Simulation test method, system and equipment for whole vehicle and storage medium

Abstract

The invention provides a simulation test method, system and device for a whole vehicle, and a storage medium. The method comprises the following steps: obtaining test data; performing deep semantic analysis on the test data through a large model scene generation engine to obtain a scene file; loading the scene file through a simulation engine for testing, and generating a test report; according to the method, an efficient, reliable and extensible intelligent driving simulation test system is constructed, the test efficiency, accuracy and system flexibility are remarkably improved, and powerful support is provided for research and development of the automatic driving technology; the system has the same beneficial effects.

Description

Technical Field

[0001] This invention relates to the field of vehicle simulation testing technology, and in particular to a method, system, equipment, and storage medium for simulating and testing a complete vehicle. Background Technology

[0002] With the rapid development of autonomous driving technology, simulation and vehicle synchronous control have become crucial for verifying algorithms and safety. The current mainstream solution is a vehicle-in-the-loop testing system, whose core architecture is as follows: Figure 1 As shown, this system connects the controller of a real vehicle to a virtual driving environment running on a simulation server, forming a closed-loop testing system.

[0003] In vehicle-in-the-loop testing, simulation testing systems are typically used. When autonomous driving algorithms need to be verified, the simulation server connects to the vehicle controller interface via a communication interface, such as a CAN bus or Ethernet interface, to send virtual environment data to the corresponding vehicle controller. However, due to increasingly complex test scenarios, numerous vehicle configurations, and a growing number of sensor types, current simulation testing methods not only suffer from insufficient test coverage but also exhibit low testing efficiency and difficulty in guaranteeing the reliability of results.

[0004] Therefore, improving testing efficiency, accuracy, and system flexibility is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides a simulation testing method, system, equipment, and storage medium for a complete vehicle. It solves the key bottleneck problem in traditional simulation testing systems by using automatic generation technology of simulation scenarios based on large models.

[0006] The first objective of this invention is to provide a simulation testing method for a complete vehicle; The technical solution provided by this invention is as follows: A simulation testing method for a complete vehicle includes the following steps: Obtain test data; The test data is subjected to deep semantic analysis using a large model scene generation engine to obtain scene files. The simulation engine loads the scene file for testing and generates a test report.

[0007] Preferably, the step of performing deep semantic parsing on the test data using a large model scene generation engine to obtain scene files specifically includes: Entity recognition is performed using a large model scene generation engine to extract key parameters; The scene topology is constructed based on the key parameters to generate the scene file.

[0008] Preferably, it further includes: Clock synchronization is established based on multiple timestamps and offsets.

[0009] Preferably, after performing deep semantic parsing on the test data using a large model scene generation engine to obtain scene files, the method further includes: Configure the scheduling strategy of the time-aware shaper according to the scene file.

[0010] Preferably, the step of loading the scene file through the simulation engine for testing specifically includes: The simulation engine loads the scene file and initializes the virtual environment; The vehicle controller connects to the simulation loop to receive virtual sensor data and outputs control commands to execute tests.

[0011] Preferably, after loading the scene file through the simulation engine for testing, the method further includes: A multi-sensor fusion algorithm is used to generate environmental perception results and vehicle state estimates.

[0012] Preferably, after generating the environmental perception results and vehicle state estimation using a multi-sensor fusion algorithm, the method further includes: Based on real-time monitoring of timing deviations and data quality, operating parameters are dynamically adjusted.

[0013] The second objective of this invention is to provide a simulation testing system for a complete vehicle. The technical solution provided by this invention is as follows: A simulation testing system for a complete vehicle includes: an acquisition module, a parsing module, and a testing module; The acquisition module is used to acquire test data; The parsing module is used to perform deep semantic parsing on the test data through a large model scene generation engine to obtain scene files; The testing module is used to load the scene file through the simulation engine for testing and generate a test report.

[0014] The third objective of this invention is to provide an electronic device; The technical solution provided by this invention is as follows: An electronic device, comprising: At least one processor; and A memory communicatively connected to the at least one processor, the memory storing a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the steps of any one of the methods for simulating the testing of a whole vehicle.

[0015] A fourth objective of this invention is to provide a computer-readable storage medium; The technical solution provided by this invention is as follows: A computer-readable storage medium, characterized in that the storage medium is used to store a computer program, the computer program being used to cause a computer to execute the steps of any one of the simulation testing methods for a whole vehicle.

[0016] Compared with existing technologies, the present invention provides a vehicle simulation testing method, which includes the following steps: acquiring test data; performing deep semantic analysis on the test data through a large model scene generation engine to obtain scene files; loading the scene files through a simulation engine for testing and generating a test report; this method constructs an efficient, reliable, and scalable intelligent driving simulation testing system, which significantly improves testing efficiency, accuracy, and system flexibility, and provides strong support for the research and development of autonomous driving technology.

[0017] The present invention also provides a simulation testing system for a complete vehicle. Since this system and the simulation testing method for a complete vehicle solve the same technical problem and belong to the same technical concept, they should have the same beneficial effects, and will not be described in detail here. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A flowchart illustrating a simulation testing method for a complete vehicle provided in this application embodiment; Figure 2 A schematic diagram of the structure of a vehicle simulation testing system provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0020] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] It should be noted that when a component is referred to as "fixed to" or "set on" another component, it can be directly on or indirectly set on the other component; when a component is referred to as "connected to" another component, it can be directly connected to or indirectly connected to the other component.

[0022] It should be noted that the structures, proportions, sizes, etc., shown in the accompanying drawings of this specification are only for the purpose of assisting those skilled in the art in understanding and reading the content disclosed in the specification, and are not intended to limit the conditions under which this application can be implemented. Therefore, they have no substantial technical significance. Any modifications to the structure, changes in the proportions, or adjustments to the size should still fall within the scope of the technical content disclosed in this application, provided that they do not affect the effects and purposes that this application can produce.

[0023] like Figure 1 As shown, this embodiment of the invention provides a simulation testing method for a complete vehicle, including the following steps: S1. Obtain test data; S2. Perform deep semantic analysis on the test data using a large model scene generation engine to obtain scene files; S3. Load the scene file using the simulation engine for testing and generate a test report.

[0024] In steps S1 to S3, users input test data, i.e., test requirements, in natural language through a web interface or voice interaction interface. The input supports structured descriptions, including environmental conditions (e.g., "highway at night in the rain"), dynamic elements (e.g., "truck ahead suddenly brakes"), and special events (e.g., "pedestrian runs across from the right"). The system provides intelligent completion and semantic verification functions to ensure the accuracy and completeness of the requirement description. Then, a large model scene generation engine performs deep semantic parsing on the above test requirements to generate scene files. Finally, the simulation engine loads the scene files for testing. After the test is completed, the report generation module automatically generates a detailed test report, which includes test configuration information, execution logs, performance metric statistics, abnormal event records, and result analysis. It supports multiple output formats (PDF, HTML, JSON) and can be automatically pushed to the project management system and test database via API interface. This method constructs an efficient, reliable, and scalable intelligent driving simulation test system, significantly improving testing efficiency, accuracy, and system flexibility, providing strong support for the research and development of autonomous driving technology.

[0025] Preferably, the step of performing deep semantic parsing on the test data using a large model scene generation engine to obtain scene files specifically includes: Entity recognition is performed using a large model scene generation engine to extract key parameters; The scene topology is constructed based on the key parameters to generate the scene file.

[0026] In practical applications, the construction of test scenarios relies entirely on manual coding and configuration by engineers, requiring significant human intervention and time. Building a complex scenario often takes hours or even days, and the generated scenarios have limited diversity, failing to adequately cover complex real-world situations and long-tail scenarios, especially unforeseen dangerous scenarios and edge cases. This results in many potential risks going undetected in the laboratory phase, ultimately necessitating discovery in costly and lengthy real-world road tests, significantly slowing down the development process. This method employs a large-model scenario generation engine. When users describe test requirements via a natural language input interface, the system parses the semantics based on a trained LLM model, automatically extracts scenario parameters, and generates standardized OpenSCENARIO scenario files. This improvement reduces scenario preparation time from hours to minutes and enables the generation of more diverse edge scenarios.

[0027] Specifically, the large-scale scene generation engine is based on an LLM model trained on massive amounts of scene data, performing deep semantic parsing on the input requirements. First, key parameters are extracted through entity recognition, including weather conditions, light intensity, road topology, types of traffic participants, and behavioral patterns. Then, a scene topology structure is constructed according to the OpenSCENARIO standard, generating a complete description file containing road networks, traffic flow, environmental conditions, and triggering events. Finally, a rule engine performs logical verification and rationality evaluation to ensure the effectiveness and security of the generated scene. This embodiment, by creating a full-link technology system of "multimodal input, semantic parsing, AIGC generation, and standardized output," is the first to deeply integrate Transformer-based speech recognition technology (supporting a 16kHz sampling rate and over 98% recognition accuracy), scene element video analysis technology (capable of extracting key elements such as roads, vehicles, and the environment from images), and a finely tuned and optimized LLM large-scale model. By using a Few-Shot learning mechanism and rule engine verification, the system automatically converts multimodal requirements such as text, speech, and sketches into standardized simulation scenarios. It supports output of international standard formats such as OpenSCENARIO v1.0 / v1.1 and OpenDRIVE, solving the core problems of low efficiency and insufficient coverage of edge scenarios in traditional manual scenario writing.

[0028] Preferably, it further includes: Clock synchronization is established based on multiple timestamps and offsets.

[0029] In practical applications, data exchange between the simulation system and the vehicle control system relies on traditional TCP / IP networks or conventional CAN bus protocols. The inherent latency and jitter of these common network protocols result in millisecond-level time differences between the virtual simulation environment and the real vehicle controller. This timing asynchrony causes control loop inaccuracies, makes test results difficult to reproduce, and often leads to misjudging synchronization problems as algorithmic defects, thus misleading researchers' optimization directions and wasting significant time. To address system synchronization, this method deploys a TSN network switching device and integrates a high-precision clock synchronization module. Specifically, clock synchronization cards supporting the IEEE 1588 protocol are installed in both the simulation server and the vehicle controller. A time-aware shaper allocates fixed transmission time slots to critical data streams, ensuring that simulation commands and vehicle status data are transmitted within a defined time window. This improvement reduces timing errors from milliseconds to microseconds, eliminating test distortion caused by network jitter.

[0030] On both the simulation server and the vehicle controller, a high-precision clock synchronization card based on the IEEE 802.1AS-Rev protocol is used for time alignment. Sub-microsecond clock synchronization is achieved through multiple rounds of timestamp exchange and offset calculation. The synchronization process continuously monitors clock drift and uses a Kalman filter for predictive compensation to ensure long-term synchronization stability. By combining hardware clock synchronization and software scheduling, the time synchronization accuracy between the simulation system and the vehicle system is improved from milliseconds to microseconds, effectively eliminating test errors caused by timing discrepancies. Test data shows that the misjudgment rate related to timing deviations is reduced from 35% to below 1%, improving the accuracy and repeatability of test results. In addition to hardware time synchronization cards, software time synchronization algorithms, such as improved versions of PTP (Precise Time Protocol) or NTP (Network Time Protocol), can also be used in the time synchronization scheme. Although the accuracy is slightly lower, the cost is lower, making them suitable for applications where extremely high synchronization accuracy is not required.

[0031] This method integrates a collaborative architecture of dedicated TSN hardware, high-precision synchronization protocol, and dynamic calibration algorithm. At the hardware level, it employs industrial-grade TSN switching equipment (switching capacity ≥128Gbps) supporting the IEEE 802.1Qbv / Qbu standard and a PTP clock card with a built-in temperature-controlled crystal oscillator (frequency stability 1E-11 / day). At the protocol level, clock message interaction is implemented based on the IEEE 1588-2008 (PTPv2) protocol. At the algorithm level, through digital phase-locked loop dynamic calibration and intelligent bandwidth allocation algorithms, it achieves microsecond-level time synchronization between the simulation environment and the actual vehicle control system, with a synchronization error ≤100ns, ensuring the timing consistency of virtual and real data transmission and overcoming the technical bottlenecks of low synchronization accuracy and weak anti-interference capability in traditional TCP / IP networks.

[0032] Preferably, after performing deep semantic parsing on the test data using a large model scene generation engine to obtain scene files, the method further includes: Configure the scheduling strategy of the time-aware shaper according to the scene file.

[0033] In practical applications, the scheduling strategy for the time-aware shaper is configured based on the data characteristics of the test scenario; fixed time slots are allocated to the sensor data stream to ensure deterministic transmission; the highest priority is assigned to control commands to guarantee real-time performance; and the optimal effort strategy is configured for logs and monitoring data. The system generates a traffic scheduling table and sends it to the TSN switch, establishing an end-to-end deterministic transmission channel.

[0034] Preferably, the step of loading the scene file through the simulation engine for testing specifically includes: The simulation engine loads the scene file and initializes the virtual environment; The vehicle controller connects to the simulation loop to receive virtual sensor data and outputs control commands to execute tests.

[0035] In practical applications, the simulation engine loads the scenario file, initializes the virtual environment, and the vehicle controller connects to the simulation loop, beginning to receive virtual sensor data and output control commands. The system executes tests according to the trigger conditions and event sequences defined in the scenario, recording vehicle status, environmental data, and system performance indicators in real time. Real-time pause and resume functionality, as well as dynamic adjustment of scenario parameters, are supported during test execution.

[0036] Preferably, after loading the scene file through the simulation engine for testing, the method further includes: A multi-sensor fusion algorithm is used to generate environmental perception results and vehicle state estimates.

[0037] In practical applications, existing monitoring systems often employ a monolithic architecture, tightly coupling data acquisition, processing, storage, and display functions. This architecture struggles to meet the demands of accessing and processing multi-source, heterogeneous data in intelligent driving testing. Adding new sensors or data analysis functions often requires modifying and redeploying the entire system, lacking flexibility and scalability, thus limiting the evolution of the testing system and team collaboration efficiency. This approach constructs a microservice-based monitoring platform. The system is divided into three independent microservices: data acquisition, processing and storage, and visualization. These services communicate via a RESTful API. The data acquisition service supports multiple protocol adapters and can simultaneously access data from cameras, LiDAR, and CAN bus; the processing and storage service uses a time-series database to optimize query performance; and the visualization service provides a customizable monitoring interface. This improvement enables the system to scale elastically and supports the parallel execution of multiple test tasks. A multi-source data acquisition pipeline is initiated through a microservice monitoring platform. The data acquisition service acquires real-time data from camera video streams, LiDAR point clouds, millimeter-wave radar target lists, and vehicle bus data via protocol adapters. The stream processing service cleans, filters, timestamps, and unifies the coordinate system of the raw data. The data fusion service uses multi-sensor fusion algorithms to generate environmental perception results and vehicle state estimates. In this embodiment, the microservice monitoring platform employs a distributed architecture to decouple the functional modules, enabling elastic scaling and flexible deployment of the system. The platform supports real-time access and processing of multi-source heterogeneous data, can simultaneously support the parallel execution of multiple test tasks, improves system resource utilization by 60%, and reduces operation and maintenance costs by 50%.

[0038] Preferably, after generating the environmental perception results and vehicle state estimation using a multi-sensor fusion algorithm, the method further includes: Based on real-time monitoring of timing deviations and data quality, operating parameters are dynamically adjusted.

[0039] In practical applications, the visualization service provides multi-dimensional real-time monitoring through a web interface. The 3D scene view, rendered using WebGL, displays vehicle movement, environmental changes, and sensor perception results. The data panel displays key performance indicators, including system latency, communication quality, and algorithm accuracy. The alarm panel displays system anomalies and test boundary violations in real time. It supports simultaneous access and collaborative analysis by multiple users. Simultaneously, the system monitors timing deviations and data quality in real time, dynamically adjusting operating parameters. When timing deviations exceed thresholds, the time management module dynamically adjusts the simulation clock frequency. When data transmission anomalies occur, the network management module reschedules bandwidth resources. When scene execution deviations are detected, the scene engine dynamically corrects environmental parameters to ensure the accuracy and consistency of the test.

[0040] like Figure 2As shown, this embodiment of the invention provides a simulation testing system for a complete vehicle, including: an acquisition module, a parsing module, and a testing module; The acquisition module is used to acquire test data; The parsing module is used to perform deep semantic parsing on the test data through a large model scene generation engine to obtain scene files; The testing module is used to load the scene file through the simulation engine for testing and generate a test report.

[0041] In practical applications, the vehicle simulation testing system includes an acquisition module, a parsing module, and a testing module. The parsing module is connected to both the acquisition and testing modules. The acquisition module acquires test data and transmits it to the parsing module. The parsing module performs deep semantic analysis on the test data using a large model scene generation engine to obtain scene files, which are then transmitted to the testing module. The testing module loads the scene files using the simulation engine, performs the tests, and generates a test report. These modules together construct an efficient, reliable, and scalable intelligent driving simulation testing system, significantly improving testing efficiency, accuracy, and system flexibility, providing strong support for the research and development of autonomous driving technology.

[0042] Furthermore, embodiments of this application also disclose an electronic device, Figure 3 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content of the diagram should not be construed as limiting the scope of this application.

[0043] Figure 3 This is a schematic diagram of the structure of an electronic device 20 provided in an embodiment of this application. Specifically, the electronic device 20 may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the vehicle simulation testing method disclosed in any of the foregoing embodiments. Alternatively, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0044] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0045] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored thereon can include operating system 221, computer program 222 and data 223, etc., and the storage method can be temporary storage or permanent storage. The operating system 221 manages and controls the various hardware devices on the electronic device 20 and the computer program 222 to enable the processor 21 to perform calculations and processing on the data 223 in the memory 22. It can be Windows Server, Netware, Unix, Linux, etc. The computer program 222, in addition to including a computer program capable of performing the vehicle simulation test method executed by the electronic device 20 as disclosed in any of the foregoing embodiments, may further include computer programs capable of performing other specific tasks. The data 223 may include data received by the vehicle simulation test equipment from external devices, as well as data collected by its own input / output interface 25.

[0046] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0047] Furthermore, this application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the aforementioned simulation testing method for the entire vehicle. Specific steps of this method can be found in the corresponding content disclosed in the foregoing embodiments, and will not be repeated here.

[0048] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0049] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0050] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0051] If a flowchart is used in this application, it is used to illustrate the operations performed by the system according to embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0052] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A simulation testing method for a complete vehicle, characterized in that, Includes the following steps: Obtain test data; The test data is subjected to deep semantic analysis using a large model scene generation engine to obtain scene files. The simulation engine loads the scene file for testing and generates a test report.

2. The vehicle simulation testing method according to claim 1, characterized in that, The step of performing deep semantic analysis on the test data using a large model scene generation engine to obtain scene files specifically includes: Entity recognition is performed using a large model scene generation engine to extract key parameters; The scene topology is constructed based on the key parameters to generate the scene file.

3. The vehicle simulation testing method according to claim 1, characterized in that, Also includes: Clock synchronization is established based on multiple timestamps and offsets.

4. The vehicle simulation testing method according to claim 1, characterized in that, After obtaining scene files by performing deep semantic parsing on the test data using a large model scene generation engine, the process further includes: Configure the scheduling strategy of the time-aware shaper according to the scene file.

5. The vehicle simulation testing method according to claim 1, characterized in that, The process of loading the scene file through a simulation engine for testing specifically includes: The simulation engine loads the scene file and initializes the virtual environment; The vehicle controller connects to the simulation loop to receive virtual sensor data and outputs control commands to execute tests.

6. The vehicle simulation testing method according to claim 1, characterized in that, After loading the scene file through the simulation engine for testing, the process also includes: A multi-sensor fusion algorithm is used to generate environmental perception results and vehicle state estimates.

7. The vehicle simulation testing method according to claim 6, characterized in that, After generating environmental perception results and vehicle state estimates using a multi-sensor fusion algorithm, the process further includes: Based on real-time monitoring of timing deviations and data quality, operating parameters are dynamically adjusted.

8. A simulation testing system for a complete vehicle, characterized in that, include: Acquisition module, parsing module, and testing module; The acquisition module is used to acquire test data; The parsing module is used to perform deep semantic parsing on the test data through a large model scene generation engine to obtain scene files; The testing module is used to load the scene file through the simulation engine for testing and generate a test report.

9. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor, the memory storing a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The storage medium is used to store a computer program that causes a computer to perform the method described in any one of claims 1-7.

Images