An assisted parking test method, device, equipment and readable storage medium

Abstract

This application relates to the field of autonomous driving technology and discloses a method, apparatus, device, and readable storage medium for testing assisted parking. The method includes: identifying hazardous events in an autonomous parking assistance system; analyzing safety-critical scenarios to obtain a detailed scenario library including risk factors; simulating the detailed scenarios in the scenario library in a bench testing environment; adjusting the parameter values ​​of the risk factors in the detailed scenarios, performing automated testing, and obtaining test information on hazardous events. This application can identify known and unknown risks during testing in the early stages of expected functional safety development, providing a prerequisite for further improving APA performance.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to an assisted parking testing method, apparatus, device, and readable storage medium. Background Technology

[0002] Autonomous driving assistance technology is an active safety technology that can effectively prevent and reduce the severity of harmful events. However, when autonomous driving assistance malfunctions, the excessive reliance of most drivers on the system's reliability can significantly prolong the effective takeover time, leading to more serious traffic accidents. Furthermore, these systems, which rely on perceiving the vehicle's external or internal environment to establish situational awareness, may still lead to harmful behavior if their intended functional performance is insufficient or if misused by personnel, even if the malfunctions mentioned in GB / T34590 do not occur.

[0003] Currently, most mid-to-high-end cars worldwide are equipped with Auto Parking Assist (APA) systems, which enable cars to park or exit parking spaces correctly. However, APA systems may experience delays in recognizing obstacles, potentially leading to collisions.

[0004] How to ensure that known and unknown risks are identified during the development and testing of APAs, thereby improving the performance of APAs, is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0005] The purpose of this application is to provide a parking assistance testing method, device, equipment, and readable storage medium that can effectively test the test information corresponding to hazardous events of the autonomous parking assistance system during the testing process based on risk factors.

[0006] To solve the above-mentioned technical problems, this application provides the following technical solution:

[0007] An assisted parking test method includes:

[0008] Identify hazardous events related to autonomous parking assistance systems;

[0009] Analyze safety-critical scenarios to obtain a detailed scenario library including risk factors;

[0010] Simulate the refined scenarios in the refined scenario library in a bench testing environment;

[0011] Adjust the parameter values ​​of the risk factors in the refined scenario, perform automated testing, and obtain test information of the hazard event.

[0012] Optionally, adjusting the parameter values ​​of the risk factors in the refined scenario and performing automated testing to obtain test information of the hazardous event includes:

[0013] Randomly adjust the parameter values ​​of the risk factors in the refined scenario, perform automated testing, obtain the probability of occurrence of the hazardous event, the hazardous scenario in which the hazardous event occurs, and record the risk factor parameters in which the hazardous scenario occurs;

[0014] The occurrence probability, the hazardous scenario, and the risk factor parameters are determined as the test information for the hazardous event.

[0015] Optionally, the step of randomly adjusting the parameter values ​​of the risk factors in the refined scenario and performing automated testing to obtain the probability of occurrence of the hazardous event includes:

[0016] Randomly adjust the parameter values ​​of the risk factors in the refined scenario;

[0017] Obtain the probability calculation input parameters; wherein, the input parameters include the number of the current test case, the total number of test cases, the number of the current risk factor, the total number of risk factors in the refined scenario, the probability of the current risk factor, and the true or false value of whether the refined scenario produces the harmful event.

[0018] The probability of the hazardous event occurring is obtained by substituting the parameters into the probability calculation model.

[0019] Optionally, it also includes:

[0020] Analyze the hazardous events to determine the triggering conditions;

[0021] Define the acceptance criteria corresponding to the triggering conditions;

[0022] If the probability of occurrence is higher than the acceptance criterion, then modify the assisted parking strategy;

[0023] If the probability of occurrence is not higher than the acceptance criterion, then the assisted parking strategy is determined to have been optimized.

[0024] Optionally, after modifying the assisted parking strategy, the following steps are also included:

[0025] Perform the step of simulating the refined scenarios in the refined scenario library in the bench verification environment until the probability of occurrence is not higher than the acceptance criterion, or the number of iterations reaches a threshold.

[0026] Optionally, the analysis of safety-critical scenarios yields a detailed scenario library including risk factors, comprising:

[0027] The risk factors are obtained by analyzing key perception scenarios, key road traffic scenarios, and key vehicle control scenarios.

[0028] The risk factors are structured to obtain the refined scenario library.

[0029] Optionally, the risk factors are obtained by analyzing key road traffic scenarios, including:

[0030] The performance limitations of the sensing sensors, the influence of the surrounding environment, the sensing targets, and the sensing blind spots in the key sensing scenarios are analyzed to obtain the sensing risk factors;

[0031] The perceived risk factors include at least one of the following: detection distance, detection accuracy, potholes, muddy roads, rain, glare, lane lines, curbs, traffic lights, speed limit signs, traffic cones, medians, pedestrians, vehicles, walls, uphill, downhill, and curves.

[0032] Optionally, the risk factors are obtained by analyzing key road traffic scenarios, including:

[0033] Traffic risk factors are obtained by analyzing the vehicle's operation, relative position with other traffic participants, types of other traffic participants, and operations of other traffic participants in the key road traffic scenarios.

[0034] The traffic risk factors include at least one of the following: overtaking, changing lanes, merging, reversing, stopping, directly in front, to the side in front, directly behind, to the side in front, adults, children, passenger cars, commercial vehicles, special vehicles, motorcycles, and crossing.

[0035] Optionally, the risk factors are obtained by analyzing key vehicle control scenarios, including:

[0036] The wheel and body forces in the key vehicle control scenarios are analyzed to obtain control risk factors;

[0037] The risk control factors include at least one of the following: icy and snowy road surface, wet and slippery road surface, dry road surface, tire aging, tire blowout, crosswind, tailwind, headwind, cross slope, longitudinal slope, and road curvature radius.

[0038] An auxiliary parking test device, comprising:

[0039] Hazard event determination unit, used to determine hazard events of the autonomous parking assistance system;

[0040] The scenario refinement unit is used to analyze safety-critical scenarios and obtain a refined scenario library including risk factors.

[0041] The scene simulation unit is used to simulate the refined scenes in the refined scene library in a bench verification environment;

[0042] The hazard testing unit is used to adjust the parameter values ​​of the risk factors in the refined scenario, perform automated testing, and obtain test information of the hazard event.

[0043] An electronic device, comprising:

[0044] Memory, used to store computer programs;

[0045] A processor is used to implement the steps of the above-described assisted parking test method when executing the computer program.

[0046] A readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described assisted parking test method.

[0047] The method provided in the embodiments of this application is used to determine the hazardous events of the autonomous parking assistance system; analyze the safety-critical scenarios to obtain a detailed scenario library including risk factors; simulate the detailed scenarios in the detailed scenario library in a bench verification environment; adjust the parameter values ​​of the risk factors in the detailed scenarios, perform automated testing, and obtain test information of the hazardous events.

[0048] This application first identifies hazardous events in an autonomous parking assist system (APA), then analyzes safety-critical scenarios to obtain a detailed scenario library including risk factors. Subsequently, the detailed scenarios in this library can be simulated in a bench testing environment, and automated testing can be performed by adjusting the parameter values ​​of the risk factors within these scenarios, ultimately yielding test information on hazardous events. In other words, this application can identify known and unknown risks during testing in the early stages of expected functional safety development, providing a prerequisite for further improvements in APA performance.

[0049] Accordingly, embodiments of this application also provide an auxiliary parking test device, equipment, and readable storage medium corresponding to the above-described auxiliary parking test method, which have the aforementioned technical effects, and will not be elaborated further here. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1This is a flowchart illustrating the implementation of an assisted parking test method in this application.

[0052] Figure 2 This is a schematic diagram of an assisted parking test architecture in an embodiment of this application;

[0053] Figure 3 This is a schematic diagram illustrating a key perception scenario analysis in an embodiment of this application;

[0054] Figure 4 This is a schematic diagram illustrating a key road traffic scenario analysis in an embodiment of this application;

[0055] Figure 5 This is a schematic diagram illustrating a key vehicle control scenario in an embodiment of this application.

[0056] Figure 6 This is a schematic diagram illustrating a specific implementation of an assisted parking testing method in this application.

[0057] Figure 7 This is a schematic diagram illustrating a late emergency braking trigger condition for a vehicle as described in an embodiment of this application.

[0058] Figure 8 This is a schematic diagram of the structure of an auxiliary parking test device according to an embodiment of this application;

[0059] Figure 9 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application;

[0060] Figure 10 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0061] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are merely some embodiments of the present application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0062] Please refer to Figure 1 , Figure 1 This is a flowchart of an assisted parking test method according to an embodiment of this application. This method can be applied to, for example... Figure 2 In the architecture shown, the method includes the following steps:

[0063] S101. Identify hazardous events related to the autonomous parking assistance system.

[0064] In this embodiment, hazardous events in the autonomous parking assistance system can first be identified. Specifically, hazard analysis involves obtaining the operational design domain, driver state, vehicle state, and initial system architecture based on the APA functional specifications. The initial architecture should clearly describe the interactions between architectural elements. The APA system consists of perception elements: ultrasonic radar and surround-view cameras; perception fusion motion planning elements: domain controllers; and lateral and longitudinal actuators.

[0065] Combining the main functions of APA, the HAZOP (Hazard and Operability Study) analysis method is used to identify hazardous events related to the intended functional safety.

[0066] S102. Analyze safety-critical scenarios to obtain a detailed scenario library including risk factors.

[0067] Safety-critical scenarios include one or more risk factors, the presence of which increases the probability of injury or the severity of injury.

[0068] The detailed scenario library stores detailed scenarios, which are essentially refined versions of existing scenarios. Generally, detailed scenarios are created by overlaying basic scenarios with safety-critical scenarios. Basic scenarios are typically common scenarios derived from accident scene data, company development experience, and expert knowledge analysis. For the basic scenarios of an automated parking assist system (APA), these could include enabling vehicles to autonomously park in / out of parking spaces and searching for parking spaces.

[0069] By analyzing safety-critical scenarios, we can obtain detailed scenarios with risk factors. These detailed scenarios are then added to a detailed scenario library for subsequent testing and simulation.

[0070] In one specific embodiment of this application, safety-critical scenarios are analyzed to obtain a detailed scenario library including risk factors, comprising:

[0071] Step 1: Analyze key perception scenarios, key road traffic scenarios, and key vehicle control scenarios to obtain risk factors;

[0072] Step 2: Structure the risk factors to obtain a detailed scenario library.

[0073] For ease of description, the two steps above will be explained together below.

[0074] In this embodiment, based on the performance deficiencies of the architectural elements, the safety-critical scenarios can be divided into: perception-critical scenarios, road traffic-critical scenarios, and vehicle control-critical scenarios.

[0075] Among them, perception-critical scenarios refer to scenarios where one or more risk factors prevent the ADS vehicle from correctly perceiving its environment. Specifically, perception-critical scenarios can be analyzed through the following categories: perception sensor performance limitations, the influence of the surrounding environment, the target being perceived, and blind spots.

[0076] Please refer to Figure 3 , Figure 3 This is a schematic diagram illustrating a key scenario analysis in an embodiment of this application. Specifically, it analyzes key road traffic scenarios to obtain risk factors, including:

[0077] The performance limitations of sensing sensors, the influence of the surrounding environment, sensing targets, and sensing blind spots in key sensing scenarios are analyzed to obtain sensing risk factors;

[0078] Among them, the perceived risk factors include at least one of the following: detection distance, detection accuracy, potholes, muddy roads, rain, glare, lane lines, curbs, traffic lights, speed limit signs, traffic cones, medians, pedestrians, vehicles, walls, uphill, downhill, and curves.

[0079] That is, when analyzing key perception scenarios, the limitations of sensor performance can be analyzed to obtain perception risk factors: detection distance and detection accuracy; the impact of the surrounding environment can be analyzed, specifically including road conditions and environmental factors.

[0080] Based on the analysis of road conditions, the perceived risk factors can be identified as: potholes and muddy roads.

[0081] Based on the analysis of environmental factors, the perceived risk factors can be identified as: rainy weather and glare.

[0082] Risk assessment for perceived targets can be conducted from road surface information and traffic signs, respectively.

[0083] The analysis of temporary road restrictions and moving entities yielded the perceived risk factors: lane lines, curbs, traffic lights, speed limit signs, traffic cones, medians, pedestrians, and vehicles.

[0084] Blind spot analysis can specifically involve assessing the risks associated with road conditions and characteristics to identify perceived risk factors: medians, walls, uphill slopes, downhill slopes, and curves.

[0085] After obtaining perceived risk factors through analysis from different perspectives, duplicate risk factors can be deduplicated.

[0086] Key road traffic scenarios refer to scenarios where one or more risk factors prevent the ADS vehicle from making correct judgments. Key road traffic scenarios combine different types of vehicle actions, types of other traffic participants, relative positions to other traffic participants, and actions of other traffic participants.

[0087] Please refer to Figure 4 , Figure 4 This is a schematic diagram illustrating a key road traffic scenario analysis in an embodiment of this application. Specifically, it analyzes key road traffic scenarios to obtain risk factors, including:

[0088] Traffic risk factors are obtained by analyzing the operation of the vehicle, its relative position with other traffic participants, the types of other traffic participants, and the operations of other traffic participants in key road traffic scenarios.

[0089] Traffic risk factors include at least one of the following: overtaking, changing lanes, merging, reversing, parking, directly in front, to the side front, directly behind, to the side rear, adults, children, passenger cars, commercial vehicles, special vehicles, motorcycles, and crossing.

[0090] That is, the analysis of key road traffic scenarios can be specifically based on the vehicle's operation, its relative position to other traffic participants, the types of other traffic participants, and the operations of other traffic participants.

[0091] Among them, assessing the risks of autonomous vehicle operation yields traffic risk factors: overtaking, lane changing, merging, reversing, and parking.

[0092] By assessing the relative position to other traffic participants, traffic risk factors can be obtained: directly in front, to the side front, directly behind, and to the side rear.

[0093] To analyze other types of traffic participants, we can first analyze pedestrians and then vehicles to obtain traffic risk factors: adults, children, passenger cars, commercial vehicles, special vehicles, and motorcycles.

[0094] Analyzing the actions of other traffic participants reveals traffic risk factors: crossing, merging, and overtaking.

[0095] After analyzing traffic risk factors from different perspectives, duplicate risk factors can be deduplicated.

[0096] Key vehicle control scenarios refer to one or more risk factors that cause the ADS vehicle to fail to accurately control its movement. Key vehicle control scenarios mainly analyze the forces acting on the wheels (e.g., ground friction coefficient) and the forces acting on the vehicle body (e.g., slope, wind resistance).

[0097] Please refer to Figure 5 , Figure 5 This is a schematic diagram illustrating a key vehicle control scenario analysis in an embodiment of this application. Specifically, the key vehicle control scenario is analyzed to obtain risk factors, including:

[0098] The wheel and body forces in key vehicle control scenarios are analyzed to obtain control risk factors;

[0099] Among them, the risk factors to be controlled include at least one of the following: icy and snowy road surface, wet and slippery road surface, dry road surface, tire aging, tire blowout, crosswind, tailwind, headwind, cross slope, longitudinal slope, and road curvature radius.

[0100] The analysis of key vehicle control scenarios can be specifically divided into the analysis of vehicle forces and the analysis of vehicle forces.

[0101] Among them, the analysis of wheel stress is to analyze the scenarios that affect wheel stress. Specifically, the analysis can be carried out on road conditions to obtain control risk factors, including: icy and snowy road surface, wet and slippery road surface, and dry road surface.

[0102] Analysis of tire conditions revealed that the control risk factors include: tire aging and tire blowout.

[0103] The analysis of vehicle body stress involves analyzing the scenarios that affect the vehicle body stress, such as environmental factors and the shape and topology of road sets.

[0104] Analysis of environmental factors revealed that the control risk factors include: crosswind, tailwind, and headwind;

[0105] Analysis of road geometry and topology reveals risk control factors including cross slope, longitudinal slope, and road curvature radius.

[0106] After obtaining various risk factors, a detailed scenario library is derived through the structured analysis described above. This detailed scenario library can then be mapped onto a 6-layer scenario framework. Of course, in practical applications, it can also be mapped onto other scenario frameworks, which will not be elaborated upon here. The 6-layer scenario framework is as follows:

[0107] L1 layer: Road geometry and topology, mainly including information such as location, slope, and road shape;

[0108] Level 2: Road facilities and restrictions, mainly including information on road medians, fences, etc.

[0109] L3 layer: Temporary physical constraints, mainly including: road surface conditions, temporary roadwork obstacles, etc.;

[0110] L4 layer: Movable entities, mainly including: vehicle information, information on potential traffic accident participants, etc.

[0111] Level 5: Environmental conditions, mainly including: weather, lighting, and other information;

[0112] Layer L6: Digital information, mainly including V2X, high-precision maps, and other information.

[0113] S103. Simulate the refined scenarios in the refined scenario library in the bench verification environment.

[0114] The bench validation environment includes: a simulation environment simulator, the APA system under test, a virtual actuator, and a monitor.

[0115] The simulation environment simulator is used to simulate detailed scenarios. The APA system under test perceives the environment and issues execution commands through the information from the simulation simulator.

[0116] The virtual actuator includes a lateral actuator and a longitudinal controller that execute control commands and feed them back to the APA system. The monitor is used to debug the test bench and observe its operating status.

[0117] S104. Adjust the parameter values ​​of risk factors in the detailed scenario, perform automated testing, and obtain test information on hazard events.

[0118] During the testing process, the parameter values ​​of risk factors are adjusted according to a preset fixed order and corresponding step size, or the parameter values ​​of risk factors can be adjusted randomly to perform automated testing and obtain test information.

[0119] In one optional embodiment of this application, the parameter values ​​of risk factors in a refined scenario are randomly adjusted to perform automated testing and obtain test information on hazardous events, including:

[0120] Step 1: Randomly adjust the parameter values ​​of risk factors in the refined scenario, conduct automated testing, obtain the probability of occurrence of the hazardous event, the hazardous scenario in which the hazardous event occurs, and record the risk factor parameters of the hazardous scenario.

[0121] Step 2: Determine the probability of occurrence, hazardous scenarios, and risk factor parameters as test information for hazardous events.

[0122] In other words, the test information specifically includes the probability of a hazardous event occurring, the hazardous scenarios in which such events occur, and the risk factor parameters of the hazardous scenarios.

[0123] Specifically, the parameter values ​​of risk factors in the refined scenario are randomly adjusted, and automated testing is performed to obtain the probability of occurrence of hazardous events, including:

[0124] Step 1: Randomly adjust the parameter values ​​of risk factors in the refined scenario;

[0125] Step 2: Obtain the input parameters for probability calculation; the input parameters include the current test case number, the total number of test cases, the current risk factor number, the total number of risk factors in the refined scenario, the probability of the current risk factor, and the true or false value of whether the refined scenario produces a harmful event.

[0126] Step 3: Substitute the input parameters into the probability calculation model for the occurrence of a hazardous event to obtain the probability of the hazardous event occurring.

[0127] For example, the probability of a hazardous event occurring can be calculated using the following probability calculation model:

[0128] ;

[0129] Where P: the probability of a hazardous scenario occurring;

[0130] I: Test case number;

[0131] N: The total number of test cases;

[0132] j: Risk factor number;

[0133] M: This scenario has M risk factors;

[0134] P ji : The probability of the current risk factor j;

[0135] S i Does this scenario result in a harmful event? (S) i =1 indicates that a hazardous event has occurred, S i =0 means that no harmful event occurred.

[0136] The method provided in the embodiments of this application is used to determine the hazardous events of the autonomous parking assistance system; analyze the safety-critical scenarios to obtain a detailed scenario library including risk factors; simulate the detailed scenarios in the detailed scenario library in a bench verification environment; adjust the parameter values ​​of the risk factors in the detailed scenarios, perform automated testing, and obtain test information of the hazardous events.

[0137] This application first identifies hazardous events in an autonomous parking assist system (APA), then analyzes safety-critical scenarios to obtain a detailed scenario library including risk factors. Subsequently, the detailed scenarios in this library can be simulated in a bench testing environment, and automated testing can be performed by adjusting the parameter values ​​of the risk factors within these scenarios, ultimately yielding test information on hazardous events. In other words, this application can identify known and unknown risks during testing in the early stages of expected functional safety development, providing a prerequisite for further improvements in APA performance.

[0138] It should be noted that, based on the above embodiments, the embodiments of this application also provide corresponding improvement schemes. In the preferred / improved embodiments, the same or corresponding steps as in the above embodiments can be referred to each other, and the corresponding beneficial effects can also be referred to each other; however, these will not be elaborated upon in the preferred / improved embodiments herein.

[0139] Please refer to Figure 6, Figure 6 This is a schematic diagram illustrating a specific implementation of an assisted parking testing method according to an embodiment of this application. In this application, the assisted parking strategy can also be modified based on the probability of occurrence of hazardous events. The specific implementation process includes:

[0140] Step 1: Analyze the hazardous event and determine the triggering conditions;

[0141] Step 2: Define the acceptance criteria corresponding to the triggering conditions;

[0142] Step 3: If the probability of occurrence is higher than the acceptance criterion, then modify the assisted parking strategy;

[0143] Step 4: If the probability of occurrence is not higher than the acceptance criterion, then the assisted parking strategy has been optimized.

[0144] For ease of description, the above four steps will be explained in combination below.

[0145] Hazard analysis, based on the APA functional specifications, involves obtaining the operational design domain, driver status, vehicle status, and initial system architecture. The initial architecture should clearly describe the interactions between architectural elements. The APA system consists of perception elements: ultrasonic radar and surround-view cameras; perception fusion motion planning elements: domain controllers, and lateral and longitudinal actuators.

[0146] Combining the main functions of APA, the HAZOP analysis method is used to identify hazard events related to expected functional safety. Then, potential functional deficiencies and triggering conditions are identified. Based on the hazard events, the Fault Tree Analysis (FTA) method can be used to analyze system-level functional deficiencies and foreseeable human misuse, extending to the architectural element level.

[0147] Please refer to Figure 7 , Figure 7 This is a schematic diagram illustrating a late emergency braking trigger condition for a vehicle, as described in an embodiment of this application. Taking late emergency braking as an example, the functional deficiencies of the architectural elements—ultrasonic radar and surround-view camera—include: missed target identification; functional deficiencies of the perception fusion planning element include target identification errors; and functional deficiencies of the longitudinal actuator include excessively long braking decompression time. Foreseeable human misuse includes the driver's failure to observe the vehicle's surroundings.

[0148] Based on the functional deficiencies of the above architectural elements and the foreseeable misuse by personnel, combined with the performance deficiencies of the architectural elements, triggering conditions are designed.

[0149] Designing trigger conditions involves defining acceptance criteria for those conditions. Specifically, an acceptance criterion P0 can be defined for each trigger condition corresponding to an expected functional safety hazard event. These acceptance criteria are derived from traffic accident statistics and industry standards. For example, an accident rate ≤ 1 incident per 100,000 parking incidents.

[0150] For details on the triggering conditions, please refer to the table below:

[0151]

[0152] If the performance boundary (i.e. the probability of occurrence) is better than the acceptance criterion, no modification is needed. If it is worse than the acceptance criterion (i.e., P>P0), the strategy needs to be modified (such as replacing the corresponding hardware unit, adjusting the process or parameters in the firmware, etc.) until the performance boundary is better than the acceptance criterion.

[0153] Furthermore, after modifying the assisted parking strategy, the process of simulating refined scenarios from the scenario library in a bench testing environment can be performed until the probability of occurrence is no higher than the acceptance criterion. The threshold can be set in advance, and its specific value can be determined according to actual needs; no limitation is made here.

[0154] For more detailed scenario information, please refer to the table below.

[0155]

[0156]

[0157] Corresponding to the above method embodiments, this application also provides an assisted parking test device. The assisted parking test device described below can be referred to in correspondence with the assisted parking test method described above.

[0158] See Figure 8 As shown, the device includes the following modules:

[0159] Hazard event determination unit 101 is used to determine hazard events of the autonomous parking assistance system;

[0160] The scenario refinement unit 102 is used to analyze safety-critical scenarios and obtain a refined scenario library including risk factors.

[0161] The scene simulation unit 103 is used to simulate detailed scenes in the detailed scene library in a bench verification environment;

[0162] The hazard testing unit 104 is used to adjust the parameter values ​​of risk factors in the refined scenario, perform automated testing, and obtain test information on hazard events.

[0163] Using the apparatus provided in the embodiments of this application, hazardous events of the autonomous parking assistance system are determined; safety-critical scenarios are analyzed to obtain a detailed scenario library including risk factors; the detailed scenarios in the detailed scenario library are simulated in a bench verification environment; the parameter values ​​of risk factors in the detailed scenarios are adjusted, and automated testing is performed to obtain test information of hazardous events.

[0164] This application first identifies hazardous events in an autonomous parking assist system (APA), then analyzes safety-critical scenarios to obtain a detailed scenario library including risk factors. Subsequently, the detailed scenarios in this library can be simulated in a bench testing environment, and automated testing can be performed by adjusting the parameter values ​​of the risk factors within these scenarios, ultimately yielding test information on hazardous events. In other words, this application can identify known and unknown risks during testing in the early stages of expected functional safety development, providing a prerequisite for further improvements in APA performance.

[0165] In one specific embodiment of this application, the hazard testing unit 104 is specifically used to randomly adjust the parameter values ​​of risk factors in the refined scenario, perform automated testing, obtain the probability of occurrence of the hazard event, the hazard scenario in which the hazard event occurs, and record the risk factor parameters of the hazard scenario.

[0166] The probability of occurrence, the hazardous scenario, and the risk factor parameters are defined as the test information for hazardous events.

[0167] In one specific embodiment of this application, the hazard testing unit 104 is specifically used to randomly adjust the parameter values ​​of risk factors in the refined scenario;

[0168] Obtain the input parameters for probability calculation; among which, the input parameters include the number of the current test case, the total number of test cases, the number of the current risk factor, the total number of risk factors in the refined scenario, the probability of the current risk factor, and the true or false value of whether the refined scenario produces a harmful event.

[0169] By substituting the parameters into the probability calculation model for the occurrence of a hazardous event, the probability of the hazardous event occurring can be obtained.

[0170] In one specific embodiment of this application, it further includes: a strategy adjustment module, used to analyze hazardous events and determine triggering conditions;

[0171] Define the acceptance criteria corresponding to the triggering conditions;

[0172] If the probability of occurrence is higher than the acceptance criterion, then modify the assisted parking strategy;

[0173] If the probability of occurrence is not higher than the acceptance criterion, then the assisted parking strategy is determined to have been optimized.

[0174] In one specific embodiment of this application, it further includes: a strategy iteration change module, used to perform a step of simulating a refined scenario in a refined scenario library in a bench verification environment after modifying the assisted parking strategy, until the probability of occurrence is not higher than the acceptance criterion.

[0175] In one specific embodiment of this application, the scenario refinement unit 102 is specifically used to analyze the perception key scenario, the road traffic key scenario and the vehicle control key scenario to obtain risk factors.

[0176] By structuring the risk factors, a detailed scenario library is obtained.

[0177] In one specific embodiment of this application, the scene refinement unit 102 is specifically used to analyze the performance limitations of the sensing sensors, the influence of the surrounding environment, the sensing targets and the sensing blind spots in the key sensing scene to obtain the sensing risk factors.

[0178] Among them, the perceived risk factors include at least one of the following: detection distance, detection accuracy, potholes, muddy roads, rain, glare, lane lines, curbs, traffic lights, speed limit signs, traffic cones, medians, pedestrians, vehicles, walls, uphill, downhill, and curves.

[0179] In one specific embodiment of this application, the scenario refinement unit 102 is specifically used to analyze the vehicle operation, relative position with other traffic participants, types of other traffic participants, and operations of other traffic participants in key road traffic scenarios to obtain traffic risk factors.

[0180] Traffic risk factors include at least one of the following: overtaking, changing lanes, merging, reversing, parking, directly in front, to the side front, directly behind, to the side rear, adults, children, passenger cars, commercial vehicles, special vehicles, motorcycles, and crossing.

[0181] In one specific embodiment of this application, the scenario refinement unit 102 is specifically used to analyze the wheel forces and body forces in key vehicle control scenarios to obtain control risk factors.

[0182] Among them, the risk factors to be controlled include at least one of the following: icy and snowy road surface, wet and slippery road surface, dry road surface, tire aging, tire blowout, crosswind, tailwind, headwind, cross slope, longitudinal slope, and road curvature radius.

[0183] Corresponding to the above method embodiments, this application also provides an electronic device. The electronic device described below and the assisted parking test method described above can be referred to in correspondence.

[0184] See Figure 9 As shown, the electronic device includes:

[0185] Memory 332 is used to store computer programs;

[0186] The processor 322 is used to execute a computer program to implement the steps of the assisted parking test method of the above method embodiments.

[0187] For details, please refer to Figure 10 , Figure 10 This is a schematic diagram of a specific structure of an electronic device provided in this embodiment. The electronic device can vary significantly due to differences in configuration or performance. It may include one or more central processing units (CPUs) 322 (e.g., one or more processors) and a memory 332. The memory 332 stores one or more computer programs 342 or data 344. The memory 332 can be temporary or permanent storage. The program stored in the memory 332 may include one or more modules (not shown in the diagram), each module may include a series of instruction operations on the data processing device. Furthermore, the central processing unit 322 may be configured to communicate with the memory 332 and execute the series of instruction operations stored in the memory 332 on the electronic device 301.

[0188] Electronic device 301 may also include one or more power supplies 326, one or more wired or wireless network interfaces 350, one or more input / output interfaces 358, and / or one or more operating systems 341.

[0189] The steps in the assisted parking test method described above can be implemented by the structure of electronic devices.

[0190] Corresponding to the above method embodiments, this application also provides a readable storage medium. The readable storage medium described below can be referred to in conjunction with the assisted parking test method described above.

[0191] A readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the assisted parking test method described in the above method embodiments.

[0192] The readable storage medium can specifically be a USB flash drive, external hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, or any other readable storage medium capable of storing program code.

[0193] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0194] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0195] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0196] Finally, it should be noted that in this document, relationships such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "include," "contain," or any other variations are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus.

[0197] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for testing assisted parking, characterized in that, include: Identify hazardous events related to autonomous parking assistance systems; Analyze safety-critical scenarios to obtain a detailed scenario library including risk factors; Simulate the refined scenarios in the refined scenario library in a bench testing environment; The bench validation environment includes: a simulation environment simulator, the autonomous parking assistance system under test, a virtual actuator, and a monitor; Adjust the parameter values ​​of the risk factors in the refined scenario, perform automated testing, and obtain test information of the hazardous event; The step of adjusting the parameter values ​​of the risk factors in the refined scenario and performing automated testing to obtain test information on the hazardous event includes: Randomly adjust the parameter values ​​of the risk factors in the refined scenario, perform automated testing, obtain the probability of occurrence of the hazardous event, the hazardous scenario in which the hazardous event occurs, and record the risk factor parameters in which the hazardous scenario occurs; The occurrence probability, the hazardous scenario, and the risk factor parameters are determined as the test information for the hazardous event.

2. The assisted parking test method according to claim 1, characterized in that, The process of randomly adjusting the parameter values ​​of the risk factors in the refined scenario and performing automated testing to obtain the probability of occurrence of the hazardous event includes: Randomly adjust the parameter values ​​of the risk factors in the refined scenario; Obtain the probability calculation input parameters; wherein, the input parameters include the number of the current test case, the total number of test cases, the number of the current risk factor, the total number of risk factors in the refined scenario, the probability of the current risk factor, and the true or false value of whether the refined scenario produces the harmful event. The probability of the hazardous event occurring is obtained by substituting the parameters into the probability calculation model.

3. The assisted parking test method according to claim 1, characterized in that, Also includes: Analyze the hazardous events to determine the triggering conditions; Define the acceptance criteria corresponding to the triggering conditions; If the probability of occurrence is higher than the acceptance criterion, then modify the assisted parking strategy; If the probability of occurrence is not higher than the acceptance criterion, then the assisted parking strategy is determined to have been optimized.

4. The assisted parking test method according to claim 3, characterized in that, Following the modification of the assisted parking strategy, the following is also included: Perform the step of simulating the refined scenarios in the refined scenario library in the bench verification environment until the probability of occurrence is not higher than the acceptance criterion, or the number of iterations reaches a threshold.

5. The assisted parking test method according to any one of claims 1 to 4, characterized in that, The analysis of safety-critical scenarios yields a detailed scenario library including risk factors, comprising: The risk factors are obtained by analyzing key perception scenarios, key road traffic scenarios, and key vehicle control scenarios. The risk factors are structured to obtain the refined scenario library.

6. The assisted parking test method according to claim 5, characterized in that, The risk factors are obtained by analyzing key perception scenarios, including: The performance limitations of the sensing sensors, the influence of the surrounding environment, the sensing targets, and the sensing blind spots in the key sensing scenarios are analyzed to obtain the sensing risk factors; The perceived risk factors include at least one of the following: detection distance, detection accuracy, potholes, muddy roads, rain, glare, lane lines, curbs, traffic lights, speed limit signs, traffic cones, medians, pedestrians, vehicles, walls, uphill, downhill, and curves.

7. The assisted parking test method according to claim 5, characterized in that, The risk factors, obtained by analyzing key road traffic scenarios, include: Traffic risk factors are obtained by analyzing the vehicle's operation, relative position with other traffic participants, types of other traffic participants, and operations of other traffic participants in the key road traffic scenarios. The traffic risk factors include at least one of the following: overtaking, changing lanes, merging, reversing, stopping, directly in front, to the side in front, directly behind, to the side in front, adults, children, passenger cars, commercial vehicles, special vehicles, motorcycles, and crossing.

8. The assisted parking test method according to claim 5, characterized in that, The risk factors, obtained by analyzing key vehicle control scenarios, include: The wheel and body forces in the key vehicle control scenarios are analyzed to obtain control risk factors; The risk control factors include at least one of the following: icy and snowy road surface, wet and slippery road surface, dry road surface, tire aging, tire blowout, crosswind, tailwind, headwind, cross slope, longitudinal slope, and road curvature radius.

9. An auxiliary parking test device, characterized in that, include: Hazard event determination unit, used to determine hazard events of the autonomous parking assistance system; The scenario refinement unit is used to analyze safety-critical scenarios and obtain a refined scenario library including risk factors. The scene simulation unit is used to simulate the refined scenes in the refined scene library in a bench verification environment; The bench validation environment includes: a simulation environment simulator, the autonomous parking assistance system under test, a virtual actuator, and a monitor; A hazard testing unit is used to adjust the parameter values ​​of the risk factors in the refined scenario, perform automated testing, and obtain test information of the hazard event; wherein, adjusting the parameter values ​​of the risk factors in the refined scenario, performing automated testing, and obtaining test information of the hazard event includes: randomly adjusting the parameter values ​​of the risk factors in the refined scenario, performing automated testing, obtaining the probability of occurrence of the hazard event, and the hazard scenario in which the hazard event occurs, and recording the risk factor parameters in which the hazard scenario occurs; and determining the probability of occurrence, the hazard scenario, and the risk factor parameters as the test information of the hazard event.

10. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, configured to implement the steps of the assisted parking test method as described in any one of claims 1 to 8 when executing the computer program.

11. A readable storage medium, characterized in that, The readable storage medium stores a computer program that, when executed by a processor, implements the steps of the assisted parking test method as described in any one of claims 1 to 8.

Images