the initial instruction at the first time point.

[0164] The first simulation unit 1203 is further configured to, at a second time point of performing the automatic driving simulation task, obtain an initial instruction at the second time point based on the secondary vehicle action information and a current road condition at the second time point, the initial instruction at the second time point being used to instruct a driving behavior of the secondary vehicle model under the current road condition at the second time point; confirming that the driving behavior instructed by the initial instruction at the second time point conflicts with the secondary vehicle driving strategy, generating a first correction instruction based on the secondary vehicle driving strategy and the current road condition at the second time point to correct the driving behavior instructed by the initial instruction at the second time point, and executing the first correction instruction.

[0165] The simulation scenario file receiving interface 1201, the secondary vehicle driving strategy configuration interface 1202, and the first simulation unit 1203 can be implemented by software or by hardware. For example, the implementation of the first simulation unit 1203 is described below. Similarly, the implementation of the simulation scenario file receiving interface 1201 and the secondary vehicle driving strategy configuration interface 1202 can refer to the implementation of the first simulation unit 1203.

[0166] As an example of a software functional unit, the first simulation unit 1203 can include code running on a computing instance. The computing instance can include at least one of a physical host (computing device), a virtual machine, and a container. Further, the computing instance can be one or more. For example, the A module can include code running on multiple hosts / virtual machines / containers. It should be noted that the multiple hosts / virtual machines / containers used to run the code can be distributed in the same region (region), or can be distributed in different regions. Further, the multiple hosts / virtual machines / containers used to run the code can be distributed in the same availability zone (AZ), or can be distributed in different AZs, each AZ including one data center or multiple data centers with similar geographical locations. Generally, one region can include multiple AZs.

[0167] Likewise, the multiple hosts / virtual machines / containers used to run the code can be distributed in the same virtual private cloud (VPC) or in multiple VPCs. Among them, usually one VPC is set in one region, and communication between two VPCs in the same region or between VPCs in different regions needs to set a communication gateway in each VPC to realize the interconnection between VPCs through the communication gateway.

[0168] As an example of a hardware functional unit, the A module can include at least one computing device, such as a server, etc. Alternatively, the first simulation unit 1203 can also be a device implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), etc. Among them, the above-mentioned PLD can be implemented by a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0169] The multiple computing devices included in the first simulation unit 1203 can be distributed in the same region or in different regions. The multiple computing devices included in the first simulation unit 1203 can be distributed in the same AZ or in different AZs. Likewise, the multiple computing devices included in the first simulation unit 1203 can be distributed in the same VPC or in multiple VPCs. Among them, the multiple computing devices can be any combination of servers, ASICs, PLDs, CPLDs, FPGAs, and GALs, etc.

[0170] It should be noted that in other embodiments, the first simulation unit 1203 is configured to perform the process S403 or S404 in FIG. 4 or FIG. 5; the simulation scenario file receiving interface 1201 is configured to perform the process S401 in FIG. 4 or FIG. 5; and the secondary vehicle driving strategy configuration interface 1202 is configured to perform the process S402 in FIG. 4 or FIG. 5. The steps responsible for implementation by the simulation scenario file receiving interface 1201, the secondary vehicle driving strategy configuration interface 1202 and the first simulation unit 1203 can be specified as needed, and the entire function of the automatic driving simulation device 120 can be implemented by the simulation scenario file receiving interface 1201, the secondary vehicle driving strategy configuration interface 1202 and the first simulation unit 1203 respectively implementing different steps in the automatic driving simulation method provided in FIG. 4 or FIG. 5.

[0171] An embodiment of the present application provides a structural schematic diagram of a computing device 1300. For example, the computing device 1300 can implement the function of the automatic driving simulation platform in the above embodiments.

[0172] As shown in FIG. 13, the computing device 1300 can include a bus 1302, a processor 1304, a memory 1306 and a communication interface 1308. The processor 1304, the memory 1306 and the communication interface 1308 communicate through the bus 1302. The computing device 1300 can be a server or a cloud server. It should be understood that the number of processors and memories in the computing device 1300 is not limited in the present application.

[0173] The bus 1302 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one line is shown in FIG. 13, but it does not mean that there is only one bus or only one type of bus. The bus 1302 can include a path for transmitting information between various components (e.g., the memory 1306, the processor 1304, the communication interface 1308) of the computing device 1300.

[0174] The processor 1304 can include any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP), etc.

[0175] The memory 1306 can include volatile memory (volatile memory), such as random access memory (RAM). The processor 1304 can also include non-volatile memory (non-volatile memory), such as read-only memory (ROM), flash memory, a hard disk drive (HDD) or a solid state drive (SSD).

[0176] The communication interface 1308 uses a transceiver module such as, but not limited to, a network interface card, a transceiver, to enable communication between the computing device 1300 and other devices or communication networks.

[0177] In another aspect, the memory 1306 in the computing device 1300 shown in Figure 13 stores executable program code, and the processor 1304 executes the executable program code to respectively implement the functions of the aforementioned simulation scenario file receiving interface 1201, the secondary vehicle driving strategy configuration interface 1202 and the first simulation unit 1203, thereby implementing the automatic driving simulation method shown in Figure 4 or Figure 5. That is, the memory 1306 stores instructions for executing the automatic driving simulation method shown in Figure 4 or Figure 5.

[0178] In still another aspect, the embodiments of the present application also provide a computing device cluster as shown in Figure 14. The computing device cluster includes at least one computing device. The computing device can be a server, such as a central server, an edge server, or a local server in a local data center. In some embodiments, the computing device can also be a desktop computer, a notebook computer, or a terminal device such as a smart phone.

[0179] As shown in Figure 14, the computing device cluster includes at least one computing device 1300. The memory 1306 in one or more computing devices 1300 in the computing device cluster can store the same instructions for executing the automatic driving simulation method shown in Figure 4 or Figure 5.

[0180] In some possible implementations, the memory 1306 of one or more computing devices 1300 in the computing device cluster can also respectively store partial instructions for executing the automatic driving simulation method shown in Figure 4 or Figure 5. In other words, the combination of one or more computing devices 1300 can collectively execute the instructions for executing the automatic driving simulation method shown in Figure 4 or Figure 5.

[0181] It should be noted that the memories 1306 in different computing devices 1300 in the computing device cluster can store different instructions for performing part of the functions of the autonomous driving simulation apparatus 120 respectively. That is, the instructions stored in the memories 1306 in different computing devices 1300 can implement the functions of one or more of the simulation scenario file receiving interface 1201, the secondary vehicle driving strategy configuration interface 1202, and the first simulation unit 1203.

[0182] In some possible implementation manners, one or more computing devices 1300 in the computing device cluster can be connected through a network. The network can be a wide area network or a local area network, etc. FIG. 15 shows a possible implementation manner. As shown in FIG. 15, two computing devices 1300A and 1300B are connected through a network. Specifically, the computing devices are connected to the network through communication interfaces in the computing devices. In this kind of possible implementation manner, the memory 1306 in the computing device 1300A stores instructions for performing the functions of the simulation scenario file receiving interface 1201 and the secondary vehicle driving strategy configuration interface 1202. Meanwhile, the memory 1306 in the computing device 1300B stores instructions for performing the functions of the first simulation unit 1203.

[0183] The connection manner between the computing device cluster shown in FIG. 15 can be that, considering that the code testing method provided in the present application needs to store a large amount of data, it is considered to assign the functions implemented by the first simulation unit 1203 to the computing device 1300B to perform.

[0184] It should be understood that the functions of the computing device 1300A shown in FIG. 15 can also be completed by multiple computing devices 1300. Similarly, the functions of the computing device 1300B can also be completed by multiple computing devices 1300.

[0185] In still another aspect, the embodiments of the present application also provide a computer program product containing instructions. The computer program product can be a software or program product containing instructions, which can be run on a computing device or stored in any available medium. When the computer program product is run on at least one computing device, the at least one computing device is caused to perform the method shown in FIG. 4 or FIG. 5.

[0186] In still another aspect, the embodiments of the present application also provide a computer readable storage medium. The computer readable storage medium can be any available media or data center or the like data storage device containing one or more of the available media. The available media can be a magnetic media (for example, floppy disk, hard disk, magnetic tape), an optical media (for example, DVD), or a semiconductor media (for example, solid state disk) or the like. The computer readable storage medium includes instructions indicating the computing device to execute the method illustrated in FIG. 4 or FIG. 5, or indicating the computing device to execute the method illustrated in FIG. 4 or FIG. 5.

[0187] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the protection scope of the technical solutions of the embodiments of the present application.

Claims

1. An automatic driving simulation method, characterized in that: Applied to an autonomous driving simulation platform for executing an autonomous driving simulation task including at least one auxiliary vehicle model, the method comprises: receiving a simulation scenario file from a simulation scenario file configuration interface, the simulation scenario file including auxiliary vehicle action information and road condition information, the auxiliary vehicle action information being used to describe the driving behavior of the at least one auxiliary vehicle model in the autonomous driving simulation task, and the road condition information being used to describe the road condition of the autonomous driving simulation task; receiving a secondary vehicle driving strategy from a secondary vehicle driving strategy configuration interface, wherein the secondary vehicle driving strategy is used to describe the driving behavior of the at least one secondary vehicle model in the autonomous driving simulation task; At a first moment of executing the autonomous driving simulation task, based on the auxiliary vehicle action information and the current road condition at the first moment, obtaining an initial instruction at the first moment, the initial instruction at the first moment being used to instruct the at least one auxiliary vehicle model on a driving behavior under the current road condition at the first moment; confirming that the driving behavior indicated by the initial instruction at the first moment does not conflict with the auxiliary vehicle driving strategy, and executing the initial instruction at the first moment; At the second moment of executing the automatic driving simulation task, an initial instruction at the second moment is obtained based on the auxiliary vehicle action information and the current road condition at the second moment, and the initial instruction at the second moment is used to indicate the driving behavior of the at least one auxiliary vehicle model under the current road condition at the second moment; confirming that the driving behavior indicated by the initial instruction at the second moment conflicts with the auxiliary vehicle driving strategy, generating a first correction instruction based on the auxiliary vehicle driving strategy and the current road condition at the second moment to correct the driving behavior indicated by the initial instruction at the second moment, and executing the first correction instruction.

2. The method according to claim 1, characterized in that The autonomous driving simulation platform is specifically configured to execute the autonomous driving simulation task including the at least one auxiliary vehicle model and the at least one main vehicle model. The method further comprises: receiving a master vehicle configuration request from a master vehicle configuration interface, wherein the master vehicle configuration request is used to determine a master vehicle algorithm model, wherein the master vehicle algorithm model is used to describe the driving behavior of the at least one master vehicle model in the autonomous driving simulation task; The executing of the autonomous driving simulation task includes: executing the driving behavior of the at least one main vehicle model at the first moment and the second moment based on the main vehicle algorithm model.

3. The method according to claim 1 or 2, characterized in that The method further comprises: At a third moment in the execution of the autonomous driving simulation task, confirming that no initial instruction for instructing the auxiliary vehicle model on a driving behavior under the current road condition at the third moment is obtained based on the auxiliary vehicle action information and the current road condition at the third moment; Based on the auxiliary vehicle driving strategy and the current road condition at the third moment, a second correction instruction is generated and executed; the second correction instruction is used to instruct the auxiliary vehicle model on the driving behavior under the current road condition at the third moment.

4. The method according to any one of claims 1 to 3, characterized in that The priority of the driving behavior of the at least one accessory vehicle model defined by the accessory vehicle action information at the first moment is higher than the driving behavior of the at least one accessory vehicle model defined by the accessory vehicle driving strategy at the first moment; the priority of the driving behavior of the at least one accessory vehicle model defined by the accessory vehicle action information at the second moment is lower than the driving behavior of the at least one accessory vehicle model defined by the accessory vehicle driving strategy at the second moment.

5. The method according to any one of claims 1 to 4, characterized in that The auxiliary vehicle driving strategy includes one or more of the following strategies: path planning strategy, braking strategy, lane changing strategy, overtaking strategy, and avoidance strategy.

6. The method according to claim 5, characterized in that The path planning strategy is used to indicate the priority rules during path planning; the braking strategy is used to indicate the conditions for performing braking behavior or the braking speed value; the lane changing strategy is used to indicate the lane changing direction; the overtaking strategy is used to indicate the conditions for performing overtaking behavior; and the avoidance strategy is used to indicate the conditions for performing avoidance behavior.

7. The method according to claim 5 or 6, characterized in that The path planning strategy includes any of the following: closest distance first, left first, or right first; The overtaking strategy includes the speed of the preceding vehicle being less than or equal to a first threshold value; The avoidance strategy includes that the collision time TTC is less than or equal to a second threshold value.

8. The method according to any one of claims 1 to 7, characterized in that The simulation scenario file further includes auxiliary vehicle performance information, where the auxiliary vehicle performance information is used to indicate auxiliary vehicle performance. The method further includes: At a fourth moment in the execution of the autonomous driving simulation task, based on the auxiliary vehicle action information and the current road condition at the fourth moment, obtaining an initial instruction at the fourth moment, wherein the initial instruction at the fourth moment is used to instruct the auxiliary vehicle model on a driving behavior under the current road condition at the fourth moment; If the performance of the auxiliary vehicle does not support the driving behavior indicated by the initial instruction at the fourth moment, a third correction instruction is generated based on the auxiliary vehicle driving strategy and the current road conditions at the fourth moment to correct the driving behavior indicated by the initial instruction at the fourth moment, and the third correction instruction is executed.

9. The method according to any one of claims 1 to 8, characterized in that The method further comprises: In response to a preview request sent by a user, executing an autonomous driving simulation preview task including at least one vehicle model, wherein executing the autonomous driving simulation preview task specifically includes: executing driving behaviors of the vehicle model at different moments in the autonomous driving simulation preview task according to the auxiliary vehicle action information and the auxiliary vehicle driving strategy; A preview interface is provided, which is used to display the simulation process of the autonomous driving simulation preview task, and the simulation process includes the driving behavior of the vehicle model.

10. An automatic driving simulation device, characterized in that: The device is applied to an autonomous driving simulation platform, which is used to execute an autonomous driving simulation task including at least one auxiliary vehicle model. The device includes: a simulation scenario file receiving interface, configured to receive a simulation scenario file, the simulation scenario file including auxiliary vehicle action information and road condition information, the auxiliary vehicle action information being used to describe the driving behavior of the at least one auxiliary vehicle model in the autonomous driving simulation task, and the road condition information being used to describe the road condition of the autonomous driving simulation task; A secondary vehicle driving strategy configuration interface, configured to receive a secondary vehicle driving strategy, wherein the secondary vehicle driving strategy is used to describe the driving behavior of the at least one secondary vehicle model in the autonomous driving simulation task; a first simulation unit configured to, at a first moment of executing the autonomous driving simulation task, obtain an initial instruction at the first moment based on the auxiliary vehicle action information and the current road condition at the first moment, the initial instruction at the first moment being used to instruct the at least one auxiliary vehicle model on a driving behavior under the current road condition at the first moment; confirm that the driving behavior indicated by the initial instruction at the first moment does not conflict with the auxiliary vehicle driving strategy, and then execute the initial instruction at the first moment; The first simulation unit is further used to obtain an initial instruction at a second moment when executing the automatic driving simulation task, based on the auxiliary vehicle action information and the current road conditions at the second moment, wherein the initial instruction at the second moment is used to indicate the driving behavior of the at least one auxiliary vehicle model under the current road conditions at the second moment; confirm that the driving behavior indicated by the initial instruction at the second moment conflicts with the auxiliary vehicle driving strategy, generate a first correction instruction based on the auxiliary vehicle driving strategy and the current road conditions at the second moment, to correct the driving behavior indicated by the initial instruction at the second moment, and execute the first correction instruction.

11. The device according to claim 10, characterized in that The autonomous driving simulation platform is specifically configured to execute the autonomous driving simulation task including the at least one auxiliary vehicle model and the at least one main vehicle model; the device further comprises: A master vehicle configuration interface, configured to receive a master vehicle configuration request, wherein the master vehicle configuration request is used to determine a master vehicle algorithm model; the master vehicle algorithm model is used to describe the driving behavior of the at least one master vehicle model in the autonomous driving simulation task; The second simulation unit is used to execute the driving behavior of the at least one main vehicle model at the first moment and the second moment based on the main vehicle algorithm model during the execution of the automatic driving simulation task.

12. The device according to claim 10 or 11, characterized in that The first simulation unit is further configured to: confirm, at a third moment in the execution of the autonomous driving simulation task, that no initial instruction instructing the auxiliary vehicle model on a driving behavior under the current road conditions at the third moment is obtained based on the auxiliary vehicle action information and the current road conditions at the third moment; generating a second correction instruction based on the auxiliary vehicle driving strategy and the current road condition at the third moment, and executing the second correction instruction; The second correction instruction is used to instruct the auxiliary vehicle model on a driving behavior under the current road condition at the third moment.

13. The device according to any one of claims 10 to 12, characterized in that The priority of the driving behavior of the at least one accessory vehicle model defined by the accessory vehicle action information at the first moment is higher than the driving behavior of the at least one accessory vehicle model defined by the accessory vehicle driving strategy at the first moment; the priority of the driving behavior of the at least one accessory vehicle model defined by the accessory vehicle action information at the second moment is lower than the driving behavior of the at least one accessory vehicle model defined by the accessory vehicle driving strategy at the second moment.

14. The device according to any one of claims 10 to 13, characterized in that The auxiliary vehicle driving strategy includes one or more of the following strategies: path planning strategy, braking speed strategy, lane changing strategy, overtaking strategy, and avoidance strategy.

15. The device according to claim 14, characterized in that The path planning strategy is used to indicate the priority rules during path planning; the braking speed strategy is used to indicate the braking speed value; the lane changing strategy is used to indicate the lane changing direction; the overtaking strategy is used to indicate the conditions for executing overtaking behavior; and the avoidance strategy is used to indicate the conditions for executing avoidance behavior.

16. The device according to claim 14 or 15, characterized in that The path planning strategy includes any one of the following: shortest distance priority, left priority, or right priority; the overtaking strategy includes the speed of the preceding vehicle being less than or equal to a first threshold value; the avoidance strategy includes the collision time TTC being less than or equal to a second threshold value.

17. The device according to any one of claims 10 to 16, characterized in that The simulation scenario file further includes auxiliary vehicle performance information, where the auxiliary vehicle performance information is used to indicate auxiliary vehicle performance. The first simulation unit is further configured to: At a fourth moment in the execution of the autonomous driving simulation task, based on the auxiliary vehicle action information and the current road condition at the fourth moment, obtaining an initial instruction at the fourth moment, wherein the initial instruction at the fourth moment is used to instruct the auxiliary vehicle model on a driving behavior under the current road condition at the fourth moment; If the performance of the auxiliary vehicle does not support the driving behavior indicated by the initial instruction at the fourth moment, a third correction instruction is generated based on the auxiliary vehicle driving strategy and the current road conditions at the fourth moment to correct the driving behavior indicated by the initial instruction at the fourth moment, and the third correction instruction is executed.

18. The device according to any one of claims 10 to 17, characterized in that The device further comprises: a preview unit, configured to execute, in response to a preview request sent by a user, an autonomous driving simulation preview task including at least one vehicle model, wherein executing the autonomous driving simulation preview task specifically comprises: executing driving behaviors of the vehicle model at different moments in the autonomous driving simulation preview task according to the auxiliary vehicle action information and the auxiliary vehicle driving strategy; A display unit is used to provide a preview interface, where the preview interface is used to display the simulation process of the autonomous driving simulation preview task, where the simulation process includes the driving behavior of the vehicle model.

19. The device according to claim 11, characterized in that The first simulation unit and the second simulation unit are deployed in a simulator, and the simulator is used to perform the autonomous driving simulation task; or, the first simulation unit and the second simulation unit are deployed separately.

20. A computing device cluster, characterized in that: comprising at least one computing device, each computing device including a processor and a memory; The processor of the at least one computing device is configured to execute instructions stored in a memory of the at least one computing device, so that the computing device cluster executes the method according to any one of claims 1 to 9.

21. A computer program product comprising instructions, characterized in that When the instructions are executed by a computing device cluster, the computing device cluster is caused to perform the method according to any one of claims 1 to 9.

22. A computer-readable storage medium, characterized in that The method comprises computer program instructions. When the computer program instructions are executed by a computing device cluster, the computing device cluster performs the method according to any one of claims 1 to 9.

Images