An integrated simulation test and evaluation method and system for an autonomous driving system

Abstract

The present invention relates to the technical field of autonomous driving system testing, and particularly relates to an integrated simulation testing and evaluation method and system for an autonomous driving system. The system includes a simulation interaction module, a modeling module, a database module, a processing module, a scheduling module, a sensor module, and a computing module. The method includes establishing a vehicle dynamics model, test cases, a scenario model, and a traffic flow model, and performing mapping. When conducting simulation testing, obtaining simulation configuration parameters, scheduling each model for simulation, obtaining simulation results, and generating an evaluation report based on the simulation results. The present invention integrates two methods for testing an autonomous driving system, namely scenario-based testing and traffic flow-based testing, fully leveraging the advantages of both testing methods to improve testing efficiency. At the same time, the autonomous driving system is evaluated from two perspectives: the safety of the vehicle itself and the impact on traffic safety, with a more comprehensive evaluation angle and more accurate evaluation results.

Description

Technical Field

[0001] The present invention relates to the technical field of autonomous driving system testing, and particularly to an integrated simulation testing and evaluation method and system for an autonomous driving system. Background Art

[0002] Traffic accidents cause serious harm to humans. As the most random factor in the traffic environment, the driver is also the main cause of traffic accidents. In view of traffic accident problems, autonomous driving vehicles are recognized as an effective way to avoid or reduce traffic accidents caused by human errors. The autonomous driving system is software on an autonomous driving vehicle for realizing driving control functions. To ensure the accuracy and safety of the autonomous driving vehicle during driving, it is necessary to test and evaluate the autonomous driving system on it before the autonomous driving vehicle hits the road. Especially for high-level autonomous driving vehicles, that is, autonomous driving vehicles of SAE L3 level and above, the driver no longer always has the motion control right of the vehicle during operation, and the autonomous driving system becomes the main body for monitoring the driving environment and controlling the vehicle operation.

[0003] Currently, the commonly used simulation testing methods for autonomous driving systems mainly start from standards and regulations, pre-design scenario segments, and then evaluate the safety of the autonomous driving system based on passability. However, since the randomness of the traffic environment and the interactivity between traffic participants are ignored in this testing method, there is a large difference from the real environment during vehicle driving, and it is also difficult to meet the requirements of test scenario coverage. Existing methods cannot test and evaluate the impact of the autonomous driving system on the traffic environment, such as traffic passing efficiency and traffic conflict safety, resulting in inaccurate evaluation results of the autonomous driving system. Summary of the Invention

[0004] The present invention aims to provide an integrated simulation testing and evaluation method for an autonomous driving system to improve the accuracy of autonomous driving system testing and evaluation.

[0005] The integrated simulation testing and evaluation method for the autonomous driving system in this solution includes the following steps:

[0006] Step 1, establish a vehicle dynamics model of the autonomous driving vehicle and store it in the dynamics model library, establish a scenario model and store it in the test scenario library, establish test cases and store them in the test case library, and establish a traffic flow model and store it in the traffic flow library;

[0007] It further includes the following steps:

[0008] Step 2, establish a mapping relationship between the traffic flow model and the scenario model according to the map information preset in the traffic flow model and the scenario model;

[0009] Step 3: Obtain test requirements, establish a simulation calculation center for simulation testing, and schedule the dynamic model library, test scenario library, test case library, and traffic flow library according to the obtained test requirements during the simulation;

[0010] Step 4: After scheduling, perform simulation according to the simulation configuration data in the test requirements, store the simulation data, and collect the simulation results during the simulation process;

[0011] Step 5: Conduct simulation evaluation of the autonomous driving system according to the used test scenario library or traffic flow library, and generate an evaluation report.

[0012] The beneficial effects of this solution are:

[0013] By adding test scenarios, test cases, and traffic flow during the simulation process, integrating the specific interaction scenarios of autonomous driving vehicles during actual driving into the simulation, integrating scenario-based autonomous driving system testing and traffic flow-based autonomous driving system testing, giving full play to the advantages of the two testing methods, improving the testing efficiency, making the simulation results more accurate, and at the same time evaluating the autonomous driving system from two perspectives of the vehicle's own safety and its impact on traffic safety, with a more comprehensive evaluation angle and more accurate evaluation results.

[0014] Further, in the above step 1, the test scenario elements, the complexity of the test scenario, and the passing conditions of the test scenario are combined to form test cases. The test case library includes a test case sub-library based on ODD, a test case sub-library based on functional safety, a test case sub-library based on expected functional safety, and a test case sub-library based on expert experience. The complexity is the weighted value of the scenario element complexity and the driving task complexity. The scenario element complexity is quantified according to the types of static and dynamic element components in the test scenario, and the driving task complexity is quantified according to the types of driving tasks in the test scenario per unit time.

[0015] The beneficial effects are: Form test cases from multiple aspects and form test cases under multiple different conditions, making the test scenario more complete and closer to the actual driving situation, and improving the accuracy of simulation testing.

[0016] Further, in the above step 4, when using the test scenario library, the test function, test target, the number of test scenarios, and the distribution characteristics of the test scenarios are used as simulation data. When using the traffic flow library, the map file, traffic flow density, vehicle distribution, and driver style distribution are used as simulation data.

[0017] The beneficial effects are: When performing simulation using different libraries, using different data as simulation data makes the evaluation results more accurate when evaluating in different aspects.

[0018] Further, in step 5, when using the test scenario library for simulation, the safety level of the autonomous driving system is scored according to the complexity, coverage, and pass rate of the test cases by the first model, and the first model is:

[0019] where: dc is the coverage of the test case, C is the complexity of a single test scenario, and T is the pass rate of a single test case;

[0020] The coverage of the test case is:

[0021]

[0022] where: m odd is the total number of test cases in the test case sub-library based on ODD, m f is the total number of test cases in the test case sub-library based on functional safety, m s is the total number of test cases in the test case sub-library based on expected functional safety, m e is the total number of test cases in the test case sub-library based on expert experience; n odd is the total number of real test cases in the actually tested test cases that come from the test case sub-library based on ODD, n f is the total number of real test cases in the actually tested test cases that come from the test case sub-library based on functional safety, n s is the total number of real test cases in the actually tested test cases that come from the test case sub-library based on expected functional safety, n e is the total number of real test cases in the actually tested test cases that come from the test case sub-library based on expert experience.

[0023] The beneficial effect is that the safety level of the autonomous driving system is scored by the first model, and a quantitative evaluation is carried out on the safety of the autonomous driving vehicle, improving the accuracy of the vehicle safety evaluation.

[0024] Further, in step 5, when using the traffic flow library for simulation, the traffic conflicts of the autonomous driving system are simulated and evaluated by using the state information, trajectory information, and traffic flow density information of traffic participants.

[0025] The beneficial effect is that the safety of the autonomous driving system is evaluated from the perspective of the actual traffic in which the vehicle travels, improving the integrity of the evaluation perspective and making the vehicle safety evaluation more accurate.

[0026] Further, in step 5, traffic conflicts are characterized by substituting variable headways, spacings between vehicles, and collision times. When there are traffic conflicts, the occurrence frequency of traffic conflicts is collected for simulation evaluation. The occurrence frequency is the ratio of the number of conflicts to the mileage. The positions and moments when traffic conflicts occur are extracted, and the time distribution and spatial distribution of traffic conflicts are formed based on the positions and moments.

[0027] The beneficial effects are as follows: Traffic conflicts are obtained through corresponding parameters, and simulation evaluation is carried out based on traffic conflicts, improving the accuracy and comprehensiveness of simulation evaluation.

[0028] Further, it also includes step 6. When using the test scenario library and traffic flow library for simulation simultaneously, the simulation results in the two cases are comprehensively evaluated with weights to obtain the comprehensive performance safety score value of the safety of autonomous vehicles.

[0029] The beneficial effects are as follows: Comprehensive evaluation is carried out on the simulations from two perspectives of scenarios and traffic flows, making the overall evaluation of the autonomous driving system more reliable.

[0030] The integrated simulation test and evaluation system for autonomous driving systems includes a simulation interaction module, a modeling module, a database module, a processing module, a scheduling module, a sensor module, and a computing module;

[0031] The simulation interaction module is used to obtain test requirements and send them to the processing module;

[0032] The modeling module is used to establish the vehicle dynamics model of autonomous vehicles, the modeling module is used to establish the scenario model, the modeling module is used to establish test cases, and the modeling module is used to establish the traffic flow model;

[0033] The database module includes a dynamics model library, a test scenario library, a test case library, and a traffic flow library for storing the required tests;

[0034] The processing module is used to obtain the vehicle dynamics model and store it in the dynamics model library in the database module, the processing module is used to obtain the scenario model and store it in the test scenario library in the database module, the processing module obtains the test cases and stores them in the test case library in the database module, and the processing module obtains the traffic flow model and stores it in the traffic flow library in the database module;

[0035] The scheduling module is used to schedule the dynamics model library, the test scenario library, the test case library, and the traffic flow library according to test requirements;

[0036] The sensor module is used to detect the simulation results during the simulation test;

[0037] A calculation module is configured to receive the simulation results obtained by the processing module from the sensor module, and calculate a simulation evaluation based on the simulation results to generate an evaluation report. Description of the Drawings

[0038] Figure 1 FIG. 1 is a schematic block diagram of an integrated simulation test and evaluation system for an autonomous driving system according to Embodiment 1 of the present invention;

[0039] Figure 2 FIG. 2 is a flowchart of an integrated simulation test and evaluation method for an autonomous driving system according to Embodiment 2 of the present invention;

[0040] Figure 3 FIG. 3 is a schematic block diagram of a calculation principle for the complexity of a test scenario in the integrated simulation test and evaluation method for an autonomous driving system according to Embodiment 2 of the present invention;

[0041] Figure 4 FIG. 4 is a schematic block diagram of a test case generation principle in the integrated simulation test and evaluation method for an autonomous driving system according to Embodiment 2 of the present invention;

[0042] Figure 5 FIG. 5 is a schematic diagram of a data mapping relationship between models in a computing center in the integrated simulation test and evaluation method for an autonomous driving system according to Embodiment 2 of the present invention;

[0043] Figure 6 FIG. 6 is a schematic diagram of a test execution and evaluation process for simulation under a scenario model in the integrated simulation test and evaluation method for an autonomous driving system according to Embodiment 2 of the present invention;

[0044] Figure 7 FIG. 7 is a schematic diagram of a test execution and evaluation process for simulation under a traffic flow model in the integrated simulation test and evaluation method for an autonomous driving system according to Embodiment 2 of the present invention. Detailed Description of the Embodiments

[0045] The following provides a more detailed description through specific embodiments.

[0046] Embodiment 1

[0047] An integrated simulation test and evaluation system for an autonomous driving system, as Figure 1 shown: includes a simulation interaction module, a modeling module, a database module, a processing module, a scheduling module, a sensor module, and a calculation module.

[0048] The simulation interaction module is configured to obtain test requirements and send them to the processing module. The test requirements are represented by the simulation configuration parameters required during the test process. The simulation interaction module can obtain the test requirements through existing input peripherals such as keyboards and touchscreens, and display the required simulation configuration parameters on an existing display screen.

[0049] The modeling module is used to establish the vehicle dynamics model of the autonomous vehicle, the modeling module is used to establish the scenario model, the modeling module is used to establish the test cases, the modeling module is used to establish the traffic flow model. The modeling module can establish various models through existing software installed on a PC host or a laptop computer, and establish each model by using the installed software and existing modeling methods.

[0050] The database module can be built with existing database software, such as Oracle software. The database module includes a dynamic model library, a test scenario library, a test case library, and a traffic flow library for storing the models required for testing.

[0051] The processing module is used to obtain the vehicle dynamics model and store it in the dynamic model library in the database module, the processing module is used to obtain the scenario model and store it in the test scenario library in the database module, the processing module obtains the test cases and stores them in the test case library in the database module, and the processing module obtains the traffic flow model and stores it in the traffic flow library in the database module; the processing module establishes a mapping relationship between the traffic flow model and the scenario model according to the map information, and the map information is generated when the traffic flow model and the scenario model are established. For example, the processing module establishes a mapping relationship between the scenario model file and the traffic flow model file with the same static map in the way of the same file name prefix.

[0052] The scheduling module is used to schedule the dynamic model library, the test scenario library, the test case library, and the traffic flow library according to the test requirements. For example, it schedules the model libraries according to whether the test requirements are scenario-based tests, traffic flow-based tests, or both scenario and traffic flow tests.

[0053] The sensor module is used to detect the simulation results during the simulation test. The simulation results include the corresponding parameters obtained by simulation under the test scenario and traffic flow conditions. The sensor module can use the sensors required in the existing autonomous driving system, such as ranging sensors and image sensors, etc.

[0054] The calculation module is used to receive the simulation results obtained by the processing module from the sensor module, calculate the simulation evaluation according to the simulation results, and generate an evaluation report. The simulation evaluation is calculated according to the preset calculation formula based on the parameters in the obtained simulation results, such as the formula in the method of Embodiment 2. The evaluation report includes the scores or graphs of the simulation tests of the vehicle dynamics model under different conditions.

[0055] The system of this embodiment models the vehicle through a modeling module, and conducts simulation tests on the test scenarios and traffic flow of the modeled vehicle model under different test cases. During the simulation process, it is automatically scheduled after mapping, and the states of the autonomous vehicle driving under different conditions are simulated through different library mappings, making the test conditions closer to the actual driving situation, making the test simulation closer to the actual driving environment, improving the accuracy of the test simulation, and being able to discover problems existing in the autonomous driving system in advance.

[0056] Embodiment 2

[0057] The integrated simulation test and evaluation method for an autonomous driving system uses the integrated simulation test and evaluation system of Embodiment 1, as Figure 2 shown, and includes the following steps:

[0058] Step 1, establish a vehicle dynamics model of the autonomous vehicle through the modeling module and store it in the dynamics model library. The vehicle dynamics model of the autonomous vehicle is established according to the actual vehicle to be tested. The establishment of the vehicle dynamics module uses existing vehicle dynamics software and existing technologies, which will not be elaborated here.

[0059] Establish a scenario model and store it in the test scenario library. Based on the design operation domain (ODD), functional safety, expected functional safety, and expert experience specified by the existing standards of the autonomous driving system, establish scenario models respectively. The storage format of the scenario models is the open-x format. The scenario models are established using existing VTD software. For example, the scenario model of the urban expressway exit scenario. The test scenario library includes a scenario sub-library based on ODD, a scenario sub-library based on functional safety, a scenario sub-library based on expected functional safety, and a scenario sub-library based on expert experience.

[0060] As Figure 4 shown, establish test cases and store them in the test case library. Combine the test scenario elements, the complexity of the test scenario, and the passing conditions of the test scenario to form test cases. The test case library includes a test case sub-library based on ODD, a test case sub-library based on functional safety, a test case sub-library based on expected functional safety, and a test case sub-library based on expert experience. As Figure 3As shown, the complexity is the weighted value of the scenario element complexity and the driving task complexity. For example, the weighted value is the sum of the scenario element complexity A multiplied by the weight w1 and the driving task complexity multiplied by the weight w2. The weights w1 and w2 are set according to the simulation test requirements. For example, w1 = 4 and w2 = 5. The scenario element complexity is quantified according to the types of composition of static elements and dynamic elements in the test scenario. For example, it is the sum of the types of composition of static elements and the types of composition of dynamic elements. The driving task complexity is quantified according to the types of driving tasks in the test scenario per unit time. For example, taking the number P of driving task types within T unit time as the driving task complexity.

[0061] Establish a traffic flow model and store it in the traffic flow library. The establishment of the traffic flow model is carried out respectively based on the design operation domain, functional safety, expected functional safety of the autonomous driving system, and expert experience. The traffic flow model can be established using the existing VISSIM software. The traffic flow model includes the average traffic volume Q, average speed V of the road section, average density K, trajectory information of traffic participants, and status information of traffic participants on a certain route. After the model and test cases are established, they are stored in the database module.

[0062] Step 2: Through the processing module, according to the map information preset in the traffic flow model and the scenario model, the map information is uniformly preset when the traffic flow model and the scenario model are established, such as Figure 5 As shown, establish a mapping relationship between the traffic flow model and the scenario model in the test scenario library. For example, establish a mapping relationship between the scenario model file and the traffic flow model file with the same static map with the same file name prefix.

[0063] Step 3: Obtain the test requirements through the simulation interaction module, establish a simulation calculation center for simulation testing, and during the simulation, through the scheduling module, schedule the dynamic model library, test scenario library, test case library, and traffic flow library according to the obtained test requirements. That is, based on whether the test requirement is a scenario-based test, a traffic flow-based test, or a test that requires both scenarios and traffic flow, to schedule the model library in the simulation software. For example, when the test requirement is a scenario-based test for type A autonomous driving vehicles, retrieve the corresponding vehicle dynamics model from the dynamic model library, start the vehicle dynamics software and the scenario simulation software, and establish an API interface communication connection between the vehicle dynamics software and the scenario simulation software.

[0064] Step 4, after scheduling, the processing module performs simulation according to the simulation configuration data in the test requirements, stores the simulation data, and collects the simulation results during the simulation. The simulation results include the corresponding parameters obtained by simulation under the test scenario and traffic flow conditions. When using the test scenario library, the test functions, test objectives, the number of test scenarios, and the distribution characteristics of the test scenarios are used as simulation data. When using the traffic flow library, the map file, traffic flow density, vehicle distribution, and driver style distribution are used as simulation data. The traffic flow density is the number of vehicles passing through per unit time. The vehicle distribution is the proportion of cars, trucks, and two-wheelers in the total. The driver style distribution includes aggressive, normal, and conservative. The map file is the map information in the traffic flow model and the scenario model.

[0065] Step 5, the computing module conducts a simulation evaluation of the autonomous driving system according to the used test scenario library or traffic flow library and generates an evaluation report. As Figure 6 shown, when performing simulation using the test scenario library, the complexity, coverage, and pass rate of the test cases are used to score the safety level of the autonomous driving system according to the first model. The first model is:

[0066] where: dc is the coverage of the test case, C is the complexity of a single test scenario, and T is the pass rate of a single test case;

[0067] The coverage of the test case is:

[0068]

[0069] where: m odd is the total number of test cases in the test case sub-library based on ODD, m f is the total number of test cases in the test case sub-library based on functional safety, m s is the total number of test cases in the test case sub-library based on expected functional safety, m e is the total number of test cases in the test case sub-library based on expert experience; n odd is the total number of real test cases in the actually tested test cases that come from the test case sub-library based on ODD, n f is the total number of real test cases in the actually tested test cases that come from the test case sub-library based on functional safety, n s is the total number of real test cases in the actually tested test cases that come from the test case sub-library based on expected functional safety, n e is the total number of real test cases in the actually tested test cases that come from the test case sub-library based on expert experience, n odd n f n s and n eFrom the simulation configuration parameters in the test requirements.

[0070] As Figure 7 shown, when using the traffic flow library for simulation, the traffic conflicts of the autonomous driving system are simulated and evaluated by using the state information, trajectory information and traffic flow density information of traffic participants, so as to replace the variable headway, vehicle spacing and collision time to characterize traffic conflicts. When there are traffic conflicts, the occurrence frequency of traffic conflicts is collected for simulation evaluation. The occurrence frequency is the ratio of the number of conflicts to the driving mileage (CR). The location and time when the traffic conflict occurs are extracted, and the time distribution and spatial distribution of traffic conflicts are formed by the location and time. The time distribution is a two-dimensional graph: the abscissa of the time coordinate is the time period within a day, and the ordinate is the conflict frequency; the spatial distribution is a three-dimensional graph: the horizontal and vertical coordinates are the global geographical location coordinates respectively, and the traffic conflict frequency is displayed in the form of a heat map.

[0071] Step 6, when using the test scenario library and the traffic flow library for simulation at the same time, the simulation results in the two cases are weighted and comprehensively evaluated to obtain the comprehensive performance safety score value of the safety of the autonomous driving vehicle, which is expressed as:

[0072] Safety all = CR × K1 1 + Safety × K2 2 , where CR is the ratio of the number of conflicts obtained from the traffic flow simulation test to the driving mileage, K1 is its weight value, the specific value of K1 is set according to actual needs, Safety is the safety level number obtained from the scenario simulation test, K2 is the corresponding weight value, and the specific value of K2 is set according to actual needs.

[0073] Due to the conventional thinking, since autonomous driving vehicles can avoid human subjective negligence or mistakes, autonomous driving vehicles are considered to have a high safety factor. Therefore, when evaluating the autonomous driving system, it is generally considered that the safety of the autonomous driving system meets the requirements according to the requirements of the autonomous driving system to meet the corresponding standards. In the method of this embodiment, by setting test cases, test scenarios and traffic flows for the performance simulation evaluation of the autonomous driving system on autonomous driving vehicles, the influence of the actual driving environment and traffic flow can be considered, the test can be carried out from multiple dimensions, and the evaluation can be carried out according to the test results, improving the test accuracy and evaluation accuracy.

[0074] The above are only embodiments of the present invention, and common general knowledge of specific structures and characteristics in the solution is not described in detail herein. It should be noted that for those skilled in the art, without departing from the structure of the present invention, several modifications and improvements can be made, which should also be regarded as the protection scope of the present invention, and these will not affect the implementation effect of the present invention and the practicability of the patent. The protection scope claimed in this application shall be subject to the content of its claims, and the specific implementation manners and the like recorded in the specification can be used to interpret the content of the claims.

Claims

1. An integrated simulation test and evaluation method for an autonomous driving system, comprising the following steps: Step 1, establish a vehicle dynamics model of an autonomous driving vehicle and store it in the dynamics model library, establish a scenario model and store it in the test scenario library, establish test cases and store them in the test case library, and establish a traffic flow model and store it in the traffic flow library; characterized in that: In the said Step 1, combine the test scenario elements, the complexity of the test scenario, and the passability conditions of the test scenario to form test cases. The test case library includes a test case sub-library based on ODD, a test case sub-library based on functional safety, a test case sub-library based on expected functional safety, and a test case sub-library based on expert experience. The complexity is the weighted value of the scenario element complexity and the driving task complexity. The scenario element complexity is quantified according to the types of static and dynamic element components in the test scenario, and the driving task complexity is quantified according to the types of driving tasks in the test scenario per unit time; It further includes the following steps: Step 2, establish a mapping relationship between the traffic flow model and the scenario model according to the preset map information in the traffic flow model and the scenario model; Step 3, obtain test requirements, establish a simulation computing center for simulation testing, and schedule the dynamics model library, test scenario library, test case library, and traffic flow library according to the obtained test requirements during simulation; Step 4, after scheduling, perform simulation according to the simulation configuration data in the test requirements, store the simulation data, and collect the simulation results during the simulation process; Step 5, perform simulation evaluation of the autonomous driving system according to the used test scenario library or traffic flow library, and generate an evaluation report.

2. The integrated simulation test and evaluation method for an autonomous driving system according to claim 1, characterized in that: In the said Step 4, when using the test scenario library, use the test function, test target, the number of test scenarios, and the distribution characteristics of the test scenarios as simulation data. When using the traffic flow library, use the map file, traffic flow density, vehicle distribution, and driver style distribution as simulation data.

3. The integrated simulation test and evaluation method for an autonomous driving system according to claim 2, characterized in that: In the said Step 5, when performing simulation using the test scenario library, score the safety level of the autonomous driving system according to the complexity, coverage, and passability of the test cases according to the first model. The first model is: ， Wherein: dc C is the coverage of test cases, C is the complexity of a single test scenario, and T is the pass rate of a single test case; is the complexity of the i-th test scenario in the ODD-based test case library; is the pass rate of the i-th test case in the ODD-based test case library; is the complexity of the i-th test scenario in the sub-library of test cases based on functional safety; is the pass rate of the i-th test case in the sub-library of test cases based on functional safety; is the complexity of the i-th test scenario in the sub-library of test cases based on expected functional safety; is the pass rate of the i-th test case in the sub-library of test cases based on expected functional safety; is the complexity of the i-th test scenario in the sub-library of test cases based on expert experience; is the pass rate of the i-th test case in the sub-library of test cases based on expert experience; The coverage of the said test case is: ； Wherein: is the total number of test cases in the test case library based on ODD, is the total number of test cases in the test case library based on functional safety, is the total number of test cases in the test case library based on expected functional safety, is the total number of test cases in the test case library based on expert experience; is the total number of real test cases from the test case library based on ODD among the actually tested test cases, is the total number of real test cases from the test case library based on functional safety among the actually tested test cases, is the total number of real test cases from the test case library based on expected functional safety among the actually tested test cases, is the total number of real test cases from the test case library based on expert experience among the actually tested test cases.

4. The integrated simulation test and evaluation method for an autonomous driving system according to claim 3, characterized in that: In the said Step 5, when performing simulation using the traffic flow library, use the state information, trajectory information, and traffic flow density information of traffic participants to perform simulation evaluation of the traffic conflicts of the autonomous driving system.

5. The integrated simulation test and evaluation method for an autonomous driving system according to claim 4, characterized in that: In step 5, traffic conflicts are characterized by substituting variable headway, spacing between vehicles, and collision time. When there are traffic conflicts, the occurrence frequency of traffic conflicts is collected for simulation evaluation. The occurrence frequency is the ratio of the number of conflicts to the mileage. The location and time when traffic conflicts occur are extracted, and the time distribution and spatial distribution of traffic conflicts are formed based on the location and time.

6. The integrated simulation test and evaluation method for an autonomous driving system according to claim 5, wherein: It further includes step 6. When the test scenario library and the traffic flow library are used for simulation simultaneously, the simulation results in the two cases are weighted and comprehensively evaluated to obtain a comprehensive performance safety score value for the safety of autonomous vehicles.

7. An integrated simulation test and evaluation system for an autonomous driving system, wherein: It includes a simulation interaction module, a modeling module, a database module, a processing module, a scheduling module, a sensor module, and a calculation module; The simulation interaction module is used to obtain test requirements and send them to the processing module; The modeling module is used to establish a vehicle dynamics model of an autonomous vehicle. The modeling module is used to establish a scenario model. The modeling module is used to establish test cases according to step 1 in the method described in claim 1. The test scenario elements, the complexity of the test scenario, and the passability conditions of the test scenario are combined to form test cases. The test case library includes a test case sub-library based on ODD, a test case sub-library based on functional safety, a test case sub-library based on expected functional safety, and a test case sub-library based on expert experience. The complexity is the weighted value of the scenario element complexity and the driving task complexity. The scenario element complexity is quantified according to the types of static and dynamic element components in the test scenario. The driving task complexity is quantified according to the types of driving tasks in the test scenario per unit time. The modeling module is used to establish a traffic flow model; The database module includes a dynamic model library, a test scenario library, a test case library, and a traffic flow library for storing the tests required; The processing module is used to obtain the vehicle dynamics model and store it in the dynamic model library in the database module. The processing module is used to obtain the scenario model and store it in the test scenario library in the database module. The processing module obtains the test cases and stores them in the test case library in the database module. The processing module obtains the traffic flow model and stores it in the traffic flow library in the database module; The scheduling module is used to schedule the dynamic model library, the test scenario library, the test case library, and the traffic flow library according to the test requirements; The sensor module is used to detect the simulation results during the simulation test; The calculation module is used to receive the simulation results obtained by the processing module from the sensor module and calculate the simulation evaluation according to the simulation results to generate an evaluation report.

Images