A Method and Medium for Screening Test Cases of Intelligent Connected Real Vehicles in a Specific Scenario

Abstract

The present invention provides a method and medium for screening test cases for intelligent networked real vehicle tests in specific scenarios, belonging to the technical field of vehicle testing. This method is based on a test case generation method with different speed combinations and occlusion distance combinations, and screens dangerous scenario test cases by calculating the boundary braking deceleration under each different combination; this method can more comprehensively and intuitively cover possible test scenarios and improve the effectiveness and efficiency of testing.

Description

Technical Field

[0001] The present invention relates to the field of data testing, and particularly to a method and medium for screening intelligent connected vehicle test cases in a specific scenario. Background Art

[0002] The current test technology implementation methods are to design scenarios based on relevant standards, reconstruct combinations based on key elements, and refine and simplify based on real data.

[0003] However, the above three implementation methods all have corresponding problems. The test scenarios set by the relevant standards only cover the most basic and common situations, and it is difficult to comprehensively reflect various complex and extreme situations that may be encountered in actual road driving. Although the key element combination reconstruction method can achieve a high scene coverage, due to the extremely large number of possible element combinations, the number of generated test scenarios is huge, making it difficult to implement all of them, and the test efficiency is low. The cost of collecting and processing real data is high, and the data quality and integrity are difficult to guarantee, which may affect the accuracy and reliability of the refined test scenarios and may be difficult to generalize to more extensive test requirements.

[0004] To address the above problems, this paper proposes a method and medium for screening intelligent connected vehicle test cases in a specific scenario. Summary of the Invention

[0005] The present invention proposes a method and medium for screening intelligent connected vehicle test cases in a specific scenario, aiming to more comprehensively cover potential dangerous scenarios by considering different speed combinations and occlusion distance combinations; and to efficiently screen out high-risk test cases by calculating the boundary braking deceleration under various combinations, improving the efficiency and pertinence of the test.

[0006] To achieve the above object, the present invention provides a method for screening intelligent connected vehicle test cases in a specific scenario, including the following steps:

[0007] S1. Set the test scenario and constraint conditions;

[0008] S11. Set the test scenario as an urban road scenario; specifically, the test scenario is equal to an intersection, a T-junction or a crossroads;

[0009] S12. Initialize the driving speed of the host vehicle HV as ; where ;

[0010] S13. Initialize the driving speed of the test vehicle RV as ; where ;

[0011] S14. Initialize the distance between the occluder on the road side where the host vehicle HV is located and the intersection ;

[0012] S15. Set the collision area as a square with side length W; where the side length W = the width of the host vehicle HV = the width of the test vehicle RV;

[0013] S16. Set the signal lamp identification in the urban road scenario to an unavailable state.

[0014] Among them, the host vehicle HV is a level 2 vehicle, with the ability of auxiliary vehicle perception; it has the ability of auxiliary vehicle execution and can perform longitudinal control such as early warning and braking; it has an ADAS positioning module and can obtain real-time physical position information through the positioning module; it can judge the current state by obtaining the surrounding environment target information, know the collision relationship with each target object, and obtain a suitable trajectory plan; it can fuse the vehicle side perception information and the target information received on the vehicle side through a reasonable perception fusion strategy; it can calculate the early warning time by judging the collision relationship between the crossing vehicle and the host vehicle.

[0015] S2. Under the said test scenario and constraint conditions, establish a collision conflict mathematical model for the host vehicle HV and the test vehicle RV; according to the collision conflict mathematical model, calculate and obtain the first angle and the first collision time ;

[0016] Among them, the calculation formula of the first angle is:

[0017] ;

[0018] Among them, the first angle is the included angle between the connection line of the host vehicle HV and the test vehicle RV and the driving direction of the host vehicle HV when the host vehicle HV discovers the test vehicle RV; is the distance between the test vehicle RV and the collision area when the test vehicle RV is discovered by the host vehicle HV; is the distance between the host vehicle HV and the collision area when the host vehicle HV discovers the test vehicle RV;

[0019] Among them, the calculation formula of the first collision time is:

[0020]

[0021] Among them, the first collision time is the time interval from the moment when the host vehicle HV discovers the test vehicle RV to the moment when the rear of the test vehicle RV leaves the collision area; is the vehicle length of the test vehicle RV; W is the width of the collision area.

[0022] Specifically, take the first collision time As the safety time boundary; the maximum time safety boundary can be understood as: when the host vehicle HV discovers the test vehicle RV, the host vehicle HV starts to take braking avoidance actions. In order to ensure that when the front of the host vehicle HV reaches the collision area, the rear of the test vehicle RV just leaves the collision area, the minimum time required for the host vehicle HV.

[0023] S3. According to the first angle and the first collision time , calculate and obtain the minimum braking deceleration of the host vehicle HV ;

[0024] Among them, the minimum braking deceleration is the minimum braking deceleration required for the host vehicle HV to take braking avoidance actions when it discovers the test vehicle RV.

[0025] The calculation process of the minimum braking deceleration is as follows:

[0026] S31. Set that when the host vehicle HV discovers the test vehicle RV, the braking avoidance action is immediately triggered, and the host vehicle HV brakes with a constant deceleration ;

[0027] Set the maximum braking deceleration to g; where g = 9.8 m / s²;

[0028] Set the friction coefficient u between the vehicle and the road surface to 1;

[0029] Among them, Formula (1)

[0030] is the initial velocity of the host vehicle HV when it discovers the test vehicle RV; is the final velocity when the front of the host vehicle HV reaches the collision area; among them, the initial velocity and the final velocity satisfy the following formula:

[0031] Formula (2)

[0032] Among them, t is the time when the front of the host vehicle HV reaches the collision area after taking braking avoidance actions when the host vehicle HV discovers the test vehicle RV;

[0033] S32. Calculate and obtain the time t when the front of the host vehicle HV reaches the collision area after taking braking avoidance actions when the host vehicle HV discovers the test vehicle RV.

[0034] Substitute Formula (2) into Formula (1) to get:

[0035]

[0036] Furthermore, it can be calculated and obtained that:

[0037]

[0038] Among them, t needs to satisfy: .

[0039] S33. Set the safety time boundary for t selection , that is, set t = , and calculate the minimum braking deceleration ;

[0040] When t = :

[0041] ;

[0042] It can be calculated that:

[0043]

[0044] At this time:

[0045] .

[0046] S4. Use the test scenario and constraint conditions in step S1 and the minimum braking deceleration calculated in step S3 as a test case;

[0047] S5. Adjust the distance of the obstacle on the road side where the host vehicle HV is located from the intersection , the driving speed of the host vehicle HV , and the driving speed of the test vehicle RV , and repeat steps S1 to S4 to generate multiple test cases and form a test case set;

[0048] S6. Screen out the test cases in the test case set where the minimum braking deceleration does not meet the preset conditions as the test cases for the dangerous critical scenario test.

[0049] Among them, the preset conditions include but are not limited to: the minimum braking deceleration is greater than the preset threshold .

[0050] The present invention also provides a computer-readable storage medium, on which computer instructions are stored, and the instructions are called by a processor to execute the above-mentioned method for screening intelligent networked vehicle test cases in a specific scenario.

[0051] The present invention has the following beneficial effects:

[0052] 1. This invention proposes an innovative test case screening method for the on-road test of intelligent connected vehicles in the scenario of being blocked and crossing at intersections. This method first defines the test scenario and constraint conditions, clarifies the test scope and system capability requirements, establishes a mathematical model of collision conflict, determines the collision conditions by analyzing the geometric relationship and speed combination between the host vehicle (HV) and the test vehicle (RV), and calculates the minimum braking deceleration when the host vehicle takes braking avoidance after detecting the test vehicle, providing a model method for improving the accuracy of the host vehicle's braking avoidance action and the screening of high-risk test cases.

[0053] 2. By dynamically adjusting the distance between the obstacle and the intersection, changing the speed combination of the host vehicle and the test vehicle, generating multiple groups of test cases, and calculating the minimum braking deceleration under each test case, the test cases with high-risk collisions are screened out, thus helping testers more intuitively expand the test scenarios of relevant standards and improving the effectiveness and efficiency of the test. Description of the Drawings

[0054] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0055] Figure 1 It is a schematic diagram of the actual environment simulated in a method for screening test cases of intelligent connected on-road vehicles in a specific scenario. Detailed Embodiments

[0056] The following will describe the exemplary embodiments of the present application with reference to the drawings. Various details of the embodiments of the present application are included to help understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described here without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted below.

[0057] As Figure 1 shown, the present invention provides a method for screening test cases of intelligent connected on-road vehicles in a specific scenario, including the following steps:

[0058] S1. Set the test scenario and constraint conditions;

[0059] S11. Set the test scenario as an urban road scenario; specifically, the test scenario is equal to an intersection, a T-junction, or a crossroads;

[0060] S12. Initialize the driving speed of the host vehicle HV to ; where ;

[0061] S13. Initialize the driving speed of the test vehicle RV to ; where ;

[0062] S14. Initialize the distance of the obstacle on the road side where the host vehicle HV is located from the intersection ;

[0063] S15. Set the collision area as a square with side length W; where the side length W = the width of the host vehicle HV = the width of the test vehicle RV;

[0064] S16. Set the signal lamp identification in the urban road scenario to the unavailable state.

[0065] Among them, the host vehicle HV is a level L2 vehicle, with the ability of auxiliary vehicle perception; with the ability of auxiliary vehicle execution, it can perform longitudinal control such as warning and braking; it has an ADAS positioning module and can obtain real-time powerless position information through the positioning module; it can judge the current state by obtaining the surrounding environment target information, know the collision relationship with each target object, and obtain a suitable trajectory plan; it can fuse the vehicle side perception information and the target information received on the vehicle side through a reasonable perception fusion strategy; it can calculate the warning time by judging the collision relationship between the crossing vehicle and the self-vehicle.

[0066] S2. Under the said test scenario and constraint conditions, establish a collision conflict mathematical model for the host vehicle HV and the test vehicle RV; according to the collision conflict mathematical model, calculate and obtain the first angle and the first collision time ;

[0067] Among them, the calculation formula of the first angle is:

[0068] ;

[0069] Among them, the first angle is the included angle between the connection line of the host vehicle HV and the test vehicle RV and the driving direction of the host vehicle HV when the host vehicle HV discovers the test vehicle RV; is the distance between the test vehicle RV and the collision area when the test vehicle RV is discovered by the host vehicle HV; is the distance between the host vehicle HV and the collision area when the host vehicle HV discovers the test vehicle RV;

[0070] Among them, the calculation formula of the first collision time is:

[0071]

[0072] Among them, the first collision time is the time interval from the moment when the host vehicle HV discovers the test vehicle RV to the moment when the rear of the test vehicle RV leaves the collision area; is the vehicle length of the test vehicle RV; W is the width of the collision area.

[0073] Specifically, take the first collision time as the safety time boundary; the maximum time safety boundary can be understood as: starting from the moment when the host vehicle HV discovers the test vehicle RV, the host vehicle HV starts to take braking avoidance actions. In order to ensure that when the front of the host vehicle HV reaches the collision area, the rear of the test vehicle RV just leaves the collision area, the minimum time required for the host vehicle HV.

[0074] S3. According to the first angle and the first collision time , calculate and obtain the minimum braking deceleration of the host vehicle HV;

[0075] Among them, the minimum braking deceleration is the minimum braking deceleration required when the host vehicle HV discovers the test vehicle RV and takes braking avoidance actions.

[0076] The calculation process of the minimum braking deceleration is as follows:

[0077] S31. Set that when the host vehicle HV discovers the test vehicle RV, the braking avoidance action is immediately triggered, and the host vehicle HV brakes with a constant deceleration ;

[0078] Set the maximum braking deceleration to g; where g = 9.8 m / s²;

[0079] Set the friction coefficient u between the vehicle and the road surface to 1;

[0080] Among them, Formula (1)

[0081] is the initial velocity of the host vehicle HV when it discovers the test vehicle RV; is the final velocity when the front of the host vehicle HV reaches the collision area; among them, the initial velocity and the final velocity satisfy the following formula:

[0082] Formula (2)

[0083] Wherein, t is the time when the front of the host vehicle HV reaches the collision area after taking a braking avoidance action when the host vehicle HV discovers the test vehicle RV;

[0084] S32. Calculate and obtain the time t when the front of the host vehicle HV reaches the collision area after taking a braking avoidance action when the host vehicle HV discovers the test vehicle RV.

[0085] Substituting formula (2) into formula (1) gives:

[0086]

[0087] Furthermore, it can be calculated and obtained:

[0088]

[0089] Wherein, t needs to satisfy: .

[0090] S33. Set the safety time boundary for t selection , that is, set t = , and calculate the minimum braking deceleration ;

[0091] When t = :

[0092] ;

[0093] It can be calculated that:

[0094]

[0095] At this time:

[0096] .

[0097] S4. Take the test scenario and constraint conditions in step S1 and the minimum braking deceleration calculated in step S3 as a test case;

[0098] S5. Adjust the distance of the obstacle on the road side where the host vehicle HV is located from the intersection , the driving speed of the host vehicle HV , the driving speed of the test vehicle RV , and repeat steps S1 to S4 to generate multiple test cases to form a test case set;

[0099] S6. Screen out the test cases in the test case set where the minimum braking deceleration does not meet the preset conditions as the test cases for the critical dangerous scenario.

[0100] Wherein, the preset conditions include but are not limited to: the minimum braking deceleration Greater than a preset threshold 。

[0101] Furthermore, step S6 further includes:

[0102] S61. Obtain multiple test case sets in the test case set where the minimum braking deceleration is greater than a preset threshold as the first dangerous critical scenario test case set; Greater than a preset threshold as the first dangerous critical scenario test case set;

[0103] S62. Select any two test cases from the first dangerous critical scenario test case set and , and respectively obtain the and in the test cases , , values;

[0104] Among them, the value corresponding to the test case is , , ;

[0105] The value corresponding to the test case is , , ;

[0106] S63. Calculate the case distance H between the test case and the test case ;

[0107] Among them, ;

[0108] S64. When the case distance H is less than the preset threshold , calculate , ;

[0109] When , delete the test case from the first dangerous critical scenario test case set and execute step S66;

[0110] When , delete the test case from the first dangerous critical scenario test case set and execute step S66;

[0111] When the case distance H is greater than or equal to the preset threshold , execute step S65;

[0112] S65. Calculate the test case and the difference in the corresponding minimum braking deceleration, when the difference is less than a preset threshold calculate ; ;

[0113] When delete the test case from the first dangerous critical scenario test case set , and execute step S66;

[0114] When delete the test case from the first dangerous critical scenario test case set , and execute step S66;

[0115] S66. For any two test cases in the first dangerous critical scenario test case set, repeatedly execute steps S62 to S65 to obtain a second dangerous critical scenario test case set;

[0116] S67. Use the test cases in the second dangerous critical scenario test case set as the dangerous critical scenario test cases.

[0117] The present invention has the following beneficial effects:

[0118] 1. The present invention proposes an innovative test case screening method for the in-vehicle test of intelligent connected vehicles in the scenario of occlusion and crossing at intersections. The method first defines the test scenario and constraint conditions, clarifies the test scope and system capability requirements, establishes a collision conflict mathematical model, determines the collision conditions by analyzing the geometric relationship and speed combination between the host vehicle (HV) and the test vehicle (RV), and calculates the minimum braking deceleration when the host vehicle takes braking avoidance after detecting the test vehicle, providing a model method for improving the accuracy of the host vehicle's braking avoidance action and the screening of high-risk test cases.

[0119] 2. By dynamically adjusting the distance between the occluder and the intersection, changing the speed combination of the host vehicle and the test vehicle, generating multiple groups of test cases, and calculating the minimum braking deceleration under each test case, the test cases with high-risk collisions are screened out, thus helping testers more intuitively expand the test scenarios of relevant standards and improving the effectiveness and efficiency of the test.

[0120] 3. The present invention proposes a test case screening method. First, screen the test cases with a minimum braking deceleration greater than a preset threshold to form a first dangerous critical scenario test case set; then, through multi-level judgments on the minimum braking deceleration, host vehicle speed, test vehicle speed, and the distance between the occluder and the intersection in the test cases, eliminate the test cases with small distances and high similarity to form a second dangerous critical scenario test case set, improving the accuracy of high-risk test case screening.

[0121] The medium in the present invention can adopt any combination of one or more computer-readable media. The medium can be a computer-readable signal medium or a computer-readable storage medium. The medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the medium (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0122] The above specific embodiments do not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. A method for screening intelligent networked vehicle test cases in a specific scenario, characterized in that It includes the following steps: S1. Set the test scenario and constraint conditions; S11. Set the test scenario as an urban road scenario; the test scenario is equal to an intersection, a T-junction or a crossroads; S12. Initialize the driving speed of the host vehicle to V H ; where, 0 km / h ≤ V H ≤ 60 km / h; S13. Initialize the driving speed of the test vehicle RV to V R ; where 0 km / h ≤ V R ≤ 60 km / h; S14. Initialize the distance d from the obstacle on the road side where the host vehicle HV is located to the intersection obs ; S15. Set the collision area as a square with side length W; wherein, the side length W = the width of the host vehicle HV = the width of the test vehicle RV; S16. Set the signal lamp identification in the urban road scenario to the unavailable state; S2. Establish a mathematical model of the collision conflict between the host vehicle HV and the test vehicle RV under the said test scenario and constraint conditions; calculate and obtain the first angle α and the first collision time t according to the said mathematical model of the collision conflict ht ; S3. Calculate the minimum braking deceleration a of the host vehicle HV based on the first angle α and the first collision time t ht ; H ; S4. Take the test scenario and constraint conditions in step S1 and the minimum braking deceleration a calculated in step S3 H as a test case; S5. Adjust the distance d between the obstacle on the road side where the host vehicle HV is located and the intersection obs , the driving speed V of the host vehicle HV H , the driving speed V of the test vehicle RV R , repeat steps S1 to S4 to generate multiple test cases and form a test case set; S6. Screen the minimum braking deceleration a in the test case set H Use the test cases that do not meet the preset conditions as the test cases for dangerous critical scenarios; Among them, step S2 specifically includes: The calculation formula for the first angle α is: Among them, the first angle α is the included angle between the connection line of the host vehicle HV and the test vehicle RV and the driving direction of the host vehicle HV when the host vehicle HV discovers the test vehicle RV; d R is the distance between the test vehicle RV and the collision area when the test vehicle RV is discovered by the host vehicle HV; d H is the distance between the host vehicle HV and the collision area when the host vehicle HV discovers the test vehicle RV; Among them, the first collision time t ht is calculated by the following formula: Among them, the first collision time t ht is the time interval from the moment when the host vehicle HV discovers the test vehicle RV to the moment when the rear of the test vehicle RV leaves the collision area; L is the vehicle length of the test vehicle RV; W is the width of the collision area; Specifically, take the first collision time t ht as the safety time boundary; Among them, step S3 specifically includes: the minimum braking deceleration a H The calculation process is as follows: S31. Set that when the host vehicle HV detects the test vehicle RV, the braking avoidance action is immediately triggered, and the host vehicle HV brakes with a constant deceleration a ′ H Apply the brakes; Set the maximum braking deceleration to g; where g = 9.8 m / s 2 ; Set the friction coefficient u between the vehicle and the road surface to 1; Among them, is the initial speed of the test vehicle RV detected by the host vehicle HV; is the final speed when the front of the host vehicle HV reaches the collision area; wherein, the initial speed and the final speed satisfy the following formula: Among them, t is the time when the front of the host vehicle HV reaches the collision area after the host vehicle HV takes a braking avoidance action when it discovers the test vehicle RV; S32. Calculate the time t when the front of the host vehicle HV reaches the collision area after the host vehicle HV takes a braking avoidance action when it discovers the test vehicle RV; It can be obtained that: Furthermore, it can be calculated and obtained: Among them, t needs to satisfy: t ≥ t ht ; S33. Set the safety time boundary \(t\) to select \(t\) ht , that is, set \(t = t\) ht , calculate the minimum braking deceleration \(a\) H ; When t = t ht : It can be calculated that: At this time:

2. A method for screening intelligent networked real vehicle test cases in a specific scenario according to claim 1, characterized in that: Minimum braking deceleration a H It is the minimum braking deceleration required for the master vehicle HV to take braking avoidance actions when it detects the test vehicle RV.

3. A method for screening intelligent networked vehicle test cases in a specific scenario according to claim 1, characterized in that Step S6 includes: The preset conditions include: the minimum braking deceleration a H being greater than a preset threshold t ah .

4. A computer-readable storage medium, characterized in that, The medium stores computer instructions, and the computer instructions execute the method according to any one of claims 1-3.

Images