Urban navigation system expected function safety test evaluation model construction method
By constructing an expected functional safety test evaluation model for the urban pilot system, the problems of poor controllability of the test scenarios and single evaluation indicators in the existing technology are solved, and a comprehensive and in-depth evaluation of the expected functional safety of the urban pilot system and a cross-scene horizontal comparison are achieved.
Patent Information
- Application Number
- CN202510027945.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-08
- Publication Date
- 2025-05-06
AI Technical Summary
The expected functional safety test of the existing urban pilot system has problems such as poor controllability in the test scenario, single evaluation indicators, and the failure of the comprehensive evaluation system to achieve comprehensive cross-scene comparisons, resulting in the inability to scientifically and reliably evaluate the expected functional safety performance of the urban pilot system.
A model for expected functional safety testing and evaluation of urban pilot system is constructed, including building an expected functional safety simulation test scenario for urban pilot system, formulating multi-stage simulation testing schemes, constructing comprehensive evaluation indicators based on test data, and introducing test scenario weight factors based on the relative complexity of the scene, and establishing an expected safety evaluation model for urban pilot system.
It has achieved a more comprehensive and in-depth evaluation of the expected functional safety of the city's pilot system, and can conduct horizontal comparisons across scenarios, identify key boundary scenario information, and improve the accuracy and comparability of the test results.
Smart Images
Figure CN119939928A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of intelligent connected vehicle testing technology, and in particular to a method for constructing an expected functional safety test evaluation model for a city navigation system. Background Art
[0002] The emergence of intelligent connected vehicles is profoundly changing the automotive and transportation industries. This change not only improves vehicle safety and driving experience, but also promotes the sustainable development of urban transportation systems and leads the transformation of travel modes. Among them, the city navigation system, as one of the core functions of intelligent connected vehicles, realizes functions such as accurate judgment of driving paths, autonomous lane changes, driving according to navigation planning routes, and start and stop at traffic lights through intelligent perception and data sharing between vehicles and the surrounding environment, helping drivers make better decisions in complex urban environments, reducing driving burdens while improving driving experience and safety. With the advancement of intelligent connected vehicle access and road access pilot projects across the country, and the increasing penetration rate of city navigation systems, the safety testing of city navigation systems is particularly important for ensuring vehicle driving safety. In addition to conventional functional tests, in order to ensure that there are no unreasonable risks caused by insufficient expected functions, it is necessary to conduct special expected functional safety tests on vehicles. Through expected functional safety tests, the ability of the city navigation system to deal with safety hazards such as performance limitations and common human errors is evaluated, and the boundaries of system capabilities are deeply explored, aiming to ensure that the city navigation system can perform driving tasks safely and stably in changing driving scenarios.
[0003] Current standards related to expected functions, such as "Safety of Intended Functions of Road Vehicles" (GB / T43267-2023), regulate the framework of the forward development process of expected functional safety at the general level. However, the relevant standards for the product technology and application of the urban navigation system are still being formulated and improved, and the relevant test method requirements have not yet formed a system. Existing research on the expected function testing of the urban navigation system faces limitations such as a single evaluation indicator and the inability of the evaluation system to achieve comprehensive comparison across scenarios, making it difficult to scientifically and reliably evaluate the expected functional safety performance of the urban navigation system.
[0004] In addition, the application scenarios of the urban navigation system are mostly congested crossroads, crowded urban roads and urban one-way streets, involving dynamic elements such as traffic flow, various pedestrians, non-motor vehicles and traffic signals. In terms of the flexibility, controllability and repeatability of the test environment, the closed-field test method based on actual road conditions has weak simulation capabilities for some dynamic elements, and it is difficult to effectively control external variables such as lighting and weather. However, although simulation testing can quickly adjust and simulate a variety of scenario conditions in different virtual environments, the accuracy of its test results is limited by the accuracy of models such as vehicle dynamics. Therefore, the expected functional safety test of the urban navigation system has problems such as poor controllability of the test scenario, single evaluation indicators and comprehensive evaluation system. These problems will affect the effectiveness and reliability of the expected functional test, resulting in the inability to fully evaluate the performance of the car under a variety of actual driving conditions, and may ignore potential safety hazards and design defects. Among them, the lack of a comprehensive evaluation system that can achieve effective horizontal comparison across multiple scenarios will make it impossible to correlate the results of different test scenarios, resulting in the lack of failure scenario information in the evaluation results. For the intelligent connected vehicle industry, the reliability and effectiveness of the testing process, as well as the comprehensiveness and integrated nature of the quantitative evaluation of test results, are severely affected, hindering the formulation of effective industry standards and best practices, and increasing uncertainty and risk in the development process. Summary of the invention
[0005] One of the purposes of the present invention is to provide a method for constructing a safety test evaluation model for the expected functions of a city navigation system, so as to solve the problems in the prior art of the safety test of the expected functions of the city navigation system, such as poor controllability of the test scenarios and single evaluation indicators.
[0006] In order to achieve the above object, the technical solution adopted by the present invention is as follows:
[0007] A method for constructing a safety test evaluation model for an expected function of a city navigation system comprises the following steps:
[0008] S1. Construct the expected functional safety simulation test scenarios of the urban navigation system, including the simulation test scenarios of urban congested intersections, the simulation test scenarios of crowded urban trunk roads and the simulation test scenarios of urban one-way streets;
[0009] S2. Develop a multi-stage urban congested intersection simulation test plan, a multi-stage urban trunk road simulation test plan, and a multi-stage urban one-way road simulation test plan, and conduct the expected functional safety test of the urban navigation system of the test vehicle, and obtain and save the expected functional safety test data;
[0010] S3. Constructing comprehensive evaluation indicators based on the expected functional safety test data, including objective evaluation indicators and subjective evaluation indicators;
[0011] Analyzing the relative complexity of the simulation test scenario, introducing a test scenario weight factor based on the relative complexity of the scenario, and determining the test scenario weight factor according to the expected functional safety test data;
[0012] S4. Establish an expected safety evaluation model for the urban navigation system based on the test scenario weight factors.
[0013] According to the above-mentioned technical means, based on the in-loop semi-simulation test of the whole vehicle, the expected functional safety test of the urban navigation system in three typical urban scenarios, namely urban congested intersections, urban crowded main roads and urban one-way streets, was realized. While achieving flexible control over the dynamic elements of the scene, real test feedback can be obtained; a multi-dimensional quantitative test result combining subjective and objective evaluation indicators was constructed, achieving a more comprehensive and in-depth evaluation of the expected functional safety of the urban navigation system.
[0014] In addition, the expected safety evaluation model of the urban navigation system of the present invention integrates the test scenario weight factor based on the relative complexity of the scenario, quantifies the test results of the scenario test, and can realize horizontal comparison across scenarios, which helps to accurately identify and extract key boundary scenario information from low-scoring test results.
[0015] Furthermore, the objective evaluation index in step S3 includes:
[0016] (1) Safety distance control rate I1, calculated as: Where C1 is the sum of the safe distances between the tested vehicle and the front scene elements at each stage in the same simulation test scenario, and C2 is the sum of the minimum distances between the tested vehicle and the front scene elements at each stage in the same simulation test scenario;
[0017] (2) Driving path accuracy I2, calculated as: Where x is the longitudinal distance of the actual driving trajectory of the test vehicle, x∈[0,L], L is the maximum cumulative longitudinal distance of the vehicle in the city pilot driving mode; F(x) is the absolute value of the lateral distance deviation between the predetermined trajectory and the actual trajectory;
[0018] (3) Test pass rate I3, calculated as follows: I3 = [0, 1], where I3 = 0 means the vehicle under test did not pass the planned route, and I3 = 1 means the vehicle under test passed the planned route;
[0019] (4) Driving safety I4, calculated as follows: I4 = [0, 1, 2], where I4 = 0 means there is no violation of traffic rules or collision during the test; I4 = 1 means there is a violation of traffic rules or collision during the test; and I4 = 2 means there is a violation of traffic rules or collision during the test.
[0020] According to the above-mentioned technical means, multiple objective evaluation indicators are constructed, and the test results are quantified based on the test data of the test vehicle, which can make the test results more intuitively understood and analyzed, while ensuring the accuracy and comparability of the test results.
[0021] Furthermore, the subjective evaluation index in step S3 includes:
[0022] The driving trust I5 is calculated as follows: I5=[0,1,2], where I5=0 means that 30% or less of the driving behavior of the city navigation system is consistent with user expectations; I5=1 means that 30%-80% of the driving behavior of the city navigation system is consistent with user expectations; I5=2 means that 80% or more of the driving behavior of the city navigation system is consistent with user expectations.
[0023] Based on the above-mentioned technical means, the introduction of subjective evaluation indicators can directly reflect the user's needs and expectations for the vehicle performance and driving experience in the city navigation driving mode of the test vehicle, so as to supplement the test results that cannot be expressed by the objective evaluation indicators and comprehensively evaluate the expected functional safety performance of the city navigation system.
[0024] Furthermore, the S3 step includes the following sub-steps:
[0025] S31, defining basic scene information features of the simulation test scene, including road structure degree s1, number of lanes s2, number of road facilities s3 and ground visibility s4, to form a basic scene information feature set S0 = {s1, s2, s3, s4};
[0026] Get the scene information feature set S of the i-th simulation test scene i ={s i1 ,s i2 ,s i3 ,s i4};
[0027] S32, based on the basic scene information feature set S0 and the scene information feature set S of the i-th simulation test scene i Calculate the test scenario weight factor λ for the i-th simulation test scenario i , the calculation formula is: λ i ∈[0,1], where d ik is the kth information feature difference of the i-th test scene;
[0028] In the formula, R k is the maximum value of the k-th scene information feature, s ik is the value of the kth scene information feature of the ith simulation test scene, s kis the value of the basic scene information feature, i∈[1,n], n is the number of simulation test scenes, k∈[1,4].
[0029] According to the above-mentioned technical means, the scene information in the simulation test scenario can be quantified, and a variety of complex information can be uniformly quantified into comparable values, which is conducive to objectively evaluating the quality and effect of the expected functional safety test of the urban navigation system, and is conducive to comparing the test results of different scenarios.
[0030] Furthermore, the S4 step includes the following sub-steps:
[0031] S41, establish the test result matrix X of a single simulation test scenario i = [I1, I2, I3, I4, I5], and based on the test result matrix X of a single simulation test scenario i Create a test result scoring matrix In the formula, X i is the test result under the i-th simulation test scenario, i∈[1,n], n is the number of simulation test scenarios, I ij is the jth comprehensive evaluation index I of the test results in the i-th simulation test scenario j , j∈[1,5];
[0032] S42, the jth comprehensive evaluation index I of the test result in the i-th simulation test scenario j Conduct standardized operations;
[0033] S43, the jth comprehensive evaluation index I based on the standardized test results in the i-th simulation test scenario j , determine the indicator weights of each comprehensive evaluation indicator in combination with information entropy;
[0034] S44. Based on the scenario factor weights and the indicator weights, an evaluation model for a single simulation test scenario and a multi-simulation test scenario for the expected functional safety of the city navigation system is established.
[0035] Furthermore, the comprehensive evaluation index is divided into positive index and negative index, the positive index includes safety distance control rate I1, test pass rate I3 and driving confidence I5, the negative index includes driving path accuracy I2 and driving safety; the jth comprehensive evaluation index I of the test result under the i-th simulation test scenario in the step S42 is j The standardization operation includes positive indicator standardization and negative indicator standardization;
[0036] The standardized formula of the positive indicator is:
[0037] The standardized formula of the negative indicator is:
[0038] In the formula, x ij1 and x ij2 is the jth indicator I of the test results in the i-th simulation test scenario j The normalized value, n is the number of simulation test scenarios.
[0039] According to the above technical means, the standardization operation eliminates the dimensional differences between the comprehensive indicators, enables direct comparison and calculation between different indicators, and improves the comparability and calculability of the test data.
[0040] Furthermore, the indicator weight ω of each comprehensive evaluation indicator in the step S43 is j The calculation formula is: Where D j is the amount of information;
[0041] In the formula, s j is the standard deviation of the comprehensive evaluation index described in item j, r mj is the correlation coefficient between the comprehensive evaluation index described in item m and the comprehensive evaluation index described in item j;
[0042] In the formula, x im and x ij are the mth index I of the test results under the i-th simulation test scenario. m and the jth index I j The standardized value, and are the mth index I of the test results in all simulation test scenarios m and the jth index I j The standardized average value, m∈[1,5], j∈[1,5], and n is the number of simulation test scenarios.
[0043] According to the above technical means, the indicator weight of each comprehensive evaluation indicator is determined by combining the information volume and the correlation coefficient of the two comprehensive evaluation indicators, so that the indicator weight calculation of each comprehensive evaluation indicator is more objective, fair and reliable.
[0044] Furthermore, in the step S44:
[0045] The calculation formula for the expected functional safety test results of the urban navigation system in a single simulation test scenario is: In the formula, c i is the test result value of the ith simulation test scenario, λ i is the scenario factor weight of the i-th simulation test scenario, I j ×ωj is the product of the jth indicator and the corresponding weight, i∈[1,n], j∈[1,5], n is the number of simulation test scenarios;
[0046] The calculation formula for the expected functional safety test results of the urban navigation system in multiple simulation test scenarios is: Where C is the expected functional safety test result value of the urban navigation system in multiple simulation test scenarios, i∈[1,n], and n is the number of simulation test scenarios.
[0047] Based on the above-mentioned technical means, the evaluation model for a single test scenario can more accurately reflect the expected functional safety performance of the city navigation system under the test scenario, and is highly targeted; the multi-test scenario evaluation model covers a variety of different test scenarios and can more comprehensively evaluate the expected functional safety performance of the city navigation system under different scenarios.
[0048] Furthermore, the simulation test scheme for the urban congested crossroad is that the initial speed of the tested vehicle is 40km / h, and the test starts after entering the city navigation system mode, which includes four consecutive stages: the first stage is a standing pedestrian in the parking area on the same side of the tested vehicle; the second stage is the driving route of the oncoming car deviates from the central yellow line at a speed of 30km / h; the third stage is the pedestrian crossing from the parking area on the same side of the tested vehicle to the opposite side, and the pedestrian speed is 5km / h; the fourth stage is the vehicle that is parked in the parking area on the same side of the tested vehicle;
[0049] The congested urban main road simulation test scheme is that the initial speed of the tested vehicle is 30km / h, located in the middle lane, and after entering the city navigation system mode, the test starts at 50m away from the traffic light, including three traffic routes;
[0050] The urban one-way street simulation test plan is that the initial speed of the tested vehicle is 30km / h. The test starts after entering the urban navigation system mode, which includes three consecutive stages: the first stage is pedestrians walking in the same direction of the motor vehicle lane, and the pedestrian speed is 5km / h; the second stage is encountering temporary traffic facilities such as traffic cones, and the distance between two adjacent traffic cones is 5m; the third stage is cyclists riding in the opposite direction on the motor vehicle lane, and the speed of the cyclists is 10km / h.
[0051] Furthermore, the three traffic routes in the crowded urban trunk road simulation test solution include: the vehicle under test turns right through an intersection with a traffic light, the vehicle under test goes straight through an intersection with a traffic light, and the vehicle under test turns left through an intersection with a traffic light.
[0052] The beneficial effects of the present invention are:
[0053] 1. Based on the vehicle-in-the-loop semi-simulation test, the present invention realizes the expected functional safety test of the urban navigation system in three typical urban scenarios: urban congested crossroads, urban crowded main roads and urban one-way streets. While achieving flexible control over the dynamic elements of the scene, real test feedback can be obtained; a multi-dimensional quantitative test result combining subjective and objective evaluation indicators is constructed, realizing a more comprehensive and in-depth evaluation of the expected functional safety of the urban navigation system.
[0054] 2. The expected safety evaluation model of the urban navigation system of the present invention integrates the test scenario weight factor based on the relative complexity of the scenario, quantifies the test results of the scenario test, and can realize horizontal comparison across scenarios, which helps to accurately identify and extract key boundary scenario information from low-scoring test results. BRIEF DESCRIPTION OF THE DRAWINGS
[0055] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0056] Figure 1 It is a flow chart of a method for constructing a safety test evaluation model for expected functions of a city navigation system in an embodiment of the present invention;
[0057] Figure 2 is a sub-step flow chart of step S3 in the embodiment of the invention;
[0058] Figure 3 is a sub-step flow chart of step S4 in an embodiment of the present invention;
[0059] Figure 4 1 is a schematic diagram of a scenario of a simulation test solution for a city congested cross traffic intersection according to an embodiment of the present invention;
[0060] Figure 5 Schematic diagram of a scenario of a simulation test solution for a crowded urban trunk road in an embodiment of the present invention;
[0061] Figure 6 It is a schematic diagram of a scenario of a city one-way street simulation test solution in an embodiment of the present invention. DETAILED DESCRIPTION
[0062] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. The accompanying drawings are only used for exemplary description and cannot be understood as limiting the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, not for limiting the scope of protection of the present invention.
[0063] like Figures 1 to 6 As shown, this embodiment provides a method for constructing a safety test evaluation model for an expected function of a city navigation system, comprising the following steps:
[0064] S1. Construct the expected functional safety simulation test scenarios of the urban navigation system, including the simulation test scenarios of urban congested intersections, the simulation test scenarios of crowded urban trunk roads and the simulation test scenarios of urban one-way streets;
[0065] S2. Develop a multi-stage urban congested intersection simulation test plan, a multi-stage urban trunk road simulation test plan, and a multi-stage urban one-way road simulation test plan, and conduct the expected functional safety test of the urban navigation system of the test vehicle, and obtain and save the expected functional safety test data;
[0066] S3. Constructing comprehensive evaluation indicators based on the expected functional safety test data, including objective evaluation indicators and subjective evaluation indicators;
[0067] Analyzing the relative complexity of the simulation test scenario, introducing a test scenario weight factor based on the relative complexity of the scenario, and determining the test scenario weight factor according to the expected functional safety test data;
[0068] S4. Establish an expected safety evaluation model for the urban navigation system based on the test scenario weight factors.
[0069] The present invention is based on the vehicle-in-the-loop semi-simulation test, and realizes the expected functional safety test of the urban navigation system in three typical urban scenarios: urban congested crossroads, urban crowded main roads and urban one-way streets. It can obtain real test feedback while achieving flexible control of the dynamic elements of the scene; it constructs a multi-dimensional quantitative test result that combines subjective and objective evaluation indicators, and realizes a more comprehensive and in-depth evaluation of the expected functional safety of the urban navigation system.
[0070] In addition, the expected safety evaluation model of the urban navigation system of the present invention integrates the test scenario weight factor based on the relative complexity of the scenario, quantifies the test results of the scenario test, and can realize horizontal comparison across scenarios, which helps to accurately identify and extract key boundary scenario information from low-scoring test results.
[0071] Preferably, in the expected functional safety simulation test scenario of the city navigation system:
[0072] (1) The simulation test scenario for the urban congested intersection is a two-way six-lane intersection, with three lanes in each direction: straight, left and right. There are several vehicles waiting to pass through the intersection in front of the vehicle under test, and the traffic flow of a single lane is 250-550 vehicles / hour; the traffic lights at the intersection control straight and left turns, with a red light cycle of 30s for the straight lane, a green light cycle of 45s, and a yellow light cycle of 3s; the red light cycle of the left turn lane is 45s, a green light cycle of 30s, and a yellow light cycle of 3s. The lighting conditions corresponding to the test scenario are shown in Table 1:
[0073] Table 1
[0074] Test scenario Lighting characteristics Whether there is street lighting Morning rush hour The light is clear and bright 400-800lux none Summer evening peak Soft, warm tone 50-300lux none Winter evening peak 50-100 lux There are street lights
[0075] (2) The simulation test scenario for a crowded urban main road is a two-way two-lane scenario with parking areas on both sides of the lanes. Vehicles in the parking areas are distributed with Gaussian probability. The test scenario includes dynamic scene elements such as oncoming vehicles, pedestrians crossing the road, and vehicles parked on the roadside in front, as well as static scene elements such as pedestrians stationary on the roadside.
[0076] (3) The urban one-way street simulation test scenario is a narrow one-way lane scenario, including a one-way street and a non-motorized vehicle lane, involving dynamic scene elements such as people riding and walking normally on the non-motorized vehicle lane, pedestrians walking in the same direction on the motor vehicle lane, and cyclists riding in the opposite direction, as well as static scene elements such as temporary traffic signs.
[0077] In this embodiment, the objective evaluation indicators in step S3 include:
[0078] (1) Safety distance control rate I1, calculated as: Where C1 is the sum of the safe distances between the tested vehicle and the front scene elements at each stage in the same simulation test scenario, and C2 is the sum of the minimum distances between the tested vehicle and the front scene elements at each stage in the same simulation test scenario;
[0079] (2) Driving path accuracy I2, calculated as: Where x is the longitudinal distance of the actual driving trajectory of the test vehicle, x∈[0,L], L is the maximum cumulative longitudinal distance of the vehicle in the city pilot driving mode; F(x) is the absolute value of the lateral distance deviation between the predetermined trajectory and the actual trajectory;
[0080] (3) Test pass rate I3, calculated as follows: I3 = [0, 1], where I3 = 0 means the vehicle under test did not pass the planned route, and I3 = 1 means the vehicle under test passed the planned route;
[0081] (4) Driving safety I4, calculated as follows: I4 = [0, 1, 2], where I4 = 0 means there is no violation of traffic rules or collision during the test; I4 = 1 means there is a violation of traffic rules or collision during the test; and I4 = 2 means there is a violation of traffic rules or collision during the test.
[0082] By constructing multiple objective evaluation indicators and quantifying the test results based on the test data of the test vehicle, the test results can be understood and analyzed more intuitively while ensuring the accuracy and comparability of the test results.
[0083] In this embodiment, the subjective evaluation index in step S3 includes:
[0084] The driving trust I5 is calculated as follows: I5=[0,1,2], where I5=0 means that 30% or less of the driving behavior of the city navigation system is consistent with user expectations; I5=1 means that 30%-80% of the driving behavior of the city navigation system is consistent with user expectations; I5=2 means that 80% or more of the driving behavior of the city navigation system is consistent with user expectations.
[0085] By introducing subjective evaluation indicators, it can directly reflect users' needs and expectations for vehicle performance and driving experience in the city navigation driving mode of the test vehicle, supplement the test results that cannot be expressed by objective evaluation indicators, and comprehensively evaluate the expected functional safety performance of the city navigation system.
[0086] like Figure 2 As shown, in this embodiment, step S3 includes the following sub-steps:
[0087] S31, defining basic scene information features of the simulation test scene, including road structure degree s1, number of lanes s2, number of road facilities s3 and ground visibility s4, to form a basic scene information feature set S0 = {s1, s2, s3, s4};
[0088] Get the scene information feature set S of the i-th simulation test scene i ={s i1 ,s i2 ,s i3 ,s i4};
[0089] S32, based on the basic scene information feature set S0 and the scene information feature set S of the i-th simulation test scene iCalculate the test scenario weight factor λ for the i-th simulation test scenario i , the calculation formula is: λ i ∈[0,1], where d ik is the kth information feature difference of the i-th test scene;
[0090] In the formula, R k is the maximum value of the k-th scene information feature, s ik is the value of the kth scene information feature of the ith simulation test scene, s k is the value of the basic scene information feature, ∈[1,n], n is the number of simulation test scenes, k∈[1,4].
[0091] Quantifying the scenario information in the simulation test scenario can uniformly quantify a variety of complex information into comparable values, which is conducive to objectively evaluating the quality and effect of the expected functional safety test of the urban navigation system and facilitating the comparison of test results of different scenarios.
[0092] Preferably, the basic scene information features of the simulation test scene are: road structure degree s1 = 0, number of lanes s2 = 1, number of road facilities s3 = 0, and ground visibility s4 = 2km. The basic test scene information feature set is S0 = {0, 1, 0, 2,}; Get the information feature set S of the i-th test scene i When the road structure degree s i1 ∈[0,1]; when the number of lanes is less than 8, s i2 is the actual number of lanes, ranging from [1,8). If the number of lanes is greater than or equal to 8, then s i2 =8; when the number of road facilities is less than 5, s i3 is the number of road facilities, ranging from [1,5). If the number of road facilities is greater than or equal to 5, then s i3 =5, the number of road facilities here refers to the number of road facilities that affect driving tasks; when the ground visibility is less than 2km, s i4 The value is the ground visibility value. If the ground visibility is greater than or equal to 2km, then s i4 =2.
[0093] like Figure 3 As shown, in this embodiment, step S4 includes the following sub-steps:
[0094] S41, establish the test result matrix X of a single simulation test scenario i = [I1, I2, I3, I4, I5], and based on the test result matrix X of a single simulation test scenario i Create a test result scoring matrix In the formula, Xi is the test result under the i-th simulation test scenario, i∈[1,n], n is the number of simulation test scenarios, I ij is the jth comprehensive evaluation index I of the test results in the i-th simulation test scenario j , j∈[1,5];
[0095] S42, the jth comprehensive evaluation index I of the test results in the i-th simulation test scenario j Conduct standardized operations;
[0096] S43, the jth comprehensive evaluation index I based on the standardized test results in the i-th simulation test scenario j , combined with information entropy, determine the indicator weights of each comprehensive evaluation indicator;
[0097] S44. Combine the scenario factor weights and indicator weights to establish evaluation models for single simulation test scenarios and multiple simulation test scenarios for the expected functional safety of the urban navigation system.
[0098] In this embodiment, the comprehensive evaluation indicators are divided into positive indicators and negative indicators. The positive indicators include the safety distance control rate I1, the test pass rate I3 and the driving confidence I5, and the negative indicators include the driving path accuracy I2 and the driving safety. In step S42, the jth comprehensive evaluation indicator I of the test result under the i-th simulation test scenario is calculated. j The standardization operation includes positive indicator standardization and negative indicator standardization;
[0099] The standardized formula for the positive indicator is:
[0100] The standardized formula for the negative indicator is:
[0101] In the formula, x ij1 and x ij2 is the jth indicator I of the test results in the i-th simulation test scenario j The normalized value, n is the number of simulation test scenarios.
[0102] The standardization operation eliminates the dimensional differences between the comprehensive indicators, enables direct comparison and calculation between different indicators, and improves the comparability and calculability of test data.
[0103] In this embodiment, the indicator weight ω of each comprehensive evaluation indicator in step S43 is j The calculation formula is: Where D j is the amount of information;
[0104] In the formula, s jis the standard deviation of the comprehensive evaluation index described in item j, r mj is the correlation coefficient between the comprehensive evaluation index described in item m and the comprehensive evaluation index described in item j;
[0105] In the formula, x im and x ij are the mth index I of the test results under the i-th simulation test scenario. m and the jth index I j The standardized value, and are the mth index I of the test results in all simulation test scenarios m and the jth index I j The standardized average value, m∈[1,5], j∈[1,5], and n is the number of simulation test scenarios.
[0106] The indicator weight of each comprehensive evaluation indicator is determined by combining the amount of information and the correlation coefficient of the two comprehensive evaluation indicators, so that the indicator weight calculation of each comprehensive evaluation indicator is more objective, fair and reliable.
[0107] In this embodiment, in step S44:
[0108] The calculation formula for the expected functional safety test results of the urban navigation system in a single simulation test scenario is: In the formula, c i is the test result value of the ith simulation test scenario, λ i is the scenario factor weight of the i-th simulation test scenario, I j ×ω j is the product of the jth indicator and the corresponding weight, i∈[1,n], j∈[1,5], n is the number of simulation test scenarios;
[0109] The calculation formula for the expected functional safety test results of the urban navigation system in multiple simulation test scenarios is: Where C is the expected functional safety test result value of the urban navigation system in multiple simulation test scenarios, i∈[1,n], and n is the number of simulation test scenarios.
[0110] The evaluation model for a single test scenario can more accurately reflect the expected functional safety performance of the city navigation system under the test scenario and is highly targeted; the multi-test scenario evaluation model covers a variety of different test scenarios and can more comprehensively evaluate the expected functional safety performance of the city navigation system under different scenarios.
[0111] In this embodiment, Figure 4As shown, the simulation test scheme for urban congested crossroads is that the initial speed of the tested vehicle is 40km / h. The test starts after entering the city navigation system mode, which includes four consecutive stages: the first stage is the standing still pedestrians in the parking area on the same side of the tested vehicle; the second stage is the driving route of the oncoming car deviates from the central yellow line at a speed of 30km / h; the third stage is the pedestrians crossing from the parking area on the same side of the tested vehicle to the opposite side, and the pedestrian speed is 5km / h; the fourth stage is the vehicle that is parked in the parking area on the same side of the tested vehicle;
[0112] like Figure 5 As shown in Figure 3, the simulation test scheme for congested urban main roads is that the initial speed of the tested vehicle is 30 km / h, it is located in the middle lane, and after entering the city navigation system mode, the test starts at 50 m away from the traffic light, including the three traffic routes shown in Table 3 and the initial states of the traffic lights assigned to each route:
[0113] Table 2
[0114]
[0115] like Figure 6 As shown in the figure, the urban one-way simulation test plan is that the initial speed of the vehicle under test is 30km / h. The test starts after entering the urban navigation system mode, which includes three consecutive stages: the first stage is pedestrians walking in the same direction of the motor vehicle lane, and the pedestrian speed is 5km / h; the second stage is encountering temporary traffic facilities such as traffic cones, and the distance between two adjacent traffic cones is 5m; the third stage is cyclists going in the opposite direction on the motor vehicle lane, and the speed of the cyclists is 10km / h.
[0116] In this embodiment, the three traffic routes in the crowded urban main road simulation test solution include: the tested vehicle turns right through an intersection with a traffic light, the tested vehicle goes straight through an intersection with a traffic light, and the tested vehicle turns left through an intersection with a traffic light.
[0117] Obviously, the above embodiments of the present invention are only examples for clearly illustrating the present invention, and are not intended to limit the implementation methods of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the claims of the present invention.
Claims
1. A method for constructing a safety test evaluation model for the expected function of a city navigation system, characterized in that: The following steps are involved: S1. Construct the expected functional safety simulation test scenarios of the urban navigation system, including the simulation test scenarios of urban congested intersections, the simulation test scenarios of crowded urban trunk roads and the simulation test scenarios of urban one-way streets; S2. Develop a multi-stage urban congested intersection simulation test plan, a multi-stage urban trunk road simulation test plan, and a multi-stage urban one-way road simulation test plan, and conduct the expected functional safety test of the urban navigation system of the test vehicle, and obtain and save the expected functional safety test data; S3. Constructing comprehensive evaluation indicators based on the expected functional safety test data, including objective evaluation indicators and subjective evaluation indicators; Analyzing the relative complexity of the simulation test scenario, introducing a test scenario weight factor based on the relative complexity of the scenario, and determining the test scenario weight factor according to the expected functional safety test data; S4. Establish an expected safety evaluation model for the urban navigation system based on the test scenario weight factors.
2. According to claim 1, a method for constructing a safety test evaluation model for the expected function of a city navigation system is characterized in that: The objective evaluation indicators in step S3 include: (1) Safety distance control rate I1, calculated as: Where C1 is the sum of the safe distances between the tested vehicle and the front scene elements at each stage in the same simulation test scenario, and C2 is the sum of the minimum distances between the tested vehicle and the front scene elements at each stage in the same simulation test scenario; (2) Driving path accuracy I2, calculated as: Where x is the longitudinal distance of the actual driving trajectory of the test vehicle, x∈[0,L], L is the maximum cumulative longitudinal distance of the vehicle in the city pilot driving mode; F(x) is the absolute value of the lateral distance deviation between the predetermined trajectory and the actual trajectory; (3) Test pass rate I3, calculated as follows: I3 = [0, 1], where I3 = 0 means the vehicle under test did not pass the planned route, and I3 = 1 means the vehicle under test passed the planned route; (4) Driving safety I4, calculated as follows: I4 = [0, 1, 2], where I4 = 0 means there is no violation of traffic rules or collision during the test; I4 = 1 means there is a violation of traffic rules or collision during the test; and I4 = 2 means there is a violation of traffic rules or collision during the test.
3. The method for constructing a safety test evaluation model for the expected function of a city navigation system according to claim 2, characterized in that: The subjective evaluation index in step S3 includes: The driving trust level I5 is calculated as follows: I5=[0, 1, 2], where I5=0 means that 30% or less of the driving behavior of the city navigation system is consistent with user expectations; I5=1 means that 30%-80% of the driving behavior of the city navigation system is consistent with user expectations; I5=2 means that 80% or more of the driving behavior of the city navigation system is consistent with user expectations.
4. The method for constructing a safety test evaluation model for the expected function of a city navigation system according to claim 3 is characterized in that: The S3 step includes the following sub-steps: S31, defining basic scene information features of the simulation test scene, including road structure degree s1, number of lanes s2, number of road facilities s3 and ground visibility s4, to form a basic scene information feature set S0 = {s1, s2, s3, s4}; Get the scene information feature set S of the i-th simulation test scene i ={s i1 s i2 ,s i3 ,s i4 }; S32, based on the basic scene information feature set S0 and the scene information feature set S of the i-th simulation test scene i Calculate the test scenario weight factor λ for the i-th simulation test scenario i , the calculation formula is: λ i ∈[0,1], where d ik is the kth information feature difference of the i-th test scene; In the formula, R k is the maximum value of the k-th scene information feature, s ik is the value of the kth scene information feature of the ith simulation test scene, s k is the value of the basic scene information feature, ∈[1,n], n is the number of simulation test scenes, k∈[1,4].
5. The method for constructing a safety test evaluation model for the expected function of a city navigation system according to claim 4, characterized in that: The S4 step includes the following sub-steps: S41, establish the test result matrix X of a single simulation test scenario i = [I1, I2, I3, I4, I5], and based on the test result matrix X of a single simulation test scenario i Create a test result scoring matrix Where, X i is the test result under the i-th simulation test scenario, i∈[1,n], n is the number of simulation test scenarios, I ij is the jth comprehensive evaluation index I of the test results in the i-th simulation test scenario i , j∈[1,5]; S42, the jth comprehensive evaluation index I of the test result in the i-th simulation test scenario j Conduct standardized operations; S43, the jth comprehensive evaluation index I based on the standardized test results in the i-th simulation test scenario j , determine the indicator weights of each comprehensive evaluation indicator in combination with information entropy; S44. Based on the scenario factor weights and the indicator weights, an evaluation model of a single simulation test scenario and a multi-simulation test scenario for the expected functional safety of the city navigation system is established.
6. The method for constructing a safety test evaluation model for the expected function of a city navigation system according to claim 5, characterized in that: The comprehensive evaluation index is divided into positive index and negative index. The positive index includes safety distance control rate I1, test pass rate I3 and driving confidence I5. The negative index includes driving path accuracy I2 and driving safety I4. The jth comprehensive evaluation index I of the test result under the i-th simulation test scenario in step S42 is j The standardization operation includes positive indicator standardization and negative indicator standardization; The standardized formula of the positive indicator is: The standardized formula of the negative indicator is: In the formula, x ij1 and x ij2 is the jth indicator I of the test results in the i-th simulation test scenario j The normalized value, n is the number of simulation test scenarios.
7. The method for constructing a safety test evaluation model for the expected function of a city navigation system according to claim 6, characterized in that: The indicator weight ω of each comprehensive evaluation indicator in the step S43 j The calculation formula is: Where D j is the amount of information; In the formula, s j is the standard deviation of the comprehensive evaluation index described in item j, r mj is the correlation coefficient between the comprehensive evaluation index described in item m and the comprehensive evaluation index described in item j; In the formula, x im and x ij are the mth index I of the test results under the i-th simulation test scenario. m and the jth index I j The standardized value, and are the mth index I of the test results in all simulation test scenarios m and the jth index I j The standardized average value, m∈[1,5], j∈[1,5], and n is the number of simulation test scenarios.
8. The method for constructing a safety test and evaluation model for the expected function of a city navigation system according to claim 5, characterized in that: In the step S44: The calculation formula for the expected functional safety test results of the urban navigation system in a single simulation test scenario is: In the formula, c i is the test result value of the ith simulation test scenario, λ i is the scenario factor weight of the i-th simulation test scenario, I j ×ω j is the product of the jth indicator and the corresponding weight, i∈[1,n], j∈[1,5], n is the number of simulation test scenarios; The calculation formula for the expected functional safety test results of the urban navigation system in multiple simulation test scenarios is: Where C is the expected functional safety test result value of the urban navigation system in multiple simulation test scenarios, i∈[1,n], and n is the number of simulation test scenarios.
9. The method for constructing a safety test evaluation model for the expected function of a city navigation system according to claim 1, characterized in that: The simulation test scheme for the urban congested crossroad is that the initial speed of the tested vehicle is 40km / h, and the test starts after entering the city navigation system mode, which includes four consecutive stages: the first stage is the standing still pedestrians in the parking area on the same side of the tested vehicle; the second stage is the driving route of the oncoming car deviates from the central yellow line, and the speed is 30km / h; the third stage is the pedestrians crossing from the parking area on the same side of the tested vehicle to the opposite side, and the pedestrian speed is 5km / h; the fourth stage is the vehicle that is parked in the parking area on the same side of the tested vehicle; The congested urban main road simulation test scheme is that the initial speed of the tested vehicle is 30km / h, located in the middle lane, and after entering the city navigation system mode, the test starts at 50m away from the traffic light, including three traffic routes; The urban one-way street simulation test plan is that the initial speed of the tested vehicle is 30km / h. The test starts after entering the urban navigation system mode, which includes three consecutive stages: the first stage is pedestrians walking in the same direction of the motor vehicle lane, and the pedestrian speed is 5km / h; the second stage is encountering temporary traffic facilities such as traffic cones, and the distance between two adjacent traffic cones is 5m; the third stage is cyclists riding in the opposite direction on the motor vehicle lane, and the speed of the cyclists is 10km / h.
10. The method for constructing a safety test evaluation model for the expected function of a city navigation system according to claim 9, characterized in that: The three traffic routes in the crowded urban main road simulation test solution include: the tested vehicle turns right through an intersection with a traffic light, the tested vehicle goes straight through an intersection with a traffic light, and the tested vehicle turns left through an intersection with a traffic light.