Simulation test method and device of intelligent driving controller, electronic equipment and storage medium
By pre-setting test sequences and optimizing test cases using 3D simulation models, the problems of low testing efficiency and insufficient accuracy of intelligent driving systems have been solved, achieving efficient and accurate automated testing.
Patent Information
- Application Number
- CN202511519086.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-22
- Publication Date
- 2026-02-13
AI Technical Summary
Existing technologies for testing intelligent driving systems suffer from low efficiency and insufficient accuracy, require significant human and material resources, and are prone to errors in test case writing.
By pre-setting test sequences, test commands are sent to the hardware-in-the-loop test terminal to control the intelligent driving controller to perform corresponding operations and receive test results, thereby achieving test automation. This includes start, interrupt, and end test commands, and test cases are optimized using a three-dimensional simulation model and evaluation matrix.
It improves the testing efficiency of intelligent driving systems, reduces errors in test case generation, and achieves efficient and accurate automated testing.
Smart Images

Figure CN121523285A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of testing, in particular to a simulation test method and device of an intelligent driving controller, an electronic device and a storage medium. BACKGROUND
[0002] Intelligent cars have become a strategic industry in major global economies due to their significant advantages in reducing traffic accident rates, controlling ecological pollution and optimizing energy utilization efficiency. However, intelligent driving systems face multiple technical challenges in engineering practice. Therefore, before the intelligent driving system is put into use, it needs to be tested for various functions to ensure safety. Currently, different test cases for the intelligent driving system need to be written manually, and each time a function is tested, the test case needs to be loaded and the intelligent driving system needs to execute the test case once. This not only consumes a lot of manpower and resources, but also is prone to errors in test case writing. Therefore, how to improve the testing efficiency and accuracy of the intelligent driving system is a problem that needs to be solved urgently. SUMMARY
[0003] Some embodiments of the present application aim to provide a simulation test method and device of an intelligent driving controller, an electronic device and a storage medium. Through the technical solutions of the embodiments of the present application, test instructions in a test sequence are sent to a hardware-in-the-loop test terminal in sequence in response to the test sequence being set in advance, so that the hardware-in-the-loop test terminal controls the intelligent driving controller to perform a test operation corresponding to the test instruction, and obtains a test result corresponding to the test instruction. The test sequence at least includes a start test instruction, an interrupt test instruction and an end test instruction. The test result returned by the hardware-in-the-loop test terminal is received. In the embodiments of the present application, the test sequence is set in advance, including the functional items to be tested, the test time and the test sequence. When testing the intelligent driving controller, the host computer sends the test instructions in the test sequence to the hardware-in-the-loop test terminal in sequence according to the test sequence set in advance, so that the hardware-in-the-loop test terminal controls the intelligent driving controller to perform a test operation corresponding to the test instruction, and obtains a test result corresponding to the test instruction. In this way, the intelligent driving controller does not need to consume a lot of manpower and resources for testing, and test automation is realized. This not only improves the testing efficiency, but also reduces the errors in test case generation and improves the testing accuracy.
[0004] In a first aspect, some embodiments of the present application provide a simulation test method of an intelligent driving controller, comprising: In response to a pre-set test sequence, test instructions in the test sequence are sent sequentially to a hardware-in-the-loop test terminal, so that the hardware-in-the-loop test terminal controls the intelligent driving controller to perform test operations corresponding to the test instructions and obtain test results corresponding to the test instructions; wherein, the test sequence includes at least a start test instruction, an interrupt test instruction, and an end test instruction; Receive the test results returned by the hardware-in-the-loop test terminal.
[0005] Some embodiments of this application pre-set test sequences, including the functional items to be tested, as well as the test time and test order. When testing the intelligent driving controller, the host computer sequentially sends test instructions in the pre-set test sequence to the hardware-in-the-loop test terminal. The hardware-in-the-loop test terminal then controls the intelligent driving controller to execute the test operations corresponding to the test instructions, obtaining the test results corresponding to the test instructions. This eliminates the need for significant manpower and resources for testing the intelligent driving controller, achieving test automation. This not only improves testing efficiency but also reduces errors in test case generation, thus improving test accuracy.
[0006] Optionally, if the test instruction is a start test instruction, the hardware-in-the-loop test terminal controls the intelligent driving controller to execute the test operation corresponding to the test instruction, and obtains the test result corresponding to the test instruction, including: The hardware-in-the-loop test terminal obtains the test requirements in the start test instruction and determines the corresponding test cases based on the test requirements; executes the test cases to obtain the test results corresponding to the start test instruction, wherein the test cases are determined based on a pre-stored test case set. Some embodiments of this application pre-set test sequences, and according to the test instructions in the test sequence, send the start test instruction to the hardware-in-the-loop test terminal in sequence. The control simulation board sends the corresponding control signal to the intelligent driving controller unit. The intelligent driving controller makes corresponding decision judgments based on the received vehicle driving information and control signal requests, and feeds back the result signal to the defect tracking module for result analysis and evaluation. If the expected result is met, the test steps continue.
[0007] Optionally, before sequentially sending the test instructions in the test sequence to the hardware-in-the-loop test terminal, the method includes: Obtain the functional specification description file of the intelligent driving controller, test scenario parameters, and test influencing factor parameters; Based on the functional specification description document of the intelligent driving controller, test scenario parameters, and test influencing factor parameters, determine the evaluation model of the test cases; The evaluation matrix is determined based on the parameters of the test influencing factors.
[0008] In some embodiments of this application, the host computer pre-determines the evaluation model and evaluation matrix of test cases in various functional tests of the intelligent driving controller based on the functional specification description file of the intelligent driving controller, test scenario parameters, and test influencing factor parameters, and uses them to evaluate all test cases during the testing process.
[0009] Optionally, the method further includes: Obtain test cases for the intelligent controller; Execute the test cases and obtain the test case results; The test case results are evaluated based on the evaluation model and evaluation matrix to obtain an evaluation score. If the evaluation score is greater than a preset value, the test case corresponding to the evaluation score will be used as the target test case and stored in the test case set. The test case set is sent to the hardware-in-the-loop test terminal.
[0010] In some embodiments of this application, each test case is evaluated according to the test case evaluation model and evaluation matrix to obtain an evaluation score, and the test case is judged according to the evaluation score to obtain the target test case, which is stored in the test case set. Optionally, the step of evaluating the test case results based on the evaluation model of the test case and the evaluation matrix to obtain an evaluation score includes: Based on the evaluation model and evaluation matrix of the test cases, the results of the test cases are evaluated to obtain the test case validity score, test case coverage score, and test case complexity value. The evaluation score is determined based on the test case validity score, test case coverage score, and test case complexity score.
[0011] In some embodiments of this application, each generated or selected test case is evaluated, and scores are given from three dimensions: test case validity, test case coverage, and test case complexity. For unqualified test cases, the scores are recalculated, and qualified test cases are added to the test case set.
[0012] Optionally, the method further includes: Based on the pre-set initial scenario parameters, test cases in the target test case set are tested to obtain the first scenario test results; If the test results of the first scenario do not meet the preset conditions, the initial scenario parameters are optimized using the dynamic continuous optimization algorithm and the boundary benefit optimization algorithm to obtain the optimized scenario parameters; Based on the optimized scenario parameters, test cases in the target test case set are tested to obtain the second scenario test results, until the obtained second scenario test results meet the preset conditions.
[0013] Some embodiments of this application generate the required initial scenario parameters based on the test cases in the test set, and then update the test scenario parameters in real time using dynamic continuous optimization algorithm and boundary benefit optimization algorithm based on the test effect feedback during the test process, so as to ensure that the test scenario can meet the corresponding functional test.
[0014] Optionally, the hardware-in-the-loop test terminal obtains the test requirements in the start test instruction, determines the corresponding test cases based on the test requirements, executes the test cases, and obtains the test results corresponding to the start test instruction, including: The hardware-in-the-loop test terminal constructs a three-dimensional simulation model according to the test requirements. The test requirements include at least vehicle dynamics model information, road model information, and driver model information. The driver model information is used to provide real-time output braking information, throttle, and steering wheel angle for the test requirements. The road model information is used to simulate real-world road scenarios and dynamic simulated road surfaces, and to obtain vehicle status information from the intelligent driving controller in real time. The hardware-in-the-loop test terminal, based on the three-dimensional simulation model, sends the start test command to the intelligent driving controller, so that the intelligent driving controller can make corresponding decision judgments based on the vehicle driving information in the start test command and obtain the decision judgment result. Receive the decision judgment result returned by the intelligent driving controller.
[0015] Some embodiments of this application address the testing requirements of intelligent driving controllers. A 3D scene simulation platform generates a corresponding dynamic driving model. According to the test sequence requirements, the script execution module controls the simulation board to send corresponding control signals to the intelligent driving controller unit. The intelligent driving controller makes corresponding decisions based on the received vehicle driving information and control signal requests, and feeds back the results to the defect tracking module for analysis and evaluation. If the expected results are met, the testing steps continue.
[0016] Secondly, some embodiments of this application provide a simulation testing device for an intelligent driving controller, comprising: The sending module is configured to, in response to a pre-set test sequence, sequentially send test instructions in the test sequence to a hardware-in-the-loop test terminal, so that the hardware-in-the-loop test terminal controls the intelligent driving controller to perform test operations corresponding to the test instructions and obtain test results corresponding to the test instructions; wherein, the test sequence includes at least a start test instruction, an interrupt test instruction, and an end test instruction; A receiving module is used to receive the test results returned by the hardware-in-the-loop test terminal.
[0017] Some embodiments of this application pre-set test sequences, including the functional items to be tested, as well as the test time and test order. When testing the intelligent driving controller, the host computer sequentially sends test instructions in the pre-set test sequence to the hardware-in-the-loop test terminal. The hardware-in-the-loop test terminal then controls the intelligent driving controller to execute the test operations corresponding to the test instructions, obtaining the test results corresponding to the test instructions. This eliminates the need for significant manpower and resources for testing the intelligent driving controller, achieving test automation. This not only improves testing efficiency but also reduces errors in test case generation, thus improving test accuracy.
[0018] Optionally, the receiving module is further configured to: The hardware-in-the-loop test terminal obtains the test requirements in the start test instruction and determines the corresponding test cases based on the test requirements; executes the test cases to obtain the test results corresponding to the start test instruction, wherein the test cases are determined based on a pre-stored test case set. Some embodiments of this application pre-set test sequences, and according to the test instructions in the test sequence, send the start test instruction to the hardware-in-the-loop test terminal in sequence. The control simulation board sends the corresponding control signal to the intelligent driving controller unit. The intelligent driving controller makes corresponding decision judgments based on the received vehicle driving information and control signal requests, and feeds back the result signal to the defect tracking module for result analysis and evaluation. If the expected result is met, the test steps continue.
[0019] Optionally, the apparatus further includes a setup module, the setup module being used for: Obtain the functional specification description file of the intelligent driving controller, test scenario parameters, and test influencing factor parameters; Based on the functional specification description document of the intelligent driving controller, test scenario parameters, and test influencing factor parameters, determine the evaluation model of the test cases; The evaluation matrix is determined based on the parameters of the test influencing factors.
[0020] In some embodiments of this application, the host computer pre-determines the evaluation model and evaluation matrix of test cases in various functional tests of the intelligent driving controller based on the functional specification description file of the intelligent driving controller, test scenario parameters, and test influencing factor parameters, and uses them to evaluate all test cases during the testing process.
[0021] Optionally, the establishment module is used for: Obtain test cases for the intelligent controller; Execute the test cases and obtain the test case results; The test case results are evaluated based on the evaluation model and evaluation matrix to obtain an evaluation score. If the evaluation score is greater than a preset value, the test case corresponding to the evaluation score will be used as the target test case and stored in the test case set. The test case set is sent to the hardware-in-the-loop test terminal.
[0022] In some embodiments of this application, each test case is evaluated according to the test case evaluation model and evaluation matrix to obtain an evaluation score, and the test case is judged according to the evaluation score to obtain the target test case, which is stored in the test case set. Optionally, the establishment module is used for: Based on the evaluation model and evaluation matrix of the test cases, the results of the test cases are evaluated to obtain the test case validity score, test case coverage score, and test case complexity value. The evaluation score is determined based on the test case validity score, test case coverage score, and test case complexity score.
[0023] In some embodiments of this application, each generated or selected test case is evaluated, and scores are given from three dimensions: test case validity, test case coverage, and test case complexity. For unqualified test cases, the scores are recalculated, and qualified test cases are added to the test case set.
[0024] Optionally, the establishment module is used for: Based on the pre-set initial scenario parameters, test cases in the target test case set are tested to obtain the first scenario test results; If the test results of the first scenario do not meet the preset conditions, the initial scenario parameters are optimized using the dynamic continuous optimization algorithm and the boundary benefit optimization algorithm to obtain the optimized scenario parameters; Based on the optimized scenario parameters, test cases in the target test case set are tested to obtain the second scenario test results, until the obtained second scenario test results meet the preset conditions.
[0025] Some embodiments of this application generate the required initial scenario parameters based on the test cases in the test set, and then update the test scenario parameters in real time using dynamic continuous optimization algorithm and boundary benefit optimization algorithm based on the test effect feedback during the test process, so as to ensure that the test scenario can meet the corresponding functional test.
[0026] Optionally, the sending module is configured to: The hardware-in-the-loop test terminal constructs a three-dimensional simulation model according to the test requirements. The test requirements include at least vehicle dynamics model information, road model information, and driver model information. The driver model information is used to provide real-time output braking information, throttle, and steering wheel angle for the test requirements. The road model information is used to simulate real-world road scenarios and dynamic simulated road surfaces, and to obtain vehicle status information from the intelligent driving controller in real time. The hardware-in-the-loop test terminal, based on the three-dimensional simulation model, sends the start test command to the intelligent driving controller, so that the intelligent driving controller can make corresponding decision judgments based on the vehicle driving information in the start test command and obtain the decision judgment result. Receive the decision judgment result returned by the intelligent driving controller.
[0027] Some embodiments of this application address the testing requirements of intelligent driving controllers. A 3D scene simulation platform generates a corresponding dynamic driving model. According to the test sequence requirements, the script execution module controls the simulation board to send corresponding control signals to the intelligent driving controller unit. The intelligent driving controller makes corresponding decisions based on the received vehicle driving information and control signal requests, and feeds back the results to the defect tracking module for analysis and evaluation. If the expected results are met, the testing steps continue.
[0028] Thirdly, some embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, it can implement the simulation testing method for an intelligent driving controller as described in any embodiment of the first aspect.
[0029] Fourthly, some embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, can implement the simulation testing method for an intelligent driving controller as described in any embodiment of the first aspect.
[0030] Fifthly, some embodiments of this application provide a computer program product, which includes a computer program, wherein when the computer program is executed by a processor, it can implement the simulation testing method for the intelligent driving controller as described in any embodiment of the first aspect. Attached Figure Description
[0031] To more clearly illustrate the technical solutions of some embodiments of this application, the accompanying drawings used in some embodiments of this application will be briefly described below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0032] Figure 1 A flowchart illustrating a simulation testing method for an intelligent driving controller provided in an embodiment of this application; Figure 2 A schematic diagram of the overall structure of an automated testing system for intelligent driving provided in an embodiment of this application; Figure 3 A schematic diagram of the test case generation and evaluation system structure for an automated testing system for intelligent driving provided in an embodiment of this application; Figure 4 A structural diagram of a HIL simulation test equipment for an automated test system for intelligent driving, provided in an embodiment of this application; Figure 5 A schematic diagram of the testing workflow for an automated testing system for intelligent driving provided in this application embodiment; Figure 6 A schematic diagram of the structure of a simulation test device for an intelligent driving controller provided in an embodiment of this application; Figure 7 This is a schematic diagram of an electronic device provided in an embodiment of this application. Detailed Implementation
[0033] The technical solutions of some embodiments of this application will now be described with reference to the accompanying drawings.
[0034] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.
[0035] Intelligent vehicles, with their significant advantages in reducing traffic accident rates, controlling ecological pollution, and optimizing energy efficiency, have risen to become a strategic industry prioritized by major global economies. However, intelligent driving systems face multiple technical challenges in engineering practice. Therefore, before an intelligent driving system is put into road use, it is necessary to test its various functions to ensure safety. Currently, test cases for different functions of the intelligent driving system need to be written manually. Each time a function is tested, a test case needs to be loaded and the intelligent driving system executed. This not only consumes a lot of manpower and resources but is also prone to errors in test case writing. Therefore, how to improve the testing efficiency and accuracy of intelligent driving systems is an urgent problem to be solved. In view of this, some embodiments of this application provide a simulation testing method for an intelligent driving controller. The method includes, in response to a pre-set test sequence, sequentially sending test instructions in the test sequence to a hardware-in-the-loop test terminal, so that the hardware-in-the-loop test terminal controls the intelligent driving controller. The test sequence executes the test operations corresponding to the test instructions and obtains the test results corresponding to the test instructions. The test sequence includes at least a start test instruction, an interrupt test instruction, and an end test instruction. The test results returned by the hardware-in-the-loop test terminal are received. In this embodiment, a test sequence is pre-set, including the functional items to be tested, the test time, and the test order. Thus, when testing the intelligent driving controller, the host computer sends the test instructions in the pre-set test sequence to the hardware-in-the-loop test terminal sequentially. This causes the hardware-in-the-loop test terminal to control the intelligent driving controller to execute the test operations corresponding to the test instructions and obtain the test results corresponding to the test instructions. This eliminates the need for significant manpower and resources to test the intelligent driving controller, achieving test automation, improving testing efficiency, reducing errors in test case generation, and increasing test accuracy.
[0036] like Figure 1 As shown, an embodiment of this application provides a simulation testing method for an intelligent driving controller, the method comprising: S101. In response to a pre-set test sequence, test instructions in the test sequence are sent sequentially to the hardware-in-the-loop test terminal, so that the hardware-in-the-loop test terminal controls the intelligent driving controller to perform test operations corresponding to the test instructions and obtain test results corresponding to the test instructions; wherein, the test sequence includes at least a start test instruction, an interrupt test instruction and an end test instruction; This application provides an automated testing system for intelligent driving, which includes a host computer, a hardware-in-the-loop test terminal, and an intelligent driving controller. The host computer is connected to the intelligent driving controller through the hardware-in-the-loop test terminal, and the hardware-in-the-loop test terminal and the intelligent driving controller are connected by a CAN cable, an Ethernet cable, and a hardwired connection.
[0037] The host computer has a pre-set test sequence, which includes test items, test time, and start test instructions, interrupt test instructions, and end test instructions corresponding to each test item.
[0038] According to the test sequence, the host computer sends the test instructions in the test sequence to the hardware-in-the-loop test terminal in sequence, so that the hardware-in-the-loop test terminal (HIL) sends the test instructions to the intelligent driving controller. The intelligent driving controller executes the test operation corresponding to the test instructions and obtains the test results corresponding to the test instructions.
[0039] For example, the host computer controls the simulation board to send corresponding control signals according to the test sequence requirements, which are then transmitted to the intelligent driving controller unit. The intelligent driving controller makes corresponding decisions based on the received vehicle driving information and control signal requests, and feeds back the result signals to the defect tracking module for result analysis and evaluation. If the expected results are met, the test steps continue.
[0040] S102. Receive the test results returned by the hardware-in-the-loop test terminal.
[0041] The host computer receives the test results returned by the hardware-in-the-loop terminal and generates a test report based on the test results.
[0042] Some embodiments of this application pre-set test sequences, including the functional items to be tested, as well as the test time and test order. When testing the intelligent driving controller, the host computer sends test instructions in the pre-set test sequence to the hardware-in-the-loop test terminal in sequence. This causes the hardware-in-the-loop test terminal to control the intelligent driving controller to execute the test operations corresponding to the test instructions, obtaining the test results corresponding to the test instructions. This eliminates the need for significant manpower and resources to test the intelligent driving controller, achieving test automation. It not only improves test efficiency but also reduces errors in test case generation, thus improving test accuracy.
[0043] Another embodiment of this application further supplements the description of the simulation test method for the intelligent driving controller provided in the above embodiments.
[0044] Figure 2This is an overall structural diagram of an automated testing system for intelligent driving according to an embodiment of the present invention. This example provides a functional testing device for an intelligent driving controller, including: a test case generation and evaluation system 1, a HIL simulation (Hardware-in-the-Loop) testing system 2, and an intelligent driving controller unit 3; the test case generation and evaluation system 1 (host computer) is connected to the HIL simulation testing system 2; the HIL simulation testing system 2 (i.e., the hardware-in-the-loop testing terminal) and the intelligent driving controller unit 3 are connected via CAN line, Ethernet line, and hardwire.
[0045] Optionally, if the test command is a start test command, the hardware-in-the-loop test terminal controls the intelligent driving controller to execute the test operation corresponding to the test command, and obtains the test result corresponding to the test command, including: The hardware-in-the-loop test terminal obtains the test requirements from the start test command and determines the corresponding test cases based on the test requirements; it executes the test cases and obtains the test results corresponding to the start test command. The test cases are determined based on a pre-stored set of test cases. Furthermore, if during the execution of test cases by the intelligent driving controller, the host computer, based on the interrupt test instruction in the test sequence, controls the execution of the interrupt test cases by the intelligent driving controller according to the interrupt test instruction; Furthermore, if, during the execution of test cases, the host computer executes an end-test instruction in the test sequence, the hardware-in-the-loop test terminal will control the intelligent driving controller to stop the execution of test cases based on the end-test instruction. Some embodiments of this application pre-set test sequences, and according to the test instructions in the test sequence, send the start test instruction to the hardware-in-the-loop test terminal in sequence. The control simulation board sends the corresponding control signal to the intelligent driving controller unit. The intelligent driving controller makes corresponding decision judgments based on the received vehicle driving information and control signal requests, and feeds back the result signal to the defect tracking module for result analysis and evaluation. If the expected result is met, the test steps continue.
[0046] Optionally, before sequentially sending the test commands in the test sequence to the hardware-in-the-loop test terminal, the method includes: Obtain the functional specification description file of the intelligent driving controller, test scenario parameters, and test influencing factor parameters; Based on the functional specification description document of the intelligent driving controller, test scenario parameters, and test influencing factor parameters, determine the evaluation model of the test cases; The evaluation matrix is determined based on the parameters of the influencing factors tested.
[0047] Figure 3This is a structural diagram of a test case generation and evaluation system for an automated testing system for intelligent driving according to an embodiment of the present invention. Further, the test case generation and evaluation system 1 consists of a test case evaluation system generation module 11, a test case generation module 12, and a test scenario parameter generation module 13.
[0048] The use case evaluation system generation module 11 includes: Test Product Specification Library 111 stores the corresponding intelligent driving controller functional specification description files; Test scenario library 112 stores all currently accumulated test scenario parameters; The Test Influence Factor Library 113 stores all currently accumulated test influence factor parameters. The tree-structured evaluation model 114, supported by existing specifications, scenario parameters, and influencing parameter data, is a test case evaluation model derived through intelligent algorithms to complete the evaluation of all test cases during the testing process. The Influence Factor Matrix 115 is a coefficient matrix calculated based on the deviation of each influencing factor from the test results during the testing process. It assists the evaluation (How to evaluate 122) model in evaluating all test cases during the testing process.
[0049] In some embodiments of this application, the host computer pre-determines the evaluation model and evaluation matrix of test cases in various functional tests of the intelligent driving controller based on the functional specification description file of the intelligent driving controller, test scenario parameters, and test influencing factor parameters, and uses them to evaluate all test cases during the testing process.
[0050] Optionally, the method further includes: Obtain test cases for the intelligent controller; Execute the test cases and obtain the test case results; The test case results are evaluated based on the test case evaluation model and evaluation matrix to obtain an evaluation score; If the evaluation score is greater than the preset value, the test case corresponding to the evaluation score will be used as the target test case and stored in the test case set. Send the test case set to the hardware-in-the-loop test terminal.
[0051] Specifically, the use case generation module 12 includes: Test case library 121 stores all currently accumulated test cases; The test case calculation module 122 selects or generates test cases for this test based on the existing test cases and test specifications in the test case library 121. The tree-structured evaluation model 114 and the influencing factor matrix 115 evaluate each generated or selected test case, scoring them from three dimensions: test case effectiveness 123, test case coverage 124, and test case complexity 125. For unqualified test cases, the test case calculation module 122 needs to select or calculate them again. Qualified test cases are added to the single test case set 126. The single test case set is 126, containing all the test cases needed for a single test.
[0052] In some embodiments of this application, each test case is evaluated according to the test case evaluation model and evaluation matrix to obtain an evaluation score, and the test case is judged according to the evaluation score to obtain the target test case, which is stored in the test case set. Optionally, the test case results are evaluated based on the test case evaluation model and evaluation matrix to obtain an evaluation score, including: Based on the evaluation model and evaluation matrix of the test cases, the test case results are evaluated to obtain the test case validity score, test case coverage score, and test case complexity value. The evaluation score is determined based on the test case validity score, test case coverage score, and test case complexity score.
[0053] In some embodiments of this application, each generated or selected test case is evaluated, and scores are given from three dimensions: test case validity, test case coverage, and test case complexity. For unqualified test cases, the scores are recalculated, and qualified test cases are added to the test case set.
[0054] Optionally, the method further includes: Based on the pre-set initial scenario parameters, test cases in the target test case set are tested to obtain the test results for the first scenario; If the test results of the first scenario do not meet the preset conditions, the initial scenario parameters are optimized using the dynamic continuous optimization algorithm and the boundary benefit optimization algorithm to obtain the optimized scenario parameters. Based on the optimized scenario parameters, test cases in the target test case set are tested to obtain the second scenario test results, until the obtained second scenario test results meet the preset conditions.
[0055] Specifically, the test scenario parameter generation module 13 includes: The test scenario parameter initialization module 131 generates the required initial scenario parameters based on the test cases in the test set. Then, based on the test effect feedback during the test process, it uses the dynamic continuity optimization algorithm 132 and the boundary benefit optimization algorithm 133 to update the test scenario parameters in real time to ensure that the test scenario can meet the corresponding functional test. The optimal test scenario parameter set 134 contains all the optimal test scenario parameters required for this test, which are used to support the model generation of the 3D scene simulation platform. Some embodiments of this application generate the required initial scenario parameters based on the test cases in the test set, and then update the test scenario parameters in real time using dynamic continuous optimization algorithm and boundary benefit optimization algorithm based on the test effect feedback during the test process, so as to ensure that the test scenario can meet the corresponding functional test.
[0056] Optionally, the hardware-in-the-loop test terminal obtains the test requirements from the start test command, determines the corresponding test cases based on the test requirements, executes the test cases, and obtains the test results corresponding to the start test command, including: The hardware-in-the-loop test terminal constructs a three-dimensional simulation model according to the test requirements. The test requirements include at least vehicle dynamics model information, road model information, and driver model information. The driver model information is used to provide real-time output braking information, throttle, and steering wheel angle for the test requirements. The road model information is used to simulate real-world road scenarios and dynamic simulated road surfaces, and to obtain vehicle status information from the intelligent driving controller in real time. The hardware-in-the-loop test terminal is based on a three-dimensional simulation model and sends a start test command to the intelligent driving controller, so that the intelligent driving controller can make corresponding decisions based on the vehicle driving information in the start test command and obtain the decision results. Receive the decision-making results returned by the intelligent driving controller.
[0057] Figure 4 This is a structural diagram of a HIL simulation test equipment for an automated testing system for intelligent driving, according to an embodiment of the present invention. Further, the HIL simulation test system 2 includes: The automated test management platform 21 can process the selected test cases and realize the automated generation of test sequences 22; The test script generation module 23 encapsulates the generated automated test sequence to generate a test script file that includes signal analysis. Test script implementation module 24 loads the generated test script file and calls the relevant test functions in sequence to realize the fully automated test step execution and result analysis functions. The real-time signal simulator 25 includes a signal conditioning module 251 and a fault injection module 252. The signal conditioning module 251 mainly realizes the signal interaction logic control between the virtual controller and the real controller, while the fault injection module 252 mainly realizes the injection of electronic and electrical faults and the generation of functional interruption conditions to realize the reverse function test of the controller. The 3D scene simulation platform 26 models the input simulation scene parameters, provides a virtual intelligent driving test environment, tracks vehicle status information in real time during the test, and changes the model in real time based on feedback information. Virtual simulation model 27 includes vehicle dynamics model 271, road model 272, and driver model 273, wherein: Vehicle dynamics model 271 is used to execute commands related to the intelligent driving controller; Based on the state information of road model 272 and related dynamic information, the motion state of the whole vehicle is simulated and the vehicle state information is fed back in real time. Road model 272 is used to simulate real vehicle road scenes and dynamic simulated road surfaces according to the working conditions involved in the test. It includes information describing road type, road grade, road surface structure, infrastructure, dynamic driving scenarios and natural environment information. The driver model 273 can output signals such as braking, accelerator and steering wheel angle in real time according to the current test requirements to simulate the operation of a real driver; The signal board 28 includes a CAN board, a LIN board, an IO board, and an Ethernet board, which completes the output of driver operation signals and vehicle status information to intelligent driving control. The signal acquisition module 29 completes the acquisition of the controller feedback signal and outputs it to the three-dimensional scene simulation platform 26, providing data support for updating the simulation scene parameters. The three-dimensional scene simulation platform 26 adjusts the road and vehicle status information in real time through the feedback signal, forming a closed loop.
[0058] The test defect tracking module 210 tracks and records all unexpected results that occur during the test, analyzes and records them according to the result evaluation criteria, and generates an evaluation document. After the test is completed, the test report generation module 211 simplifies and integrates all defect evaluation reports to generate a standard test report document. Test report library 212 stores all test report documents accumulated from a single test.
[0059] Some embodiments of this application address the testing requirements of intelligent driving controllers. A 3D scene simulation platform generates a corresponding dynamic driving model. According to the test sequence requirements, the script execution module controls the simulation board to send corresponding control signals to the intelligent driving controller unit. The intelligent driving controller makes corresponding decisions based on the received vehicle driving information and control signal requests, and feeds back the results to the defect tracking module for analysis and evaluation. If the expected results are met, the testing steps continue.
[0060] Figure 5 This is a schematic diagram of the testing workflow for an automated testing system for intelligent driving, according to an embodiment of the present invention, including: (1) In response to the testing requirements of the intelligent driving controller, the three-dimensional scene simulation platform generates a corresponding dynamic driving model. According to the test sequence requirements, the script execution module controls the simulation board to send the corresponding control signals to the intelligent driving controller unit. The intelligent driving controller makes corresponding decisions based on the received vehicle driving information and control signal requests, and feeds back the result signals to the defect tracking module for result analysis and evaluation. If the expected results are met, the test steps continue.
[0061] (2) The script execution module controls the IO board to send the corresponding exit signal to the intelligent driving controller unit or generate functional faults or interrupt conditions. After receiving the corresponding signal, the intelligent driving controller responds accordingly and feeds back the result signal to the defect tracking module for result analysis and evaluation. If the expected result is met, the test steps continue.
[0062] (3) The results recording module records the vehicle routes during the test and calculates scores for each item of the vehicle route planning results according to the pre-set evaluation criteria. It also judges the test complexity and coverage. If there are items with low scores or insufficient test complexity and coverage, the stress test will be repeated or new test cases will be added and additional tests will be performed. After all test steps are completed, all test results are compiled and a test report is generated according to the standard template.
[0063] The embodiments of this application can intelligently provide the necessary test environment for driving system testing, such as traffic, roads, and weather, based on functional specifications and other documents. Furthermore, the provided system test environment and scenarios have characteristics such as high dimensionality, high logic, and high reliability, enabling efficient, thorough, and comprehensive automated testing of the functionality, safety, and reliability of intelligent driving control.
[0064] This invention provides a highly efficient automated simulation testing system for vehicle functions. The system includes a test case generation and evaluation system and a HIL simulation testing system, enabling 3D scenario modeling, intelligent test case execution, and result analysis and report generation. This system utilizes intelligent algorithms to objectively describe engineers' subjective experience and establishes a corresponding importance calculation model. It can automatically generate test cases and indirectly evaluate their effectiveness. Compared to manual test case writing, it can improve the average complexity of test cases by more than 70%. This enhances the dynamics and continuity of the test scenario while improving the efficiency of system fault detection. Furthermore, the system can fully automate the test process, reducing the average evaluation execution time of experimental scenarios to less than 5% of that of manual methods.
[0065] It should be noted that each of the implementable methods in this embodiment can be implemented individually or in any combination without conflict. This application does not limit this.
[0066] Another embodiment of this application provides a simulation testing device for an intelligent driving controller, used to execute the simulation testing method for the intelligent driving controller provided in the above embodiment.
[0067] like Figure 6 The diagram shown is a structural schematic of a simulation testing device for an intelligent driving controller provided in an embodiment of this application. The simulation testing device for the intelligent driving controller includes a transmitting module 601 and a receiving module 602, wherein: The sending module 601 is used to respond to a pre-set test sequence and sequentially send test instructions in the test sequence to the hardware-in-the-loop test terminal, so that the hardware-in-the-loop test terminal controls the intelligent driving controller to perform test operations corresponding to the test instructions and obtain test results corresponding to the test instructions; wherein, the test sequence includes at least a start test instruction, an interrupt test instruction, and an end test instruction; The receiving module 602 is used to receive the test results returned by the hardware-in-the-loop test terminal.
[0068] Regarding the apparatus in this embodiment, the specific manner in which each module performs its operations has been described in detail in the embodiments related to the method, and will not be elaborated upon here.
[0069] Some embodiments of this application pre-set test sequences, including the functional items to be tested, as well as the test time and test order. When testing the intelligent driving controller, the host computer sends test instructions in the pre-set test sequence to the hardware-in-the-loop test terminal in sequence. This causes the hardware-in-the-loop test terminal to control the intelligent driving controller to execute the test operations corresponding to the test instructions, obtaining the test results corresponding to the test instructions. This eliminates the need for significant manpower and resources to test the intelligent driving controller, achieving test automation. It not only improves test efficiency but also reduces errors in test case generation, thus improving test accuracy.
[0070] Another embodiment of this application further supplements the description of the simulation test device for the intelligent driving controller provided in the above embodiments.
[0071] Optionally, the receiving module is also used for: The hardware-in-the-loop test terminal obtains the test requirements from the start test command and determines the corresponding test cases based on the test requirements; it executes the test cases and obtains the test results corresponding to the start test command. The test cases are determined based on a pre-stored set of test cases. Some embodiments of this application pre-set test sequences, and according to the test instructions in the test sequence, send the start test instruction to the hardware-in-the-loop test terminal in sequence. The control simulation board sends the corresponding control signal to the intelligent driving controller unit. The intelligent driving controller makes corresponding decision judgments based on the received vehicle driving information and control signal requests, and feeds back the result signal to the defect tracking module for result analysis and evaluation. If the expected result is met, the test steps continue.
[0072] Optionally, the device further includes a setup module, which is used for: Obtain the functional specification description file of the intelligent driving controller, test scenario parameters, and test influencing factor parameters; Based on the functional specification description document of the intelligent driving controller, test scenario parameters, and test influencing factor parameters, determine the evaluation model of the test cases; The evaluation matrix is determined based on the parameters of the influencing factors tested.
[0073] In some embodiments of this application, the host computer pre-determines the evaluation model and evaluation matrix of test cases in various functional tests of the intelligent driving controller based on the functional specification description file of the intelligent driving controller, test scenario parameters, and test influencing factor parameters, and uses them to evaluate all test cases during the testing process.
[0074] Optionally, modules are created for: Obtain test cases for the intelligent controller; Execute the test cases and obtain the test case results; The test case results are evaluated based on the test case evaluation model and evaluation matrix to obtain an evaluation score; If the evaluation score is greater than the preset value, the test case corresponding to the evaluation score will be used as the target test case and stored in the test case set. Send the test case set to the hardware-in-the-loop test terminal.
[0075] In some embodiments of this application, each test case is evaluated according to the test case evaluation model and evaluation matrix to obtain an evaluation score, and the test case is judged according to the evaluation score to obtain the target test case, which is stored in the test case set. Optionally, modules are created for: Based on the evaluation model and evaluation matrix of the test cases, the test case results are evaluated to obtain the test case validity score, test case coverage score, and test case complexity value. The evaluation score is determined based on the test case validity score, test case coverage score, and test case complexity score.
[0076] In some embodiments of this application, each generated or selected test case is evaluated, and scores are given from three dimensions: test case validity, test case coverage, and test case complexity. For unqualified test cases, the scores are recalculated, and qualified test cases are added to the test case set.
[0077] Optionally, modules are created for: Based on the pre-set initial scenario parameters, test cases in the target test case set are tested to obtain the test results for the first scenario; If the test results of the first scenario do not meet the preset conditions, the initial scenario parameters are optimized using the dynamic continuous optimization algorithm and the boundary benefit optimization algorithm to obtain the optimized scenario parameters. Based on the optimized scenario parameters, test cases in the target test case set are tested to obtain the second scenario test results, until the obtained second scenario test results meet the preset conditions.
[0078] Some embodiments of this application generate the required initial scenario parameters based on the test cases in the test set, and then update the test scenario parameters in real time using dynamic continuous optimization algorithm and boundary benefit optimization algorithm based on the test effect feedback during the test process, so as to ensure that the test scenario can meet the corresponding functional test.
[0079] Optionally, the sending module is used for: The hardware-in-the-loop test terminal constructs a three-dimensional simulation model according to the test requirements. The test requirements include at least vehicle dynamics model information, road model information, and driver model information. The driver model information is used to provide real-time output braking information, throttle, and steering wheel angle for the test requirements. The road model information is used to simulate real-world road scenarios and dynamic simulated road surfaces, and to obtain vehicle status information from the intelligent driving controller in real time. The hardware-in-the-loop test terminal is based on a three-dimensional simulation model and sends a start test command to the intelligent driving controller, so that the intelligent driving controller can make corresponding decisions based on the vehicle driving information in the start test command and obtain the decision results. Receive the decision-making results returned by the intelligent driving controller.
[0080] Some embodiments of this application address the testing requirements of intelligent driving controllers. A 3D scene simulation platform generates a corresponding dynamic driving model. According to the test sequence requirements, the script execution module controls the simulation board to send corresponding control signals to the intelligent driving controller unit. The intelligent driving controller makes corresponding decisions based on the received vehicle driving information and control signal requests, and feeds back the results to the defect tracking module for analysis and evaluation. If the expected results are met, the testing steps continue.
[0081] Regarding the apparatus in this embodiment, the specific manner in which each module performs its operations has been described in detail in the embodiments related to the method, and will not be elaborated upon here.
[0082] It should be noted that each of the implementable methods in this embodiment can be implemented individually or in any combination without conflict. This application does not limit this.
[0083] This application also provides a computer-readable storage medium storing a computer program thereon. When the program is executed by a processor, it can implement the operation of any of the methods corresponding to the embodiments of the simulation test method for the intelligent driving controller provided in the above embodiments.
[0084] This application also provides a computer program product, which includes a computer program, wherein when the computer program is executed by a processor, it can implement the operation of any of the methods corresponding to the embodiments of the simulation test method for the intelligent driving controller provided in the above embodiments.
[0085] like Figure 7As shown, some embodiments of this application provide an electronic device 500, which includes: a memory 510, a processor 520, and a computer program stored in the memory 510 and executable on the processor 520. When the processor 520 reads the program from the memory 510 via a bus 530 and executes the program, it can implement any of the methods included in the above-described simulation test method for an intelligent driving controller.
[0086] Processor 520 can process digital signals and can include various computing architectures. For example, it can be a complex instruction set computer architecture, a reduced instruction set computer architecture, or an architecture that implements multiple instruction set combinations. In some examples, processor 520 can be a microprocessor.
[0087] The memory 510 can be used to store instructions executed by the processor 520 or data related to the execution of instructions. These instructions and / or data may include code for implementing some or all of the functions of one or more modules described in the embodiments of this application. The processor 520 of this disclosure embodiment can be used to execute the instructions in the memory 510 to implement the methods shown above. The memory 510 includes dynamic random access memory, static random access memory, flash memory, optical memory, or other memories well known to those skilled in the art.
[0088] The above are merely embodiments of this application and are not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application. It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.
[0089] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
[0090] 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.
Claims
1. A simulation testing method for an intelligent driving controller, characterized in that, The method includes: In response to a pre-set test sequence, test instructions in the test sequence are sent sequentially to a hardware-in-the-loop test terminal, so that the hardware-in-the-loop test terminal controls the intelligent driving controller to perform test operations corresponding to the test instructions and obtain test results corresponding to the test instructions; wherein, the test sequence includes at least a start test instruction, an interrupt test instruction, and an end test instruction; Receive the test results returned by the hardware-in-the-loop test terminal.
2. The simulation testing method for the intelligent driving controller according to claim 1, characterized in that, If the test command is a start test command, the hardware-in-the-loop test terminal controls the intelligent driving controller to execute the test operation corresponding to the test command, and obtains the test result corresponding to the test command, including: The hardware-in-the-loop test terminal obtains the test requirements in the start test instruction and determines the corresponding test cases based on the test requirements; executes the test cases to obtain the test results corresponding to the start test instruction, wherein the test cases are determined based on a pre-stored test case set.
3. The simulation testing method for the intelligent driving controller according to claim 2, characterized in that, Before sequentially sending the test commands in the test sequence to the hardware-in-the-loop test terminal, the method includes: Obtain the functional specification description file of the intelligent driving controller, test scenario parameters, and test influencing factor parameters; Based on the functional specification description document of the intelligent driving controller, test scenario parameters, and test influencing factor parameters, determine the evaluation model of the test cases; The evaluation matrix is determined based on the parameters of the test influencing factors.
4. The simulation testing method for the intelligent driving controller according to claim 3, characterized in that, The method further includes: Obtain test cases for the intelligent controller; Execute the test cases and obtain the test case results; The test case results are evaluated based on the evaluation model and evaluation matrix to obtain an evaluation score. If the evaluation score is greater than a preset value, the test case corresponding to the evaluation score will be used as the target test case and stored in the test case set. The test case set is sent to the hardware-in-the-loop test terminal.
5. The simulation test method for the intelligent driving controller according to claim 4, characterized in that, The evaluation of the test case results based on the evaluation model and the evaluation matrix, to obtain an evaluation score, includes: Based on the evaluation model and evaluation matrix of the test cases, the results of the test cases are evaluated to obtain the test case validity score, test case coverage score, and test case complexity value. The evaluation score is determined based on the test case validity score, test case coverage score, and test case complexity score.
6. The simulation testing method for the intelligent driving controller according to claim 2, characterized in that, The method further includes: Based on the pre-set initial scenario parameters, test cases in the target test case set are tested to obtain the first scenario test results; If the test results of the first scenario do not meet the preset conditions, the initial scenario parameters are optimized using the dynamic continuous optimization algorithm and the boundary benefit optimization algorithm to obtain the optimized scenario parameters; Based on the optimized scenario parameters, test cases in the target test case set are tested to obtain the second scenario test results, until the obtained second scenario test results meet the preset conditions.
7. The simulation test method for the intelligent driving controller according to claim 2, characterized in that, The hardware-in-the-loop test terminal acquires the test requirements from the start test command, determines the corresponding test cases based on the test requirements, executes the test cases, and obtains the test results corresponding to the start test command, including: The hardware-in-the-loop test terminal constructs a three-dimensional simulation model according to the test requirements. The test requirements include at least vehicle dynamics model information, road model information, and driver model information. The driver model information is used to provide real-time output braking information, throttle, and steering wheel angle for the test requirements. The road model information is used to simulate real-world road scenarios and dynamic simulated road surfaces, and to obtain vehicle status information from the intelligent driving controller in real time. The hardware-in-the-loop test terminal, based on the three-dimensional simulation model, sends the start test command to the intelligent driving controller, so that the intelligent driving controller can make corresponding decision judgments based on the vehicle driving information in the start test command and obtain the decision judgment result. Receive the decision judgment result returned by the intelligent driving controller.
8. A simulation testing device for an intelligent driving controller, characterized in that, The device includes: The sending module is configured to, in response to a pre-set test sequence, sequentially send test instructions in the test sequence to a hardware-in-the-loop test terminal, so that the hardware-in-the-loop test terminal controls the intelligent driving controller to perform test operations corresponding to the test instructions and obtain test results corresponding to the test instructions; wherein, the test sequence includes at least a start test instruction, an interrupt test instruction, and an end test instruction; A receiving module is used to receive the test results returned by the hardware-in-the-loop test terminal.
9. The simulation testing device for the intelligent driving controller according to claim 8, characterized in that, The receiving module is further configured to: The hardware-in-the-loop test terminal obtains the test requirements in the start test instruction and determines the corresponding test cases based on the test requirements; executes the test cases to obtain the test results corresponding to the start test instruction, wherein the test cases are determined based on a pre-stored test case set.
10. The simulation testing device for the intelligent driving controller according to claim 8, characterized in that, The apparatus further includes a setup module, the setup module being used for: Obtain the functional specification description file of the intelligent driving controller, test scenario parameters, and test influencing factor parameters; Based on the functional specification description document of the intelligent driving controller, test scenario parameters, and test influencing factor parameters, determine the evaluation model of the test cases; The evaluation matrix is determined based on the parameters of the test influencing factors.
11. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, it can implement the simulation test method of the intelligent driving controller according to any one of claims 1-7.
12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, characterized in that, when the program is executed by a processor, it can implement the simulation test method of the intelligent driving controller according to any one of claims 1-7.
Citation Information
Patent Citations
Lane keeping test system and method based on virtual driving system
CN114911173A
Test case quality evaluation method and device based on machine learning and electronic equipment
CN117609056A
Automatic test case generation method based on large model and particle swarm optimization
CN119271565A
Test case evaluation method, device and storage medium
CN119759746A
Method and apparatus for testing and evaluating a software component using an abstraction matrix
US20030037314A1