A test method and device for vehicle automatic lane changing

By constructing a test case sequence and automatic lane-changing algorithm in a simulation environment, the problems of low efficiency and high cost in real-vehicle field testing were solved, and fast and comprehensive automatic lane-changing function testing was achieved.

CN115270495BActive Publication Date: 2025-10-10上海友道智途科技有限公司
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202210951937.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-08-09
Publication Date
2025-10-10
Estimated Expiration
2042-08-09

AI Technical Summary

Technical Problem

In the existing technology, the actual vehicle field testing method of the vehicle automatic lane change function is inefficient and costly, difficult to fully cover the boundary conditions, and requires a lot of manpower investment.

Method used

Using simulation testing methods, by constructing simulation test scenarios and adjustable test case sequences, automatic lane changing tests are conducted in a simulation environment to obtain test results and optimize the automatic lane changing algorithm.

Benefits of technology

The test efficiency of the automatic lane-changing function is improved, the test time and cost are reduced, and the automatic lane-changing conditions of the vehicle in different scenarios can be more comprehensively reflected.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115270495B_ABST
    Figure CN115270495B_ABST
Patent Text Reader

Abstract

The application discloses a kind of vehicle automatic lane changing test method and device, obtain the simulation test scene of automatic lane changing of vehicle to be measured, the simulation test scene is used to simulate the actual automatic lane changing scene of vehicle to be measured, corresponding test case sequence of the simulation test scene is called, and under simulation test scene, test case sequence is tested to obtain test result.The test case sequence is constructed according to the automatic lane changing parameter of simulation test scene, and the automatic lane changing parameter is adjustable, based on this, it can be adjusted in the test value interval of automatic lane changing parameter, and the test case sequence that can comprehensively cover the test value interval of the automatic lane changing parameter under the simulation test scene is constructed, so that the test result can comprehensively reflect various automatic lane changing conditions of vehicle to be measured under the simulation test scene.Compared with real vehicle field test mode, the test of automatic lane changing function can be completed more quickly, and the test efficiency is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of vehicle control technology, and in particular to a method and device for testing automatic lane changing of a vehicle. Background Art

[0002] With the rapid development of science and technology, autonomous driving systems have been installed in various types of vehicles to assist drivers in performing related driving operations (such as parking, lane changing, etc.).

[0003] In an autonomous driving system, the automatic lane changing function is an important function. Generally speaking, the automatic lane changing function needs to be tested before it is officially launched, and the automatic lane changing function needs to be evaluated and optimized based on the test results. In related technologies, the automatic lane changing function is tested by using a real vehicle field test. Specifically, in the real vehicle field used for testing, the target vehicle or obstacle is controlled to interact with the test vehicle to trigger the automatic lane changing of the test vehicle. It is understandable that in order to determine the boundary conditions for triggering automatic lane changing in the automatic lane changing test scenario, multiple tests need to be performed within the test value range of various test parameters (such as the speed of the test vehicle, the speed of the target vehicle, etc.).

[0004] However, this on-site testing method, based on real vehicles, can result in poorly representative results for boundary conditions if only a few groups are tested. Testing a large number of groups consumes a significant amount of testing time, leading to low test efficiency. Furthermore, this method requires significant testing manpower, resulting in high testing costs. Summary of the Invention

[0005] In order to solve the above technical problems, the present application provides a vehicle automatic lane changing test method and device, which can complete the test of the automatic lane changing function more quickly and improve the test efficiency.

[0006] The embodiments of this application disclose the following technical solutions:

[0007] In one aspect, an embodiment of the present application provides a method for testing automatic lane change of a vehicle, the method comprising:

[0008] Obtain a simulation test scenario of the vehicle under test performing automatic lane change;

[0009] Calling a test case sequence corresponding to the simulation test scenario; the test case sequence is constructed based on the automatic lane change parameters of the simulation test scenario, and the automatic lane change parameters are adjustable;

[0010] In the simulation test scenario, an automatic lane change test is performed on the test case sequence to obtain a test result.

[0011] Optionally, performing an automatic lane change test on the test case sequence in the simulation test scenario to obtain a test result includes:

[0012] In the simulation test scenario, an automatic lane changing algorithm is used to perform an automatic lane changing test on the test case sequence to obtain a test result.

[0013] Optionally, also include:

[0014] performing data processing on the test results, and determining an automatic lane change boundary value corresponding to the simulation test scenario according to the automatic lane change parameters;

[0015] evaluating the automatic lane changing algorithm according to the automatic lane changing boundary value to obtain an evaluation result;

[0016] The automatic lane changing algorithm is optimized according to the evaluation result, so that the evaluation result corresponding to the optimized automatic lane changing algorithm meets the target condition.

[0017] Optionally, the test result includes lane-changing characteristic data of the vehicle under test performing automatic lane changing, and the data processing of the test result and determining the automatic lane-changing boundary value corresponding to the simulation test scenario according to the automatic lane-changing parameters include:

[0018] Filtering the test results according to the lane-changing characteristic data to obtain valid test results;

[0019] Data processing is performed on the valid test results, and the automatic lane change boundary value is determined according to the automatic lane change parameters.

[0020] Optionally, the lane change characteristic data includes the lane number of the vehicle to be tested, and the test results are filtered according to the lane change characteristic data to obtain valid test results, including:

[0021] The test result in which the driving lane number is changed in the test results is extracted as the valid test result.

[0022] Optionally, also include:

[0023] Constructing a simulation scenario library for the vehicle under test to perform automatic lane changing;

[0024] The step of obtaining a simulation test scenario in which the vehicle under test performs automatic lane change includes:

[0025] The simulation test scenario is called from the simulation scenario library.

[0026] Optionally, also include:

[0027] Obtaining a test value range and a preset value interval of the automatic lane change parameter;

[0028] determining a plurality of automatic lane change parameter values ​​according to the test value interval and the preset value interval;

[0029] Constructing a test case according to the multiple automatic lane change parameter values;

[0030] The test cases are spliced ​​together to obtain the test case sequence.

[0031] On the other hand, an embodiment of the present application provides a vehicle automatic lane change test device, the device comprising an acquisition unit, a calling unit, and a testing unit:

[0032] The acquisition unit is used to acquire a simulation test scenario of the vehicle under test performing automatic lane change;

[0033] The calling unit is configured to call a test case sequence corresponding to the simulation test scenario; the test case sequence is constructed based on the automatic lane change parameters of the simulation test scenario, and the automatic lane change parameters are adjustable;

[0034] The test unit is used to perform an automatic lane change test on the test case sequence in the simulation test scenario to obtain a test result.

[0035] Optionally, the testing unit is further used to:

[0036] In the simulation test scenario, an automatic lane changing algorithm is used to perform an automatic lane changing test on the test case sequence to obtain a test result.

[0037] Optionally, it also includes a determination unit, an evaluation unit, and an optimization unit:

[0038] The determining unit is configured to perform data processing on the test result and determine an automatic lane change boundary value corresponding to the simulation test scenario according to the automatic lane change parameter;

[0039] The evaluation unit is configured to evaluate the automatic lane changing algorithm according to the automatic lane changing boundary value to obtain an evaluation result;

[0040] The optimization unit is configured to optimize the automatic lane changing algorithm according to the evaluation result, so that the evaluation result corresponding to the optimized automatic lane changing algorithm meets a target condition.

[0041] Optionally, the test result includes lane-changing characteristic data of the vehicle under test performing automatic lane change, and the determining unit is further configured to:

[0042] Filtering the test results according to the lane-changing characteristic data to obtain valid test results;

[0043] Data processing is performed on the valid test results, and the automatic lane change boundary value is determined according to the automatic lane change parameters.

[0044] Optionally, the lane change characteristic data includes a lane number of the vehicle to be tested, and the determining unit is further configured to:

[0045] The test result in which the driving lane number is changed in the test results is extracted as the valid test result.

[0046] Optionally, also include building blocks:

[0047] The construction unit is used to construct a simulation scenario library for the automatic lane changing of the vehicle to be tested;

[0048] The acquisition unit is further configured to call the simulation test scenario from the simulation scenario library.

[0049] Optionally, the acquiring unit is further configured to:

[0050] Obtaining a test value range and a preset value interval of the automatic lane change parameter;

[0051] determining a plurality of automatic lane change parameter values ​​according to the test value interval and the preset value interval;

[0052] Constructing a test case according to the multiple automatic lane change parameter values;

[0053] The test cases are spliced ​​together to obtain the test case sequence.

[0054] As can be seen from the above technical solution, first, a simulation test scenario for the vehicle under test to perform automatic lane change is obtained. The simulation test scenario is used to simulate the actual automatic lane change scenario of the vehicle under test. Then, a test case sequence corresponding to the simulation test scenario is called, and the test case sequence is tested for automatic lane change in the simulation test scenario to obtain a test result. Since the test case sequence is constructed based on the automatic lane change parameters of the simulation test scenario, and the automatic lane change parameters are adjustable, based on this, it can be adjusted within the test value range of the automatic lane change parameters to construct a test case sequence that can fully cover the test value range of the automatic lane change parameters in the simulation test scenario. Therefore, the test result obtained by performing the automatic lane change test based on the test case sequence can fully reflect the various automatic lane change situations of the vehicle under test in the simulation test scenario. It can be seen that a simulation test method is provided for testing the automatic lane change function of a vehicle. For each simulation test scenario, a corresponding test case sequence can be constructed. Then, the test of the test case sequence is completed by simulation testing. Compared with the actual vehicle field test method, the test of the automatic lane change function can be completed more quickly, thereby improving the test efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0056] Figure 1 A flow chart of a method for testing automatic lane change of a vehicle provided in an embodiment of the present application;

[0057] Figure 2a A schematic diagram of a simulation scenario of automatic lane changing of a vehicle provided in an embodiment of the present application;

[0058] Figure 2b A schematic diagram of another simulation scenario of automatic lane changing of a vehicle provided in an embodiment of the present application;

[0059] Figure 2c A schematic diagram of another simulation scenario of automatic lane changing of a vehicle provided in an embodiment of the present application;

[0060] Figure 2d A schematic diagram of another simulation scenario of automatic lane changing of a vehicle provided in an embodiment of the present application;

[0061] Figure 2e A schematic diagram of another simulation scenario of automatic lane changing of a vehicle provided in an embodiment of the present application;

[0062] Figure 3 A schematic diagram of a lane number change for a vehicle provided in an embodiment of the present application;

[0063] Figure 4a A schematic diagram of an evaluation of an automatic lane-changing algorithm provided in an embodiment of the present application;

[0064] Figure 4b A schematic diagram of another evaluation of an automatic lane change algorithm provided in an embodiment of the present application;

[0065] Figure 5 A structural diagram of a vehicle automatic lane changing test device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0066] In order for those skilled in the art to better understand the scheme of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0067] With the rapid development of science and technology, an automatic driving system has been configured in various vehicles to assist a driver to perform relevant driving operations (such as parking, lane changing, etc.).

[0068] In the automatic driving system, the automatic lane changing function is an important function. Generally, the automatic lane changing function needs to be tested before it is officially put into operation, and the automatic lane changing function is evaluated, optimized, etc. based on the test results. In the related art, the automatic lane changing function is tested by using a real vehicle field test method, specifically, in a real vehicle field for testing, a target vehicle or an obstacle is controlled to interact with a test vehicle to trigger the automatic lane changing of the test vehicle. It can be understood that, in order to determine the boundary conditions of triggering the automatic lane changing in the automatic lane changing test scenario, multiple tests need to be performed in the test value range of each test parameter (such as the speed of the test vehicle, the speed of the target vehicle, etc.).

[0069] However, if the test is performed in a small number of groups based on the real vehicle field test method, the test results are difficult to represent the boundary conditions, and if a large number of groups are tested, a large amount of test time is consumed, and the test efficiency is low. In addition, this test method also needs to invest more test manpower, and the test cost is high.

[0070] Therefore, the present application provides a vehicle automatic lane changing test method and device, which provides a simulation test method for testing the vehicle automatic lane changing function. For each simulation test scenario, a test case sequence corresponding thereto can be constructed, and then the test of the test case sequence is completed by using the simulation test method. Compared with the real vehicle field test method, the test of the automatic lane changing function can be completed more quickly, and the test efficiency is improved.

[0071] The vehicle automatic lane changing test method provided in the embodiments of the present application can be implemented by a computer device, which can be a terminal device or a server. The server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device includes but is not limited to a mobile phone, a computer, a smart voice interaction device, a smart home appliance, a vehicle-mounted terminal, etc. The terminal device and the server can be connected directly or indirectly through wired or wireless communication, which is not limited in the present application.

[0072] Specifically described by the following examples:

[0073] Figure 1 This is a flowchart of a method for testing automatic lane change of a vehicle provided in an embodiment of the present application. Taking a terminal device as the aforementioned computer device as an example, the method includes S101-S103:

[0074] S101: Acquire a simulation test scenario of the vehicle under test performing automatic lane changing.

[0075] When testing the automatic lane-changing function of a vehicle, a simulation test scenario of the vehicle under test performing automatic lane-changing can be first obtained, so that the automatic lane-changing function of the vehicle can be simulated and tested under this simulation test scenario.

[0076] It is understandable that when a real vehicle is driving, there are many driving scenarios that require lane changing. Accordingly, the lane changing situation in each lane changing scenario is an important evaluation data for the vehicle's automatic lane changing function. In order to be able to quickly and conveniently perform the above simulation test, in one possible implementation method, a simulation scenario library for the automatic lane changing of the vehicle under test can be constructed, and then when testing is required, the simulation test scenario can be called from the simulation scenario library. Based on this, by pre-constructing a simulation scenario library containing various automatic lane changing scenarios, the simulation test scenario can be quickly called from the simulation scenario library when testing is required, so as to complete the relevant tests for the automatic lane changing function.

[0077] For the construction of the simulation scenario library, simulation test scenarios corresponding to various automatic lane-changing scenarios can be pre-built according to actual test requirements and with reference to typical traffic flows. This application does not impose any restrictions on this. Figure 2a-2e Several typical automatic lane-changing scenarios are shown as examples:

[0078] like Figure 2a As shown, it means that there is a static obstacle in front of the current lane of the main vehicle, so automatic lane change is required. Specifically, the VUT is the main vehicle, and the static obstacle can be a stationary vehicle (for example, Figure 2a The VT shown in the figure represents a stationary vehicle in front of the current lane of the main vehicle), or it can be a roadblock such as a cone and the construction area surrounded by it.

[0079] like Figure 2b The figure shows a scenario where the host vehicle needs to automatically change lanes after receiving a lane change command. In this scenario, there is a vehicle moving behind the host vehicle in the target lane, which will interfere with the host vehicle's lane change. VUT is the host vehicle, and VT is the vehicle moving behind the target lane.

[0080] like Figure 2c The figure shows a scenario where the host vehicle is overtaking and changing lanes, and there are no moving vehicles or static obstacles in the target lane. Specifically, VUT is the host vehicle, and VT is the low-speed vehicle in front of the host vehicle's current lane (the speed is lower than that of the host vehicle). In this scenario, the host vehicle can achieve overtaking and lane changing by automatically changing lanes.

[0081] like Figure 2d As shown, it represents a scenario where the main vehicle overtakes and changes lanes, and there is a high-speed vehicle coming from behind the target lane (the speed is higher than the speed of the main vehicle). Specifically, VUT is the main vehicle, VT1 is a low-speed vehicle in front of the main vehicle's current lane (the speed is lower than the speed of the main vehicle), and VUT2 is a high-speed vehicle coming from behind the main vehicle in the target lane. In this scenario, the main vehicle overtakes and changes lanes.

[0082] like Figure 2e As shown, it means that the main vehicle is overtaking and changing lanes, and there is a low-speed vehicle in front of the target lane (the speed is lower than the main vehicle speed). Specifically, VUT is the main vehicle, VT1 is the low-speed vehicle in front of the main vehicle's current lane (the speed is lower than the main vehicle speed), and VUT2 is the low-speed vehicle in front of the main vehicle in the target lane (the speed is lower than the main vehicle speed). In this scenario, the main vehicle is overtaking and changing lanes.

[0083] It should be noted that Figure 2a-2e The scenarios shown in the figure are only examples. In addition to the above scenarios, more lane-changing scenarios can be constructed according to test requirements.

[0084] S102: Calling a test case sequence corresponding to the simulation test scenario.

[0085] For testing the automatic lane change function, after obtaining a simulation test scenario, the corresponding test case sequence can be called to perform subsequent test steps. The test case sequence is constructed based on the automatic lane change parameters of the simulation test scenario, and the automatic lane change parameters are adjustable.

[0086] The automatic lane change parameters correspond to the simulation test scenario and reflect the key parameters required to consider the vehicle's automatic lane change behavior in the current simulation test scenario. Furthermore, these parameters are adjustable. Therefore, within the same simulation test scenario, multiple test cases corresponding to that scenario can be quickly constructed by adjusting the automatic lane change parameters. These tests can then be used to complete the relevant tests for that simulation test scenario and obtain multiple sets of test results.

[0087] It should be noted that for different automatic lane-changing scenarios, corresponding simulation test scenarios are constructed in the simulation scenario library. In each lane-changing scenario, the automatic lane-changing parameters for the vehicle to automatically change lanes are different. For example, Figure 2aIn the lane-changing scenario shown, the automatic lane-changing parameter is the host vehicle speed, and Figure 2e In the lane-changing scenario shown, the automatic lane-changing parameters are the speed of the host vehicle, the speed of the target vehicle VT1, the speed of the target vehicle VT2, and the initial distances between the host vehicle and the target vehicles VT1 and VT2.

[0088] In one possible implementation, the test case sequence corresponding to the simulation test scenario can be constructed as follows:

[0089] Obtaining the test value range and preset value interval of the automatic lane change parameter;

[0090] Determining multiple automatic lane change parameter values ​​according to a test value interval and a preset value interval;

[0091] Build test cases based on multiple automatic lane change parameter values;

[0092] The test cases are spliced ​​together to obtain a test case sequence.

[0093] Specifically, the automatic lane change parameters correspond to the simulation test scenario and reflect the key parameters that need to be considered for the vehicle's automatic lane change in this simulation test scenario. Since parameters such as the vehicle's driving speed are not constant during actual driving, but vary within a certain range, in order to fully cover the actual lane change scenario in the test, the test value range and preset value interval of the automatic lane change parameters can be first obtained. Then, based on the test value range and preset value interval, multiple automatic lane change parameter values ​​corresponding to the automatic lane change parameters can be determined. Then, test cases can be constructed based on the multiple automatic lane change parameter values. Finally, the test cases are spliced ​​to obtain a test case sequence, so that the entire test can be completed according to the test case sequence during the simulation test.

[0094] Based on this, the test case sequence constructed according to the test value range and the preset value interval can cover the entire test value range of the automatic lane change parameters, and thus can obtain more comprehensive lane change test data after the test is completed, so as to accurately determine the lane change boundaries in this lane change scenario based on the test data.

[0095] It should be noted that the test value interval can be set according to the actual driving conditions, and the preset value interval can be set according to the test requirements (such as the requirements for the number of test cases). This application does not impose any restrictions on this. Figure 2d Taking the lane-changing scenario shown in the figure as an example, the automatic lane-changing function of the intelligent heavy-duty truck is tested. The following method is used to build a test for the automatic lane-changing function of the intelligent heavy-duty truck. Figure 2d The test case sequence for lane changing in the lane changing scenario shown is as follows:

[0096] like Figure 2d As shown in the figure, it represents a scenario where the host vehicle is overtaking and changing lanes, and there is a high-speed vehicle (speed higher than the host vehicle) behind the target lane. Specifically, VUT is the host vehicle, VT1 is a low-speed vehicle in front of the host vehicle's current lane (speed lower than the host vehicle's speed), and VUT2 is a high-speed vehicle behind the host vehicle in the target lane. In this scenario, the host vehicle is overtaking and changing lanes. The corresponding automatic lane change parameters include the host vehicle speed, the target vehicle VT1 speed, the target vehicle VT2 speed, and the initial distance between the host vehicle and the target vehicles VT1 and VT2, as shown in Table 1:

[0097] Table 1

[0098]

[0099] In this example, the main vehicle can be set as an intelligent heavy-duty truck, and the test value interval of the main vehicle speed is set to 50-80km / h based on the conventional high-speed driving speed range of intelligent heavy-duty trucks. In order to obtain more comprehensive test data, the preset value interval is set to 5km / h in this example. Based on this, the number of scenarios corresponding to the main vehicle speed is determined to be 7, with specific values ​​of 50, 55, 60...75, 80km / h; accordingly, similar settings are made for other automatic lane change parameters.

[0100] Based on this, in this test scenario, a total of 7*7*11*11*31=183799 test cases are constructed, and then these test cases are spliced ​​to generate a test case sequence corresponding to this test scenario, so as to facilitate batch testing in the simulation test software and complete the testing of a large number of test cases in batches.

[0101] S103: In a simulation test scenario, perform an automatic lane change test on the test case sequence to obtain a test result.

[0102] For testing the automatic lane change function, after obtaining a simulation test scenario and a corresponding test case sequence, the automatic lane change test can be performed on the test case sequence within the simulation test scenario to obtain test results. It is understood that this test can be performed using simulation test software to complete batch testing of the test case sequence.

[0103] It can be understood that the vehicle's automatic lane-changing function is controlled by the vehicle's automatic lane-changing algorithm. Testing the vehicle's automatic lane-changing function can also be considered a test and evaluation of the automatic lane-changing algorithm. Therefore, to obtain test results for the automatic lane-changing algorithm, one possible implementation involves performing automatic lane-changing tests on the test case sequence using the automatic lane-changing algorithm in a simulation test scenario to obtain test results. This facilitates evaluation of the automatic lane-changing algorithm based on the test results.

[0104] Since the purpose of testing the automatic lane changing function and the automatic lane changing algorithm is to optimize them to obtain an automatic lane changing function and an automatic lane changing algorithm with better performance, a possible implementation may further include the following steps:

[0105] Perform data processing on the test results and determine the automatic lane change boundary value corresponding to the simulation test scenario based on the automatic lane change parameters;

[0106] Evaluate the automatic lane changing algorithm according to the automatic lane changing boundary value to obtain an evaluation result;

[0107] The automatic lane changing algorithm is optimized according to the evaluation results so that the evaluation results corresponding to the optimized automatic lane changing algorithm meet the target conditions.

[0108] Specifically, the test results can be processed to determine the automatic lane change boundary value corresponding to the simulation test scenario. The automatic lane change algorithm can then be evaluated based on the automatic lane change boundary value to obtain an evaluation result. If the current evaluation result indicates that the automatic lane change algorithm tested does not meet the expected automatic lane change performance, the automatic lane change algorithm can be optimized and retested to ensure that the evaluation result corresponding to the optimized automatic lane change algorithm meets the target conditions.

[0109] It should be noted that the automatic lane change boundary is an indicator used to evaluate the lane changing situation in this simulation test scenario. It can be set according to the actual test requirements, and this application does not impose any restrictions on this. For example, it can be a parameter determined according to the evaluation indicators corresponding to the specific scenario, and then the minimum value of these parameters is extracted from the test results as the automatic lane change boundary value. These parameters may include the minimum value of parameters such as the relative distance between the main vehicle and the target vehicle, the collision time, and the following distance. Alternatively, the automatic lane change boundary can be set to the lane change aggressiveness and lane change efficiency according to the test requirements, based on which different versions of the automatic lane change algorithm can be evaluated more intuitively.

[0110] It is understood that the test case sequence includes multiple test cases, and accordingly, the test results include the test results corresponding to each test case. To improve the accuracy of the automatic lane change boundary value determined based on the test results, the test results can first be preprocessed to obtain a valid test result. Then, based on the valid test result, subsequent processes such as determining the automatic lane change boundary value and evaluating and optimizing the automatic lane change algorithm can be carried out. Therefore, in one possible implementation, the test results include lane change characteristic data of the vehicle under test performing automatic lane changes. The test results can then be screened based on the lane change characteristic data to obtain a valid test result. Finally, the valid test results are data processed to determine the automatic lane change boundary value.

[0111] Lane-changing characteristic data is a parameter that can indicate whether a vehicle has automatically changed lanes. By filtering test results based on this data, it is possible to eliminate test results in which the vehicle did not automatically change lanes. Valid test results that are filtered out can be considered to indicate that the vehicle has automatically changed lanes. Subsequent analysis based on these valid test results can improve the accuracy of determining the automatic lane-changing boundary value.

[0112] It should be noted that lane-changing characteristic data is a parameter that can indicate that a vehicle has automatically changed lanes. The specific parameters can be set based on actual circumstances and are not limited in this application. For example, lane-changing characteristic data can be the vehicle's lane number; a change in the lane number indicates that the vehicle has automatically changed lanes. Alternatively, a lane-changing characteristic parameter can be the vehicle's steering angle; if the steering angle during driving is greater than a predetermined angle, the vehicle is considered to have automatically changed lanes.

[0113] In the embodiment of the present application, the lane change characteristic parameter is set as the vehicle's driving lane number as an example. Specifically, the lane change characteristic data includes the driving lane number of the vehicle to be tested, and then the test result in which the driving lane number is changed in the test result is extracted as the aforementioned valid test result. Figure 3 As shown, the horizontal axis is the test time and the vertical axis is the driving lane number. It can be seen that during the test time of 1-8132, the driving lane number is -3 (-3 can represent the rightmost lane). At 8132, the vehicle changes lanes. After completing the lane change, during the test time of 8132-8824, the driving lane number is -2 (-2 can represent the middle lane). It can be seen that during the test cycle, the driving lane number changes, indicating that the vehicle completes the automatic lane change, and this test result is the valid test result.

[0114] Furthermore, different lane-changing scenarios require different simulation test scenarios and different automatic lane-changing parameters. Similarly, the evaluation metrics used in the test results after the test are completed also differ. Therefore, when processing the test results to extract evaluation metrics for different simulation test scenarios, analysis can be tailored to the specific circumstances.

[0115] The embodiment of the present application provides corresponding evaluation indicators for the aforementioned typical lane-changing scenarios, as shown in Table 2:

[0116] Table 2

[0117]

[0118] For see Figure 2d In the scenario shown above, "Overtaking and changing lanes with a high-speed vehicle coming from behind the target lane," the lane changing situation is relatively complex and can be divided into the following two outcomes based on the actual situation:

[0119] (1) The target vehicle VT2 overtakes the main vehicle, and the main vehicle changes lanes

[0120] In this case, the evaluation indicators are the main vehicle speed V at the time of lane change, the distance D2 between the main vehicle and the target vehicle VT2 in the driving direction, and the following time distance THW=D2 / V between the main vehicle and the target vehicle VT2 at the time of lane change.

[0121] (2) The target vehicle VT2 does not overtake the main vehicle, and the main vehicle changes lanes

[0122] In this case, the evaluation indicators are the main vehicle speed V at the time of lane change, the distance D2 between the main vehicle and the target vehicle VT2 in the driving direction, and the collision time TTC with the target vehicle VT2 at the time of lane change = D2 / (V2-V).

[0123] That is, evaluation indicators need to be set for different scenarios based on actual conditions, and then a differential analysis of the test results corresponding to different scenarios is performed to obtain the automatic lane changing test conditions of the vehicle to be tested in different scenarios.

[0124] For ease of understanding, the present application embodiment still uses the aforementioned Figure 2d Taking the test results corresponding to the lane-changing scenario shown as an example, the automatic lane-changing boundaries are set to lane-changing aggressiveness and lane-changing efficiency. Accordingly, the target conditions can be set according to the automatic lane-changing boundaries. For example, when the automatic lane-changing boundaries are lane-changing aggressiveness and lane-changing efficiency, the target conditions can be set to ensure that the lane-changing aggressiveness and lane-changing efficiency reach preset levels. Based on this, the test results can be fed back to the automatic lane-changing algorithm, and the automatic lane-changing algorithm can be optimized to achieve version iteration of the automatic lane-changing algorithm and obtain an automatic lane-changing algorithm with better automatic lane-changing performance. Specifically:

[0125] In the specific case of "(1) target vehicle VT2 overtakes the main vehicle, and the main vehicle changes lanes", since the main vehicle changes lanes after the target vehicle VT2 overtakes the main vehicle, in this case, there is a risk of rear-end collision with the target vehicle VT2 when the main vehicle changes lanes. It can be understood that the greater the distance between the main vehicle and the target vehicle VT2 when changing lanes, the smaller the rear-end collision risk. Accordingly, the main vehicle needs to wait for the target vehicle VT2 to overtake the main vehicle for a period of time before changing lanes, which will affect the lane changing efficiency of the main vehicle. Therefore, in this case, the lane changing efficiency can be used as an evaluation indicator of the lane changing boundary. Figure 4a As shown, the horizontal axis is the version number of the automatic lane change algorithm, including three versions: V1.0, V2.0 and V3.0. The left vertical axis is the distance D2 between the main vehicle and the target vehicle VT2 in the driving direction, and the right vertical axis is the following time distance THW. It can be seen that as the automatic lane change algorithm is optimized from V1.0 to V3.0, the lane change efficiency in this scenario has been improved.

[0126] In the specific case of "(2) target vehicle VT2 has not overtaken the main vehicle, and the main vehicle changes lanes", since the main vehicle changes lanes before the target vehicle VT2 has overtaken the main vehicle, in this case, there is a risk of collision with the target vehicle VT2 when the main vehicle changes lanes. It can be understood that the greater the distance between the main vehicle and the target vehicle VT2 when changing lanes, the smaller the collision risk. Therefore, in this case, the aggressiveness of lane change can be used as an evaluation indicator of the lane change boundary. Figure 4b As shown, the horizontal axis is the version number of the automatic lane change algorithm, including three versions: V1.0, V2.0 and V3.0. The left vertical axis is the distance D2 between the main vehicle and the target vehicle VT2 in the driving direction, and the right vertical axis is the collision time TTC. It can be seen that as the automatic lane change algorithm is optimized from V1.0 to V3.0, the lane change aggressiveness in this scenario has increased.

[0127] Based on this, we can preliminarily conclude that the optimized automatic lane change algorithm, version V3.0, outperforms versions V2.0 and V1.0, and can be considered to meet the aforementioned target conditions. It should be noted that since the target conditions can be set based on actual test optimization requirements, further optimization and testing can be performed after version V3.0 based on actual needs to obtain an automatic lane change algorithm that is superior to version V3.0.

[0128] As can be seen from the above technical solution, first, a simulation test scenario for the vehicle under test to perform automatic lane change is obtained. The simulation test scenario is used to simulate the actual automatic lane change scenario of the vehicle under test. Then, a test case sequence corresponding to the simulation test scenario is called, and the test case sequence is tested for automatic lane change in the simulation test scenario to obtain a test result. Since the test case sequence is constructed based on the automatic lane change parameters of the simulation test scenario, and the automatic lane change parameters are adjustable, based on this, it can be adjusted within the test value range of the automatic lane change parameters to construct a test case sequence that can fully cover the test value range of the automatic lane change parameters in the simulation test scenario. Therefore, the test result obtained by performing the automatic lane change test based on the test case sequence can fully reflect the various automatic lane change situations of the vehicle under test in the simulation test scenario. It can be seen that a simulation test method is provided for testing the automatic lane change function of a vehicle. For each simulation test scenario, a corresponding test case sequence can be constructed. Then, the test of the test case sequence is completed by simulation testing. Compared with the actual vehicle field test method, the test of the automatic lane change function can be completed more quickly, thereby improving the test efficiency.

[0129] Figure 5 This is a structural diagram of a vehicle automatic lane change test device provided in an embodiment of the present application. The device includes an acquisition unit 501, a calling unit 502, and a testing unit 503:

[0130] The acquisition unit 501 is used to acquire a simulation test scenario of the vehicle under test performing automatic lane change;

[0131] The calling unit 502 is configured to call a test case sequence corresponding to the simulation test scenario; the test case sequence is constructed based on the automatic lane change parameters of the simulation test scenario, and the automatic lane change parameters are adjustable;

[0132] The testing unit 503 is configured to perform an automatic lane change test on the test case sequence in the simulation test scenario to obtain a test result.

[0133] Optionally, the testing unit is further used to:

[0134] In the simulation test scenario, an automatic lane changing algorithm is used to perform an automatic lane changing test on the test case sequence to obtain a test result.

[0135] Optionally, it also includes a determination unit, an evaluation unit, and an optimization unit:

[0136] The determining unit is configured to perform data processing on the test result and determine an automatic lane change boundary value corresponding to the simulation test scenario according to the automatic lane change parameter;

[0137] The evaluation unit is configured to evaluate the automatic lane changing algorithm according to the automatic lane changing boundary value to obtain an evaluation result;

[0138] The optimization unit is configured to optimize the automatic lane changing algorithm according to the evaluation result, so that the evaluation result corresponding to the optimized automatic lane changing algorithm meets a target condition.

[0139] Optionally, the test result includes lane-changing characteristic data of the vehicle under test performing automatic lane changing, and the determining unit is further configured to:

[0140] Filtering the test results according to the lane-changing characteristic data to obtain valid test results;

[0141] Data processing is performed on the valid test results, and the automatic lane change boundary value is determined according to the automatic lane change parameters.

[0142] Optionally, the lane change characteristic data includes a lane number of the vehicle to be tested, and the determining unit is further configured to:

[0143] The test result in which the driving lane number is changed in the test results is extracted as the valid test result.

[0144] Optionally, also include building blocks:

[0145] The construction unit is used to construct a simulation scenario library for the automatic lane changing of the vehicle to be tested;

[0146] The acquisition unit is further configured to call the simulation test scenario from the simulation scenario library.

[0147] Optionally, the acquiring unit is further configured to:

[0148] Obtaining a test value range and a preset value interval of the automatic lane change parameter;

[0149] determining a plurality of automatic lane change parameter values ​​according to the test value interval and the preset value interval;

[0150] Constructing a test case according to the multiple automatic lane change parameter values;

[0151] The test cases are spliced ​​together to obtain the test case sequence.

[0152] As can be seen from the above technical solution, first, a simulation test scenario for the vehicle under test to perform automatic lane change is obtained. The simulation test scenario is used to simulate the actual automatic lane change scenario of the vehicle under test. Then, a test case sequence corresponding to the simulation test scenario is called, and the test case sequence is tested for automatic lane change in the simulation test scenario to obtain a test result. Since the test case sequence is constructed based on the automatic lane change parameters of the simulation test scenario, and the automatic lane change parameters are adjustable, based on this, it can be adjusted within the test value range of the automatic lane change parameters to construct a test case sequence that can fully cover the test value range of the automatic lane change parameters in the simulation test scenario. Therefore, the test result obtained by performing the automatic lane change test based on the test case sequence can fully reflect the various automatic lane change situations of the vehicle under test in the simulation test scenario. It can be seen that a simulation test method is provided for testing the automatic lane change function of a vehicle. For each simulation test scenario, a corresponding test case sequence can be constructed. Then, the test of the test case sequence is completed by simulation testing. Compared with the actual vehicle field test method, the test of the automatic lane change function can be completed more quickly, thereby improving the test efficiency.

[0153] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to the partial description of the method embodiments. The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without expending creative work.

[0154] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0155] The above describes in detail a method and apparatus for testing automatic lane change for a vehicle provided in an embodiment of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is intended only to facilitate understanding of the present invention. Furthermore, those skilled in the art will appreciate that variations in the specific implementation and scope of application of the present invention may occur.

[0156] In summary, the contents of this specification should not be construed as limiting this application. Any changes or substitutions that can be readily conceived by a person skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Moreover, based on the implementations provided in the above aspects, this application can also be further combined to provide more implementations.

Claims

1. A method for testing automatic lane change of a vehicle, characterized in that: The method comprises: Obtain a simulation test scenario of the vehicle under test performing automatic lane change; Calling a test case sequence corresponding to the simulation test scenario; the test case sequence is constructed based on the automatic lane change parameters of the simulation test scenario, and the automatic lane change parameters are adjustable; In the simulation test scenario, an automatic lane change test is performed on the test case sequence using an automatic lane change algorithm to obtain a test result, wherein the test result includes lane change characteristic data of the automatic lane change performed by the vehicle under test, wherein the lane change characteristic data is a parameter characterizing that the vehicle under test has performed the automatic lane change; Filtering the test results according to the lane-changing characteristic data to obtain valid test results; performing data processing on the valid test results and determining the automatic lane change boundary value according to the automatic lane change parameter, wherein the automatic lane change boundary is an indicator for evaluating the lane change situation in the simulation test scenario; evaluating the automatic lane changing algorithm according to the automatic lane changing boundary value to obtain an evaluation result; The automatic lane changing algorithm is optimized according to the evaluation result, so that the evaluation result corresponding to the optimized automatic lane changing algorithm meets the target condition.

2. The method according to claim 1, characterized in that The lane-changing characteristic data includes the lane number of the vehicle to be tested, and the test results are screened according to the lane-changing characteristic data to obtain valid test results, including: The test result in which the driving lane number is changed in the test results is extracted as the valid test result.

3. The method according to any one of claims 1 to 2, characterized in that Also includes: Constructing a simulation scenario library for the vehicle under test to perform automatic lane changing; The step of obtaining a simulation test scenario in which the vehicle under test performs automatic lane change includes: The simulation test scenario is called from the simulation scenario library.

4. The method according to any one of claims 1 to 2, characterized in that Also includes: Obtaining a test value range and a preset value interval of the automatic lane change parameter; determining a plurality of automatic lane change parameter values ​​according to the test value interval and the preset value interval; Constructing a test case according to the multiple automatic lane change parameter values; The test cases are spliced ​​together to obtain the test case sequence.

5. A vehicle automatic lane-changing test device, characterized in that: The device includes an acquisition unit, a call unit, a test unit, a screening unit, a determination unit, an evaluation unit and an optimization unit: The acquisition unit is used to acquire a simulation test scenario of the vehicle under test performing automatic lane change; The calling unit is configured to call a test case sequence corresponding to the simulation test scenario; the test case sequence is constructed based on the automatic lane change parameters of the simulation test scenario, and the automatic lane change parameters are adjustable; The testing unit is configured to perform an automatic lane change test on the test case sequence using an automatic lane change algorithm in the simulation test scenario to obtain a test result, wherein the test result includes lane change characteristic data of the automatic lane change performed by the vehicle under test, wherein the lane change characteristic data is a parameter indicating that the vehicle under test has performed the automatic lane change; The screening unit is configured to screen the test results according to the lane-changing characteristic data to obtain a valid test result, wherein the lane-changing characteristic data is a parameter indicating that the vehicle under test has performed an automatic lane change; The determining unit is configured to perform data processing on the valid test results and determine an automatic lane change boundary value corresponding to the simulation test scenario based on the automatic lane change parameters, wherein the automatic lane change boundary is an indicator for evaluating the lane change situation in the simulation test scenario; The evaluation unit is configured to evaluate the automatic lane changing algorithm according to the automatic lane changing boundary value to obtain an evaluation result; The optimization unit is configured to optimize the automatic lane changing algorithm according to the evaluation result, so that the evaluation result corresponding to the optimized automatic lane changing algorithm meets a target condition.

Citation Information

Patent Citations

  • Test method and device for autonomous vehicle

    CN114354219A

  • Vehicle testing method, device and equipment based on virtual scene and storage medium

    CN114817072A