CN115327953A - Simulation test method and device for intelligent driving algorithm, electronic equipment and medium - Google Patents

Abstract

The application relates to the technical field of intelligent driving test, in particular to a simulation test method, a simulation test device, electronic equipment and a medium for an intelligent driving algorithm, wherein the method comprises the following steps: when the simulation model enters a preset working condition after the test of the last test step is detected to be completed, judging that the current test step meets the preset test condition, and executing the test operation of the target intelligent driving algorithm to obtain the test result of the current test step; and sequentially testing all the testing steps, or when the simulation model does not enter a preset working condition and the current testing step does not meet the preset testing condition, ending the simulation test, and determining that the target intelligent driving algorithm is qualified, unqualified or incomplete according to the testing result of at least one testing step. Therefore, the problems that a test method in the related art consumes a large amount of resources to carry out scene simulation test, and the early stage is not suitable for large-scale scene coverage verification and the like for agile development are solved.

Description

Simulation test method and device for intelligent driving algorithm, electronic equipment and medium

Technical Field

The present disclosure relates to the field of intelligent driving test technologies, and in particular, to a simulation test method and apparatus for an intelligent driving algorithm, an electronic device, and a medium.

Background

In the related art, the intelligent driving vehicle test method adopts an intelligent driving vehicle real vehicle scene or road experiment to verify various functions and algorithms of the intelligent driving vehicle.

However, the test method of the related art is based on scene coverage, rather than forward case design, and has no structural test solution, when a vehicle performs an actual vehicle scene experiment, a large amount of resources are consumed to perform a scene simulation test, the cost is high, and for agile development, the early stage is not suitable for large-scale scene coverage verification.

Disclosure of Invention

The application provides a simulation test method, a simulation test device, electronic equipment and a simulation test medium for an intelligent driving algorithm, and aims to solve the problems that a test method in the related art consumes a large amount of resources to perform scene simulation test, and is not suitable for large-scale scene coverage verification in an early stage for agile development.

An embodiment of a first aspect of the present application provides a simulation test method for an intelligent driving algorithm, including the following steps: detecting whether the simulation model enters a preset working condition or not after the test of the last test step is finished; when the simulation model enters a preset working condition, judging that the current testing step meets a preset testing condition, and executing the testing operation of the target intelligent driving algorithm to obtain a testing result of the current testing step; and sequentially testing all the testing steps, or when the simulation model does not enter a preset working condition and the current testing step is judged not to meet the preset testing condition, ending the simulation test, and determining that the target intelligent driving algorithm is qualified in testing, unqualified in testing or incomplete in testing according to the testing result of at least one testing step.

According to the technical means, the simulation test on the logic scene can be automatically carried out on the intelligent driving algorithm, the completion condition of the last test step is used as the test starting condition of the current test step, the test of the current step is started after the last test is completed, the test step is extended on a time domain, the continuity of the test scene is realized, the test requirement on the logic scene in the early development stage is met, the test coverage in a large number of scenes of a parameter space is not needed, the test scene is accurate and controllable, the number of the test scenes can be greatly reduced, meanwhile, a real-vehicle road test is not needed, the cost of the simulation test can be reduced, and the defects of the functional logic of the intelligent driving algorithm can be found in the early development stage.

Optionally, in an embodiment of the present application, the determining that the target smart driving algorithm is qualified, unqualified or incomplete according to the test result of the at least one test step includes: detecting whether the test result of any test step meets a preset qualified condition or not; when the test result of any test step does not meet the preset qualified condition, judging that the target intelligent driving algorithm is unqualified in test, and when the test result of any test step meets the preset qualified condition, detecting whether a blockage record exists in the test step; if the blockage records do not exist, the target intelligent driving algorithm is judged to be qualified in the test, if the blockage records exist and the test blockage of the last test step is identified, the target intelligent driving algorithm is judged to be unfinished in the test, otherwise, the target intelligent driving algorithm is judged to be unqualified in the test.

According to the technical means, multiple indexes of the intelligent driving algorithm can be tested based on the result of the automatic logic test, specific defect types which are unqualified in test are given, simulation test coverage is carried out without a large number of scenes of a parameter space, the test scenes are accurate and controllable, the number of the test scenes can be greatly reduced, a real vehicle road test is not needed, the cost of the simulation test can be reduced, and the defects of the functional logic of the intelligent driving algorithm can be found in the early development stage.

Optionally, in an embodiment of the application, when it is determined that the current testing step does not meet the preset testing condition, before ending the simulation testing, the method includes: detecting the duration of the simulation model which does not enter a preset working condition; and when the duration is longer than the preset duration, judging that the current testing step meets the blocking condition, recording the testing blocking of the current testing step, and ending the simulation test, otherwise, continuously judging whether the current testing step meets the preset testing condition.

According to the technical means, when the test condition is not met, the simulation is finished when the length of time which is not met is longer than a certain length of time, so that the misjudgment condition possibly caused by immediately finishing the simulation is avoided, and the test accuracy and the reliability are improved.

Optionally, in an embodiment of the present application, before detecting whether the simulation model enters the preset working condition after the test of the previous test step is completed, the method includes: detecting whether the simulation model and all the associated subsystems meet normal operation conditions; if the normal running condition is met, judging whether the current testing step meets the preset testing condition, otherwise, judging that the current testing step is blocked in testing, and ending the simulation testing.

According to the technical means, whether the simulation model and all the associated subsystems operate normally or not is detected during testing, whether the testing conditions are met or not is continuously judged when the simulation model and all the associated subsystems operate normally, and the testing step is judged to be blocked when the simulation model and all the associated subsystems operate abnormally, so that the testing can be guaranteed when the simulation model and all the associated subsystems operate normally, the interference of the abnormal operation of the simulation model and all the associated subsystems on the simulation testing is avoided, and the accuracy of the testing result is improved.

Optionally, in an embodiment of the present application, before performing the simulation test of the first test step, the method includes: acquiring at least one piece of test step information of a target intelligent driving algorithm, wherein each piece of test step information comprises a test condition, an execution operation and a blocking condition; and generating an execution script according to the at least one piece of test step information, and sequentially carrying out simulation test on the target intelligent driving algorithm according to the test steps based on the execution script to obtain a test result corresponding to the test steps.

According to the technical means, the test script can be automatically generated by the user providing the test step information, and automatic simulation test is carried out based on the test script, so that a test personnel programming test program is not needed, the functional logic test requirement of the intelligent driving algorithm can be met by only providing the test requirement, the test of the test personnel is more convenient, the convenience of the simulation test is improved, and the use experience of the user is improved.

The embodiment of the second aspect of the present application provides a simulation test device for an intelligent driving algorithm, including: the first detection module is used for detecting whether the simulation model enters a preset working condition after the test of the previous test step is finished; the first judgment module is used for judging that the current testing step meets the preset testing condition when the simulation model enters the preset working condition, and executing the testing operation of the target intelligent driving algorithm to obtain the testing result of the current testing step; and the test module is used for sequentially testing and completing all the test steps, or when the simulation model does not enter a preset working condition and the current test step is judged not to meet the preset test condition, ending the simulation test and determining that the target intelligent driving algorithm is qualified in test, unqualified in test or incomplete in test according to the test result of at least one test step.

Optionally, in an embodiment of the present application, the test module is further configured to detect whether a test result of any test step meets a preset qualification condition; when the test result of any test step does not meet the preset qualified condition, judging that the target intelligent driving algorithm is unqualified in test, and when the test result of any test step meets the preset qualified condition, detecting whether a blockage record exists in the test step; if the blockage records do not exist, the target intelligent driving algorithm is judged to be qualified in the test, if the blockage records exist and the test blockage of the last test step is identified, the target intelligent driving algorithm is judged to be unfinished in the test, otherwise, the target intelligent driving algorithm is judged to be unqualified in the test.

Optionally, in an embodiment of the present application, before ending the simulation test when it is determined that the current testing step does not satisfy the preset testing condition, the method includes: the second detection module is used for detecting the duration of the simulation model which does not enter the preset working condition; and the second judgment module is used for judging that the current testing step meets the blocking condition when the duration is longer than the preset duration, recording the testing blocking of the current testing step, and ending the simulation test, otherwise, continuously judging whether the current testing step meets the preset testing condition.

Optionally, in an embodiment of the present application, before detecting whether the simulation model enters the preset working condition after the test of the previous test step is completed, the method includes: the third detection module is used for detecting whether the simulation model and all the associated subsystems meet normal operation conditions; and the third judging module is used for judging whether the current testing step meets the preset testing condition or not if the normal running condition is met, otherwise, judging that the current testing step is blocked in the testing process, and ending the simulation testing.

Optionally, in an embodiment of the present application, before performing the simulation test of the first test step, the method includes: the system comprises an acquisition module, a processing module and a control module, wherein the acquisition module is used for acquiring at least one piece of test step information of a target intelligent driving algorithm, and each piece of test step information comprises a test condition, an execution operation and a blocking condition; and the generating module is used for generating an execution script according to the at least one piece of test step information, and sequentially carrying out simulation test on the target intelligent driving algorithm according to the test steps based on the execution script to obtain a test result corresponding to the test steps.

An embodiment of a third aspect of the present application provides an electronic device, including: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement a simulation test of the intelligent driving algorithm as described in the embodiments above.

A fourth aspect of the present application provides a computer-readable storage medium, on which a computer program is stored, where the program is executed by a processor, so as to implement a simulation test of an intelligent driving algorithm as described in the foregoing embodiments.

Therefore, the application has at least the following beneficial effects:

1. the method can automatically perform simulation test on a logic scene on the intelligent driving algorithm, the completion condition of the last test step is used as the test starting condition of the current test step, and the test of the current step is started after the last test is completed, so that the test steps are extended in a time domain, the continuity of the test scene is realized, and the test requirement on the logic scene in the early development stage is met, therefore, test coverage is not required to be performed in a large number of scenes in a parameter space, the test scene is accurate and controllable, the number of the test scenes can be greatly reduced, meanwhile, a real vehicle road test is not required, the cost of the simulation test can be reduced, and the defect of the functional logic of the intelligent driving algorithm can be found in the early development stage.

2. The method has the advantages that multiple indexes of the intelligent driving algorithm can be tested based on the result of the automatic logic test, specific defect types which are unqualified in the test are given, simulation test coverage is carried out without a large number of scenes of parameter space, the test scenes are accurate and controllable, the number of the test scenes can be greatly reduced, meanwhile, real-vehicle road tests are not needed, the cost of the simulation test can be reduced, and the defects of the functional logic of the intelligent driving algorithm can be discovered in the early development stage.

3. When the test condition is not met, the simulation is finished when the length of time which is not met is longer than a certain length of time, the misjudgment condition possibly caused by immediately finishing the simulation is avoided, and the test accuracy and the reliability are improved.

4. Whether the simulation model and all the associated subsystems operate normally is detected during testing, whether the testing conditions are met or not is continuously judged when the simulation model and all the associated subsystems operate normally, and the testing step is judged to be blocked when the simulation model and all the associated subsystems operate abnormally, so that the simulation test can be ensured to be performed when the simulation model and all the associated subsystems operate normally, the interference of the abnormal operation of the simulation model and all the associated subsystems on the simulation test is avoided, and the accuracy of the test result is improved.

5. The user provides test step information and can automatically generate the test script, carries out automatic simulation test based on the test script to need not the tester and programme the test program, only need provide the test demand and can satisfy the functional logic test demand of intelligent driving algorithm, the tester test of being convenient for more promotes the convenience of simulation test simultaneously, promotes user's use and experiences.

Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.

Drawings

The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:

FIG. 1 is a flow chart of a simulation testing method for an intelligent driving algorithm according to an embodiment of the present application;

FIG. 2 is a flow chart of an intelligent driving algorithm simulation test execution provided in accordance with an embodiment of the present application;

FIG. 3 is a block diagram illustrating a simulation testing apparatus for an intelligent driving algorithm according to an embodiment of the present disclosure;

fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Description of reference numerals: a first detection module-100, a first judgment module-200, a test module-300, a memory-401, a processor-402, and a communication interface-403.

Detailed Description

Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative and intended to explain the present application and should not be construed as limiting the present application.

A simulation test method, a simulation test device, an electronic apparatus, and a storage medium for an intelligent driving algorithm according to embodiments of the present application are described below with reference to the accompanying drawings. In order to solve the problems mentioned in the background technology, the application provides a simulation test method of an intelligent driving algorithm, wherein in the method, whether a simulation model enters a preset working condition or not is detected after the test of the previous test step is finished; when the simulation model enters a preset working condition, judging that the current testing step meets a preset testing condition, and executing the testing operation of the target intelligent driving algorithm to obtain a testing result of the current testing step; and sequentially testing all the testing steps, or when the simulation model does not enter the preset working condition and the current testing step is judged not to meet the preset testing condition, ending the simulation test, and determining that the target intelligent driving algorithm is qualified in test, unqualified in test or incomplete in test according to the testing result of at least one testing step. Through the automatic simulation test, the number of test scenes can be effectively reduced, more problems can be found, and the time for analyzing and classifying the problem data afterwards can be saved. Therefore, the problems that a test method in the related technology consumes a large amount of resources to carry out scene simulation test, and the early stage is not suitable for large-scale scene coverage verification and the like for agile development are solved.

Specifically, fig. 1 is a schematic flow chart of a simulation testing method of an intelligent driving algorithm provided in an embodiment of the present application.

As shown in fig. 1, the simulation test method of the intelligent driving algorithm includes the following steps:

in step S101, it is detected whether the simulation model enters a preset working condition after the test in the previous test step is completed.

The preset working condition may be understood as a design working condition where a tester expects a simulation model to enter after a test, and may be specifically set according to actual test requirements, without specific limitations.

It can be understood that, in the embodiment of the present application, after the test of each test step is finished, whether the simulation model enters the design working condition is detected, and in the specific implementation, whether the working condition of the required design is reached can be determined by observing the state of the internal signal.

In step S102, when the simulation model enters a preset condition, it is determined that the current testing step meets a preset testing condition, and a testing operation of the target intelligent driving algorithm is performed to obtain a testing result of the current testing step.

It can be understood that if the test of the previous test step is completed and the design condition is entered, it can be determined that the current test step meets the preset test condition, because the passing condition after the test of the previous test step is completed in the embodiment of the present application is used as the test condition for starting the test of the current step, the test step is extended in the time domain, the continuity of the test scenario is realized, the test requirement of the agile development early stage on the logic scenario is met, the test coverage in a large number of scenarios in the parameter space is not needed, the test scenario is accurate and controllable, the number of the test scenarios can be greatly reduced, meanwhile, the real vehicle road test is not needed, the cost of the simulation test can be reduced, and the defect of the intelligent driving algorithm functional logic can be found in the development early stage.

According to the embodiment of the application, after the current testing step meets the preset testing condition, the testing script of the testing step is generated by calling the preset program, and the testing is executed. The test script reads the internal or external signal of the tested algorithm in real time to judge whether the algorithm is in the running state of a certain step described by the requirement and design, thereby obtaining the test result of the current test step.

For example, in the test execution operation, the description is "signal a = x", that is, at this time, the closed-loop signal of signal a is cut off, and x is transmitted to the object to be measured as an analog value. Thereby achieving the purpose of fault injection. When the description is ' controlling the front vehicle to start at the acceleration of 1m/s 2, the target speed is 60kph ' and the like ', the embodiment of the application can carry out semantic segmentation on the statement through a natural language processing program, thereby calling a plurality of preset programs for controlling the traffic participants and sending information to simulation software to change the vehicle behavior.

In step S103, all the testing steps are sequentially tested, or when the simulation model does not enter the preset working condition and the current testing step is determined not to satisfy the preset testing condition, the simulation testing is ended, and the target intelligent driving algorithm is determined to be qualified, unqualified or incomplete according to the testing result of at least one testing step.

It can be understood that, in the embodiment of the application, when all the test steps meet the passing condition, all the tests are sequentially executed according to the steps, the logic test requirement of the intelligent driving algorithm is met, and when the test of any test step fails, the simulation test is ended, so that the qualification judgment of the target intelligent driving algorithm can be realized according to the reason of the end of the simulation test, the target intelligent driving algorithm can be analyzed according to the test result, more problems can be found, and the time for analyzing and classifying the problem data afterwards can be saved.

In one embodiment of the present application, determining that the target smart driving algorithm is qualified, unqualified or incomplete according to the test result of the at least one test step includes: detecting whether the test result of any test step meets a preset qualified condition; when the test result of any test step does not meet the preset qualified condition, judging that the target intelligent driving algorithm is unqualified in test, and when the test result of any test step meets the preset qualified condition, detecting whether a blockage record exists in the test step; and if the blockage record does not exist, judging that the target intelligent driving algorithm test is qualified, if the blockage record exists and the test blockage of the last test step is identified, judging that the target intelligent driving algorithm test is not finished, otherwise, judging that the target intelligent driving algorithm test is unqualified.

According to the embodiment of the application, when the algorithm meets a certain test condition (including but not limited to external scene information and an algorithm internal state), a certain event is triggered, and whether the output result of the algorithm meets the requirement or not is observed. As shown in fig. 2, after the simulation test is performed, the embodiment of the present application may analyze the test data according to the index of subjective and objective evaluation, for example, maximum acceleration and deceleration, minimum inter-vehicle distance, kilometer compaction line length, maximum transverse speed, and the like. When the evaluation index can not meet the requirement, the target intelligent driving algorithm test can be judged to be unqualified, and the unsatisfied part is analyzed. And when all the steps are correctly executed and the statistical evaluation index is met, the test qualification of the target intelligent driving algorithm can be judged. When the test step in the last step is blocked or the statistical evaluation index is not met, it can be judged that the system is not normally processed under a reasonable working condition due to bug in the algorithm, and the target intelligent driving algorithm test is not completed. When the case is blocked midway, the target intelligent driving algorithm test can be judged to be unqualified.

In an embodiment of the present application, when it is determined that the current testing step does not satisfy the preset testing condition, before ending the simulation testing, the method includes: detecting the duration of the simulation model which does not enter a preset working condition; and when the duration is longer than the preset duration, judging that the current testing step meets the blocking condition, recording the testing blocking of the current testing step, and ending the simulation test, otherwise, continuously judging whether the current testing step meets the preset testing condition.

It can be understood that, when it is determined that the current test step does not satisfy the preset test condition, before the simulation test is finished, whether the current test step is blocked or not is determined by detecting the duration of the simulation model entering the preset working condition. And when the duration time does not reach the preset duration time, continuously judging whether the current test step meets the preset test condition or not until the simulation model enters the preset working condition, executing the test operation of the target intelligent driving algorithm, and obtaining the test result of the current test step, so that the misjudgment condition possibly caused by immediately finishing the simulation is avoided, and the test accuracy and the reliability are improved. The preset time may be determined according to actual conditions, and is not particularly limited.

In an embodiment of the present application, before detecting whether the simulation model enters the preset working condition after the test of the previous test step is completed, the method includes: detecting whether the simulation model and all the associated subsystems meet normal operation conditions or not; if the normal operation condition is met, judging whether the current testing step meets the preset testing condition, otherwise, judging that the current testing step tests the blockage, and ending the simulation test.

According to the embodiment of the application, firstly, the normal operation of the subsystem associated with the simulation model needs to be ensured, so that the scene in a line scope can be correctly processed according to the requirement design, when the normal operation condition is met, whether the current test step enters the preset working condition after the test of the last test step is completed is judged, when the normal operation condition is not met, the test blockage of the current test step can be judged, the simulation test is finished by the system, the test is ensured to be carried out when the simulation model and all the associated subsystems operate normally, the interference of the abnormal operation of the simulation model and all the associated subsystems on the simulation test is avoided, and the accuracy of the test result is improved.

It should be noted that in the simulation test method for the intelligent driving algorithm provided by the present application, the test object includes, but is not limited to, a model developed by simulink, an automatically generated or handwritten C + + code, and an ECU controller for burning the algorithm, so as to realize the simulation test of the algorithm in the loop, such as MIL (model in loop), SIL (software in loop), and HIL (hardware in loop).

In one embodiment of the present application, before performing the simulation test of the first test step, the method includes: acquiring at least one piece of test step information of a target intelligent driving algorithm, wherein each piece of test step information comprises a test condition, an execution operation and a blocking condition; and generating an execution script according to the information of the at least one test step, and sequentially carrying out simulation test on the target intelligent driving algorithm according to the test steps based on the execution script to obtain a test result corresponding to the test steps.

It will be appreciated that a simulation test case may have multiple test step information, each test step information including test conditions, execution operations, and blocking conditions. As shown in fig. 2, when it is detected that the simulation model and all the associated subsystems meet the normal operation condition and the current test step meets the preset test condition, the execution script of the test step may be generated by calling the preset program, and the execution script may read the internal or external signal of the tested algorithm in real time to determine whether the algorithm is in the operation state of a certain step described by the requirement and design.

In the actual execution overstroke, the script in the embodiment of the present application may obtain whether the tree algorithm meets the requirement design in the above judgment, so as to find the defect of the algorithm logic at an early stage of development.

According to the simulation test method of the intelligent driving algorithm, when a simulation model enters a preset working condition and a current test step meets a preset test condition, a test script of the current test step is generated by calling a preset program, test operation is executed to obtain a test result, all test steps of a test case are executed in sequence, when the simulation model does not enter the preset working condition and the current test step is judged not to meet the preset test condition, the simulation test is finished, and the target intelligent driving algorithm is determined to be qualified, unqualified or unfinished according to the test result of at least one test step. By constructing continuous scenes for simulation test, the number of test scenes can be effectively reduced, more problems can be found, and the time for analyzing and classifying problem data afterwards can be saved. Therefore, the problems that a test method in the related technology consumes a large amount of resources to carry out scene simulation test, and the early stage is not suitable for large-scale scene coverage verification and the like for agile development are solved.

Next, a simulation test device of an intelligent driving algorithm according to an embodiment of the present application is described with reference to the accompanying drawings.

Fig. 3 is a block diagram illustrating a simulation testing apparatus for an intelligent driving algorithm according to an embodiment of the present application.

As shown in fig. 3, the simulation test apparatus 10 for an intelligent driving algorithm includes: a first detection module 100, a first determination module 200, and a test module 300.

The first detection module 100 is configured to detect whether the simulation model enters a preset working condition after the test of the previous test step is completed; the first judging module 200 is used for judging that the current testing step meets the preset testing condition when the simulation model enters the preset working condition, and executing the testing operation of the target intelligent driving algorithm to obtain the testing result of the current testing step; the testing module 300 is configured to sequentially complete all testing steps, or, when the simulation model does not enter the preset working condition and it is determined that the current testing step does not meet the preset testing condition, end the simulation testing, and determine that the target intelligent driving algorithm is qualified, unqualified or incomplete according to a testing result of at least one testing step.

In an embodiment of the present application, the testing module 300 is further configured to detect whether a testing result of any testing step satisfies a preset qualified condition; when the test result of any test step does not meet the preset qualified condition, judging that the target intelligent driving algorithm is unqualified in test, and when the test result of any test step meets the preset qualified condition, detecting whether a blockage record exists in the test step; if the blockage records do not exist, the target intelligent driving algorithm test is judged to be qualified, if the blockage records exist and the test blockage of the last test step is identified, the target intelligent driving algorithm test is judged to be incomplete, otherwise, the target intelligent driving algorithm test is judged to be unqualified.

In an embodiment of the present application, when it is determined that the current testing step does not satisfy the preset testing condition, before the simulation test is ended, the simulation testing apparatus 10 of the intelligent driving algorithm further includes: the second detection module is used for detecting the duration that the simulation model does not enter the preset working condition; and the second judging module is used for judging that the current testing step meets the blocking condition when the duration is longer than the preset duration, recording the testing blocking of the current testing step, and ending the simulation test, otherwise, continuously judging whether the current testing step meets the preset testing condition.

In an embodiment of the present application, before detecting whether the simulation model enters the preset working condition after the test of the previous test step is completed, the simulation testing apparatus 10 for an intelligent driving algorithm further includes: the third detection module is used for detecting whether the simulation model and all the associated subsystems meet normal operation conditions; and the third judging module judges whether the current testing step meets the preset testing condition if the normal running condition is met, otherwise, judges that the current testing step tests the blockage, and ends the simulation test.

In one embodiment of the present application, before performing the simulation test of the first test step, the simulation test apparatus 10 of the smart driving algorithm further includes: the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring at least one piece of test step information of a target intelligent driving algorithm, and each piece of test step information comprises a test condition, an execution operation and a blocking condition; and the generating module is used for generating an execution script according to the information of the at least one test step, and sequentially carrying out simulation test on the target intelligent driving algorithm according to the test steps based on the execution script to obtain a test result corresponding to the test steps.

It should be noted that the explanation of the embodiment of the simulation test method for an intelligent driving algorithm is also applicable to the simulation test device for an intelligent driving algorithm of the embodiment, and is not repeated herein.

According to the simulation test device of the intelligent driving algorithm, when a simulation model enters a preset working condition and a current test step meets a preset test condition, a preset program is called to generate a test script of the current test step, test operation is executed to obtain a test result, all test steps of a test case are executed in sequence, when the simulation model does not enter the preset working condition and the current test step is judged not to meet the preset test condition, the simulation test is finished, and the test qualification, the test disqualification or the test incompletion of a target intelligent driving algorithm is determined according to the test result of at least one test step. By constructing continuous scenes for simulation test, the number of test scenes can be effectively reduced, more problems can be found, and the time for analyzing and classifying the problem data afterwards can be saved. Therefore, the problems that a test method in the related technology consumes a large amount of resources to carry out scene simulation test, and the early stage is not suitable for large-scale scene coverage verification and the like for agile development are solved.

Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device may include:

memory 401, processor 402, and computer programs stored on memory 401 and executable on processor 402.

The processor 402, when executing the program, implements the simulation testing method of the intelligent driving algorithm provided in the above embodiments.

Further, the electronic device further includes:

a communication interface 403 for communication between the memory 401 and the processor 402.

A memory 401 for storing computer programs operable on the processor 402.

The Memory 401 may include a high-speed RAM (Random Access Memory) Memory, and may also include a non-volatile Memory, such as at least one disk Memory.

If the memory 401, the processor 402 and the communication interface 403 are implemented independently, the communication interface 403, the memory 401 and the processor 402 may be connected to each other through a bus and perform communication with each other. The bus may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 4, but this does not indicate only one bus or one type of bus.

Optionally, in a specific implementation, if the memory 401, the processor 402, and the communication interface 403 are integrated on a chip, the memory 401, the processor 402, and the communication interface 403 may complete mutual communication through an internal interface.

Processor 402 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more Integrated circuits configured to implement embodiments of the present Application.

Embodiments of the present application further provide a computer-readable storage medium, on which a computer program is stored, where the program, when executed by a processor, implements the above simulation test method for an intelligent driving algorithm.

In the description of the present specification, reference to the description of "one embodiment," "some embodiments," "an example," "a specific example," or "some examples" or the like means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or N embodiments or examples. Moreover, various embodiments or examples and features of various embodiments or examples described in this specification can be combined and combined by one skilled in the art without being mutually inconsistent.

Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or to implicitly indicate the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "N" means at least two, e.g., two, three, etc., unless specifically limited otherwise.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more N executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present application.

It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable gate arrays, field programmable gate arrays, and the like.

It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.

Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.

Claims (10)

1. A simulation test method of an intelligent driving algorithm is characterized by comprising the following steps:

detecting whether the simulation model enters a preset working condition after the test of the previous test step is finished;

when the simulation model enters a preset working condition, judging that the current testing step meets a preset testing condition, and executing the testing operation of the target intelligent driving algorithm to obtain a testing result of the current testing step;

and sequentially testing all the testing steps, or when the simulation model does not enter a preset working condition and the current testing step is judged not to meet the preset testing condition, ending the simulation test, and determining that the target intelligent driving algorithm is qualified in testing, unqualified in testing or incomplete in testing according to the testing result of at least one testing step.

2. The method of claim 1, wherein the determining that the target smart driving algorithm is qualified, unqualified, or incomplete based on the test results of the at least one testing step comprises:

detecting whether the test result of any test step meets a preset qualified condition or not;

when the test result of any test step does not meet the preset qualified condition, judging that the target intelligent driving algorithm is unqualified in test, and when the test result of any test step meets the preset qualified condition, detecting whether a blockage record exists in the test step;

if the blockage records do not exist, the target intelligent driving algorithm is judged to be qualified in the test, if the blockage records exist and the test blockage of the last test step is identified, the target intelligent driving algorithm is judged to be unfinished in the test, otherwise, the target intelligent driving algorithm is judged to be unqualified in the test.

3. The method according to claim 1, wherein before ending the simulation test when it is determined that the current testing step does not satisfy the preset testing condition, the method comprises:

detecting the duration of the simulation model which does not enter a preset working condition;

and when the duration is longer than the preset duration, judging that the current testing step meets the blocking condition, recording the testing blocking of the current testing step, and ending the simulation test, otherwise, continuously judging whether the current testing step meets the preset testing condition.

4. The method of claim 1, wherein before detecting whether the simulation model enters the preset condition after the test of the previous test step is completed, the method comprises:

detecting whether the simulation model and all the associated subsystems meet normal operation conditions or not;

if the normal running condition is met, judging whether the current testing step meets the preset testing condition, otherwise, judging that the current testing step is blocked in testing, and ending the simulation testing.

5. The method according to any of claims 1-4, before performing the simulation test of the first test step, comprising:

acquiring at least one piece of test step information of a target intelligent driving algorithm, wherein each piece of test step information comprises a test condition, an execution operation and a blocking condition;

and generating an execution script according to the at least one piece of test step information, and sequentially carrying out simulation test on the target intelligent driving algorithm according to the test steps based on the execution script to obtain a test result corresponding to the test steps.

6. A simulation test device for an intelligent driving algorithm is characterized by comprising:

the first detection module is used for detecting whether the simulation model enters a preset working condition or not after the test of the last test step is finished;

the first judgment module is used for judging that the current testing step meets the preset testing condition when the simulation model enters the preset working condition, and executing the testing operation of the target intelligent driving algorithm to obtain the testing result of the current testing step;

and the test module is used for sequentially testing and completing all the test steps, or when the simulation model does not enter a preset working condition and the current test step is judged not to meet the preset test condition, ending the simulation test and determining that the target intelligent driving algorithm is qualified in test, unqualified in test or incomplete in test according to the test result of at least one test step.

7. The apparatus of claim 6, wherein the testing module is further configured to:

detecting whether the test result of any test step meets a preset qualified condition; when the test result of any test step does not meet the preset qualified condition, judging that the target intelligent driving algorithm is unqualified in test, and when the test result of any test step meets the preset qualified condition, detecting whether a blockage record exists in the test step; and if the blockage record does not exist, judging that the target intelligent driving algorithm test is qualified, if the blockage record exists and the test blockage of the last test step is identified, judging that the target intelligent driving algorithm test is not finished, otherwise, judging that the target intelligent driving algorithm test is unqualified.

8. The apparatus of claim 6, wherein before ending the simulation test when it is determined that the current testing step does not satisfy the preset testing condition, the method comprises:

the second detection module is used for detecting the duration of the simulation model which does not enter the preset working condition;

and the second judgment module is used for judging that the current testing step meets the blocking condition when the duration is longer than the preset duration, recording the testing blocking of the current testing step, and ending the simulation test, otherwise, continuously judging whether the current testing step meets the preset testing condition.

9. An electronic device, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the method of simulation testing of an intelligent driving algorithm according to any one of claims 1-5.

10. A computer-readable storage medium, on which a computer program is stored, characterized in that the program is executable by a processor for implementing a simulation test method for an intelligent driving algorithm according to any of claims 1-5.

Images