Vehicle testing method, electronic device and vehicle

Abstract

The application provides a vehicle testing method, an electronic device and a vehicle, relates to the technical field of automobile testing, can realize fusion evaluation of multidimensional risks, improves the accuracy and adaptability of risk evaluation, better copes with complex test scenes, is especially suitable for unmanned site testing of intelligent driving vehicles, and can effectively improve the test safety and evaluation accuracy of an intelligent driving system. The vehicle testing method comprises the following steps: in the process that a test vehicle executes a first test task, acquiring risk field parameters of the test vehicle, the risk field parameters comprising test site risk field parameters, vehicle end risk field parameters and environment risk field parameters; constructing a multidimensional risk field model of the test vehicle according to the risk field parameters of the test vehicle; and determining a first task adjustment strategy according to the multidimensional risk field model, the first task adjustment strategy being used for indicating adjustment of a test route and / or a test task.

Description

Technical Field

[0001] This application relates to the field of automotive testing technology, specifically to a vehicle testing method, electronic equipment, and vehicle. Background Technology

[0002] Vehicle durability testing is a crucial part of the vehicle development process. Traditional durability testing is mostly conducted by drivers in closed test tracks or public roads, which suffers from high labor costs, low testing efficiency, and poor repeatability. With the development of autonomous driving technology, unmanned durability testing is gradually becoming an industry trend.

[0003] In unmanned endurance testing, test vehicles operate for extended periods without a driver, facing a variety of dynamic risks. Existing risk assessment methods consider only a limited range of risk factors, making it difficult to adequately support accurate assessments in complex testing scenarios. Summary of the Invention

[0004] This application provides a vehicle testing method, electronic device, and vehicle that can achieve multi-dimensional risk fusion assessment, improve the accuracy and adaptability of risk assessment, and thus better cope with complex testing scenarios.

[0005] In a first aspect, this application provides a vehicle testing method, which includes: during the execution of a first test task by a test vehicle, acquiring risk field parameters of the test vehicle, the risk field parameters including test site risk field parameters, vehicle-side risk field parameters, and environmental risk field parameters; constructing a multi-dimensional risk field model of the test vehicle based on the risk field parameters of the test vehicle; and determining a first task adjustment strategy based on the multi-dimensional risk field model, the first task adjustment strategy being used to indicate adjustments to the test route and / or test task.

[0006] The vehicle testing method provided in this application constructs a multi-dimensional risk field model by acquiring multiple risk field parameters and adjusting the vehicle's testing tasks according to the model. This achieves a multi-dimensional risk fusion assessment of the test vehicle during the measurement process, avoiding misjudgments caused by a single dimension, improving the accuracy of risk assessment, and ensuring the safety and efficiency of the testing process. Furthermore, it can better handle various complex testing scenarios and improve the adaptability of testing tasks.

[0007] In some embodiments, determining a first task adjustment strategy based on a multi-dimensional risk field model includes: determining the first risk field strength output by the multi-dimensional risk field model; and determining the first task adjustment strategy based on a comparison between the first risk field strength and a risk threshold.

[0008] In some embodiments, the risk threshold includes a first risk threshold and a second risk threshold, and the first task adjustment strategy satisfies any one of the following: if the comparison result shows that the field strength of the first risk field is less than the first risk threshold, the first task adjustment strategy is used to instruct the continued execution of the first test task on the first test route; if the comparison result shows that the field strength of the first risk field is greater than or equal to the first risk threshold and less than the second risk threshold, the first task adjustment strategy is used to instruct the test route to be adjusted from the first test route to the second test route; if the comparison result shows that the field strength of the first risk field is greater than the second risk threshold, the first task adjustment strategy is used to instruct the test vehicle to be adjusted from the first test task to perform the second test task.

[0009] In some embodiments, the method further includes: determining a second risk field strength of the test vehicle during the execution of a second test task; and determining a second task adjustment strategy if the second risk field strength is greater than or equal to a second risk threshold.

[0010] In some embodiments, the second task adjustment strategy is used to instruct any of the following: instructing the test route to be adjusted from the second test route to the third test route; instructing the test vehicle to be adjusted from the second test task to perform the third test task; wherein the third test task is a preset low-risk test task; instructing the test vehicle to stop in a preset avoidance zone.

[0011] In some embodiments, before determining the first task adjustment strategy based on the comparison between the first risk field strength and the risk threshold, the method further includes: obtaining the completed test mileage and vehicle health status information of the test vehicle; and determining the risk threshold based on the completed test mileage and vehicle health status information of the test vehicle.

[0012] In some embodiments, the risk threshold is negatively correlated with the mileage of completed testing.

[0013] In some embodiments, a multi-dimensional risk field model of the test vehicle is constructed based on the risk field parameters of the test vehicle, including: obtaining vehicle health status information of the test vehicle; correcting the vehicle-side risk field parameters based on the vehicle health status information to obtain corrected vehicle-side risk field parameters; and constructing a multi-dimensional risk field model of the test vehicle based on the corrected vehicle-side risk field parameters, the test site risk field parameters, and the environmental risk field parameters.

[0014] Secondly, this application provides a vehicle testing device, which includes an acquisition unit and a processing unit. The acquisition unit is used to acquire risk field parameters of the test vehicle during the execution of a first test task. The risk field parameters include test site risk field parameters, vehicle-end risk field parameters, and environmental risk field parameters. The processing unit constructs a multi-dimensional risk field model of the test vehicle based on the risk field parameters. Based on the multi-dimensional risk field model, it determines a first task adjustment strategy, which is used to indicate the adjustment of the test route and / or test task.

[0015] In some embodiments, the processing unit is specifically used to determine the first risk field strength output by the multi-dimensional risk field model; and to determine a first task adjustment strategy based on the comparison between the first risk field strength and the risk threshold.

[0016] In some embodiments, the risk threshold includes a first risk threshold and a second risk threshold, and the first task adjustment strategy satisfies any one of the following: if the comparison result shows that the field strength of the first risk field is less than the first risk threshold, the first task adjustment strategy is used to instruct the continued execution of the first test task on the first test route; if the comparison result shows that the field strength of the first risk field is greater than or equal to the first risk threshold and less than the second risk threshold, the first task adjustment strategy is used to instruct the test route to be adjusted from the first test route to the second test route; if the comparison result shows that the field strength of the first risk field is greater than the second risk threshold, the first task adjustment strategy is used to instruct the test vehicle to be adjusted from the first test task to perform the second test task.

[0017] In some embodiments, the processing unit is further configured to determine the second risk field strength of the test vehicle during the execution of the second test task; and to determine the second task adjustment strategy if the second risk field strength is greater than or equal to the second risk threshold.

[0018] In some embodiments, the second task adjustment strategy is used to instruct any of the following: instructing the test route to be adjusted from the second test route to the third test route; instructing the test vehicle to be adjusted from the second test task to perform the third test task; wherein the third test task is a preset low-risk test task; instructing the test vehicle to stop in a preset avoidance zone.

[0019] In some embodiments, before determining the first task adjustment strategy based on the comparison between the first risk field strength and the risk threshold, the acquisition unit is further configured to acquire the completed test mileage and vehicle health status information of the test vehicle; the processing unit is further configured to determine the risk threshold based on the completed test mileage and vehicle health status information of the test vehicle.

[0020] In some embodiments, the risk threshold is negatively correlated with the mileage of completed testing.

[0021] In some embodiments, the processing unit is specifically used to acquire vehicle health status information of the test vehicle; correct the vehicle-side risk field parameters based on the vehicle health status information to obtain corrected vehicle-side risk field parameters; and construct a multi-dimensional risk field model of the test vehicle based on the corrected vehicle-side risk field parameters, test site risk field parameters, and environmental risk field parameters.

[0022] Thirdly, this application provides an electronic device comprising: a processor and a memory; the memory storing processor-executable instructions; when the processor is configured to execute the instructions, causing the electronic device to implement the method of the first aspect described above.

[0023] Fourthly, this application provides a computer-readable storage medium comprising: computer software instructions; which, when executed in an electronic device, cause the electronic device to implement the method described in the first aspect.

[0024] Fifthly, this application provides a vehicle that includes the electronic equipment described in the third aspect, or the vehicle that includes the computer-readable storage medium described in the fourth aspect.

[0025] Sixthly, this application provides a computer program product comprising a computer program; when the computer program is run in an electronic device, it causes the electronic device to implement the method described in the first aspect.

[0026] The beneficial effects of the second to sixth aspects mentioned above are described in the corresponding description of the first aspect and will not be repeated here. Attached Figure Description

[0027] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the 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.

[0028] Figure 1 This is a schematic diagram of the structure of a vehicle testing system provided in an embodiment of this application; Figure 2 A flowchart of a vehicle testing method provided in an embodiment of this application; Figure 3 A schematic diagram illustrating the construction of a multi-dimensional risk field model provided in an embodiment of this application; Figure 4 A flowchart illustrating a method for determining a first task scheduling strategy as provided in an embodiment of this application; Figure 5A flowchart illustrating a method for determining a second task scheduling strategy as provided in an embodiment of this application; Figure 6 A flowchart illustrating a method for determining a risk threshold as provided in an embodiment of this application; Figure 7 A flowchart illustrating a method for constructing a multi-dimensional risk field model provided in this application embodiment; Figure 8 A flowchart illustrating another vehicle testing method provided in this application embodiment; Figure 9 This is a schematic diagram of the structure of a vehicle testing device provided in an embodiment of this application; Figure 10 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0029] Figure Descriptions: Vehicle testing system 10, test site infrastructure 100, cloud scheduling platform 200, test vehicle 300, roadside sensing device 110, meteorological environment monitoring device 120, first communication module 130, test site data storage module 210, terrain and road surface feature storage module 220, comprehensive risk field strength calculation module 230, task adjustment strategy generation module 240, test vehicle test scheduling module 250, second communication module 260, positioning module 310, environmental perception module 320, vehicle status monitoring module 330, on-board computing unit 340, execution control module 350, third communication module 360. Detailed Implementation

[0030] In the embodiments of this application, the terms "first," "second," "third," "fourth," "fifth," and "sixth" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined with "first," "second," "third," "fourth," "fifth," and "sixth" may explicitly or implicitly include one or more of that feature.

[0031] In embodiments of this application, the terms "comprising," "including," or any other variations thereof 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. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0032] "A and / or B" includes the following three combinations: A only, B only, and a combination of A and B.

[0033] Vehicle durability testing is a crucial part of the vehicle development process. Traditional durability testing is mostly conducted by drivers in closed test tracks or public roads, which suffers from high labor costs, low testing efficiency, and poor repeatability. With the development of autonomous driving technology, unmanned durability testing is gradually becoming an industry trend.

[0034] In unmanned endurance testing, test vehicles operate for extended periods without a driver, facing a variety of dynamic risks. Existing risk assessment methods consider only a limited range of risk factors, making it difficult to adequately support accurate assessments in complex testing scenarios.

[0035] To address the aforementioned technical issues, this application provides a vehicle testing method, electronic device, and vehicle that can achieve multi-dimensional risk fusion assessment, improving the comprehensiveness and adaptability of risk assessment, thereby better handling complex testing scenarios. The vehicle testing method involves: during the execution of a first test task by the test vehicle, acquiring the risk field parameters of the test vehicle, including test site risk field parameters, vehicle-side risk field parameters, and environmental risk field parameters; constructing a multi-dimensional risk field model of the test vehicle based on the risk field parameters; and determining a first task adjustment strategy based on the multi-dimensional risk field model, which is used to indicate adjustments to the test route and / or test task.

[0036] The vehicle testing method provided in the embodiments of this application is described below with reference to the accompanying drawings.

[0037] This application provides a vehicle testing system. For example... Figure 1 As shown, the vehicle testing system 10 includes a test site infrastructure 100, a cloud scheduling platform 200, and at least one test vehicle 300.

[0038] It should be noted that the test vehicles described in this application are not limited to fully driverless vehicles, but may also include test vehicles with human drivers but capable of data collection and command execution.

[0039] The test site infrastructure 100 includes a roadside sensing device 110, a meteorological environment monitoring device 120, and a first communication module 130.

[0040] The roadside sensing device 110 is used to collect static road structure information and dynamic obstacle information of the test site. Static road structure information may include, for example, lane line geometry features (such as curvature, width, and type), physical boundary attributes (such as curb height, guardrail location and type), road surface terrain classification (such as asphalt, cement, gravel, and wading), road surface slope, and static high-risk areas of the test site (such as the outer edge of sharp curves and the edge of high embankments). The static road structure information can be obtained from pre-collected high-precision maps in the cloud, serving as the basic input data for risk calculation of the test site.

[0041] The meteorological environment monitoring device 120 is used to collect meteorological information from basic environmental data, such as ambient temperature, visibility, snowfall, rainfall, wind speed, and light intensity. Meteorological information can be obtained through site meteorological sensors or third-party meteorological service interfaces and is used in meteorological functions for subsequent environmental risk calculations.

[0042] The first communication module 130 is used to communicate with the test vehicle 300, for example, through communication based on vehicle-to-everything (V2X) or dedicated short-range communications (DSRC) technologies.

[0043] The cloud-based scheduling platform 200 is deployed in the cloud and is responsible for the fusion of multi-source basic data, multi-dimensional risk modeling, and generation of task adjustment strategies.

[0044] The cloud-based scheduling platform 200 includes a test site data storage module 210, a terrain and road surface feature storage module 220, a comprehensive risk field strength calculation module 230, a task adjustment strategy generation module 240, a test vehicle test scheduling module 250, and a second communication module 260.

[0045] The test site data storage module 210 is used to store static road structure related data of the test site (such as lane line geometry, physical boundaries, road surface topography, etc.) as the basic data for test site risk calculation.

[0046] The terrain and road surface feature storage module 220 is used to store feature data such as terrain geometry and road surface adhesion coefficient, such as slope values, road surface friction coefficients, and road surface material types for different road sections, as the input basis for the terrain risk function.

[0047] The comprehensive risk field strength calculation module 230 is used to construct a multi-dimensional risk field model of the test vehicle based on the received original dynamic data from the vehicle, basic environmental data, and static data from the test site, and output the comprehensive risk field strength. This model integrates the risk level of the test site, the risk level of the vehicle, the environmental risk level, and correction terms.

[0048] The task adjustment strategy generation module 240 determines the task adjustment strategy based on the risk field strength output by the multidimensional risk model. This strategy is used to instruct adjustments to the test route and / or test task. For example, when the risk is low, the original test plan can be maintained; when the risk is at a medium level, the test route can be adjusted to avoid high-risk areas (such as slippery surfaces or curves with obstructed visibility); when the risk is high, the test vehicle can be instructed to slow down, terminate the current test task, or perform a safe stop.

[0049] The test vehicle scheduling module 250 is used to schedule the test vehicle 300 through the second communication module 260 according to the task adjustment strategy determined by the task adjustment strategy generation module 240.

[0050] The second communication module 260 is used for bidirectional communication with the test vehicle 300 and the test site infrastructure 100 via a wireless communication network, such as network communication based on 5G or Long Term Evolution Vehicle-to-Everything (LTE-V2X), to issue task adjustment strategies and receive raw collected data uploaded by the vehicle. The data transmission delay is no greater than 100 milliseconds.

[0051] Furthermore, the cloud-based dispatch platform 200 can independently acquire auxiliary decision-making data such as high-precision maps, traffic data, and meteorological data, without relying on vehicle uploads. For example, the cloud can obtain real-time weather forecasts for the test site through third-party meteorological service interfaces, or obtain precise geometric information of roads through high-precision map services.

[0052] Test vehicle 300 is deployed on the vehicle side and is responsible for raw data collection and command execution.

[0053] The test vehicle 300 includes a positioning module 310, an environmental perception module 320, a vehicle status monitoring module 330, an on-board computing unit 340, an execution control module 350, and a third communication module 360.

[0054] The positioning module 310 is used to acquire the location information of the test vehicle in real time, such as the distance from the vehicle to the center line of the lane and the distance from the vehicle to the boundary line, as the basic location data for risk calculation of the test site.

[0055] The environmental perception module 320 is used to collect raw perception data of the vehicle's surroundings, including raw point cloud or image data of the surrounding environment, as well as dynamic obstacle information (such as the position, speed, size, and type of obstacles such as other test vehicles, pedestrians, and non-motorized vehicles). This module includes at least one or more of the following: LiDAR, camera, and millimeter-wave radar.

[0056] The vehicle condition monitoring module 330 is used to collect real-time dynamic data of the vehicle, including driving speed, acceleration, tire pressure, steering angle, pitch angle, wheel speed, etc. This module includes at least one or more of the following: an inertial measurement unit (IMU), a tire pressure sensor, a vehicle speed sensor, and wheel speed sensors. These basic parameters are used for subsequent calculations of vehicle-side risk levels (such as kinetic energy level, roll stability, pitch stability, tire contact patch status, and ground clearance).

[0057] The onboard computing unit 340 is used to preprocess the collected raw data (such as time synchronization, coordinate transformation, filtering and noise reduction) and upload it to the cloud when communication is normal. In the event of communication interruption or timeout, the onboard computing unit 340 enters a local degraded decision-making mode to perform local path planning and safety control. For example, when the 5G signal loss exceeds a set threshold, the vehicle automatically switches to local decision-making, relying on onboard sensors to maintain lane centering and decelerate to a safe speed.

[0058] The execution control module 350 is used to receive and execute the task adjustment strategy sent from the cloud, driving the corresponding actuators to complete route adjustment or task change operations. The corresponding actuators may include, for example, a braking system, a steering system, and a drive system.

[0059] The third communication module 360 ​​is used to upload the collected raw data (such as location information, environmental perception data, and vehicle status data) to the cloud dispatch platform 200 in real time via a wireless communication network, and to receive task adjustment strategies issued by the cloud. The data transmission delay is no more than 100 milliseconds.

[0060] Under normal system communication conditions, the test vehicle 300 uploads its collected location information, raw environmental perception data, and vehicle dynamic data to the cloud dispatch platform 200 in real time via the third communication module 360. Examples of uploaded data include: vehicle speed, acceleration, tire pressure, steering angle, obstacle projection area, obstacle orientation angle, relative speed and distance to other test vehicles, and relative heading angle.

[0061] The cloud-based scheduling platform 200 integrates the raw data uploaded by the test vehicle 300, as well as independently acquired high-precision maps, meteorological data, traffic data, etc., and constructs a multi-dimensional risk field model through the comprehensive risk field strength calculation module 230 to calculate the current comprehensive risk field strength (e.g., total risk field strength). The task adjustment strategy generation module 240 then generates a task adjustment strategy based on the model output results.

[0062] It should be noted that the application scenarios of the embodiments in this application are not limited. The system architecture and business scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new business scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0063] Figure 2 A flowchart of a vehicle testing method provided in this application embodiment is shown below. Figure 2 As shown, the vehicle testing method includes the following steps: S101. During the process of the test vehicle performing the first test task, obtain the risk field parameters of the test vehicle.

[0064] Among them, risk field parameters are used to characterize the safety risk factors encountered by the test vehicle during driving. In order to ensure the accuracy of vehicle test evaluation, risk field parameters include, but are not limited to, test site risk field parameters, vehicle-side risk field parameters, and environmental risk field parameters.

[0065] Test site risk field parameters refer to risk factors related to the static road structure of the test site. For example, test site risk field parameters include lane line risk, physical boundary risk, and test site topographic risk, which can be determined based on the following data: lane line geometry (curvature, width, type), physical boundary attributes (curve height, guardrail location and type), road surface topography classification (asphalt, cement, gravel, wading, etc.), road surface slope, and static high-risk areas of the test site (such as the outer side of sharp curves, the edge of high embankments).

[0066] In some embodiments, the risk field parameters of the test site can be obtained through a high-precision map pre-collected in the cloud.

[0067] Vehicle-side risk field parameters refer to dynamic risk factors perceived in real time by the test vehicle's own state or on-board sensors.

[0068] Specifically, the vehicle-end risk field parameters include: kinetic energy level, roll stability, pitch stability, tire contact patch status, and bottoming-out risk. Each parameter is calculated from several corresponding raw sensor parameters to reflect the corresponding vehicle-end risk: kinetic energy level is calculated from vehicle speed and mass to assess the risk of impact-induced loss of control; roll stability is calculated from parameters such as lateral acceleration and suspension displacement to assess the risk of rollover; pitch stability is calculated from parameters such as longitudinal acceleration and pitch angle to assess the risk of longitudinal roll-out risk; tire contact patch status is calculated from parameters such as tire pressure, wheel speed, and vertical load to assess the risk of insufficient grip or slippage; and bottoming-out risk is calculated from chassis height sensors or suspension travel to assess the risk of bottoming-out or chassis collision.

[0069] In some embodiments, the test vehicle collects raw sensor signals such as vehicle speed, acceleration, wheel speed, suspension displacement, tire pressure, and vehicle attitude angle through an onboard bus (such as Controller Area Network (CAN), onboard Ethernet, or FlexRay bus). The cloud obtains the above raw data from the test vehicle and uploads it to the cloud in real time through a wireless communication network (such as 5G or V2X).

[0070] Environmental risk field parameters refer to the risk factors arising from changes in meteorological conditions and the characteristics of dynamic obstacles within the test site. Specifically, environmental risk field parameters can be determined based on dynamic obstacle information and meteorological information.

[0071] In some embodiments, dynamic obstacle information is extracted by the cloud from the raw sensor data uploaded by the test vehicle: the test vehicle collects raw perception data of the surrounding environment in real time through onboard LiDAR, cameras, and millimeter-wave radar and uploads it to the cloud. The cloud identifies the position, speed, size, type, and other information of dynamic obstacles (such as other test vehicles, pedestrians, non-motorized vehicles, etc.). In addition, the cloud can also obtain global obstacle information through fixed cameras deployed in the test site as a supplementary data source.

[0072] In some embodiments, meteorological information is obtained from site meteorological sensors or third-party meteorological service interfaces via the cloud. Exemplarily, meteorological information may include ambient temperature, visibility, snowfall, rainfall, wind speed, and light intensity.

[0073] In some embodiments, the test vehicle can be any vehicle equipped with autonomous driving or advanced driver assistance functions. For example, the test vehicle can be a passenger car or commercial vehicle equipped with an autonomous driving system. This application does not limit the specific vehicle model.

[0074] In some embodiments, the first test task is a predefined sequence of operations used to evaluate specific performance or safety of the test vehicle. Exemplarily, the first test task may include, but is not limited to: lane keeping and following tasks on urban roads, turning tasks at intersections, automatic emergency braking tasks, automatic parking tasks, etc.

[0075] S102. Based on the risk field parameters of the test vehicle, construct a multi-dimensional risk field model of the test vehicle.

[0076] In some embodiments, the multi-dimensional risk field model is a comprehensive quantitative model that integrates the risk field parameters of the test vehicle (including test site risk field parameters, vehicle-end risk field parameters, and environmental risk field parameters) to assess the overall risk level of the test vehicle at the current moment and current location in real time.

[0077] Specifically, the multidimensional risk field model satisfies the following relationship: , in, This represents the risk field strength output by the multi-dimensional risk field model; The test site risk field strength is determined based on the test site risk field parameters. The test site risk field strength is determined based on the vehicle-side risk field parameters; The field strength of the test site risk field is determined based on the environmental risk field parameters.

[0078] For example, Figure 3 This demonstrates the construction of a multi-dimensional risk field model. For example... Figure 3 As shown, the construction parameters of the multi-dimensional risk field model include test site risk field parameters (including lane line risk, physical boundary risk, and test site terrain risk), vehicle-end risk field parameters (kinetic energy level, roll stability, pitch stability, tire contact status, and bottoming-out risk), and environmental risk field parameters (weather conditions and obstacle characteristics). The risk field strength output by this multi-dimensional risk field model is... l is obtained through the coupled calculation of the above-mentioned test site risk field parameters, vehicle-end risk field parameters, and environmental risk field parameters.

[0079] Optionally, the multi-dimensional risk field model can also include other types of risk items, such as communication link quality risk or information security risk, and add corresponding risk extension terms to the above relationship.

[0080] Risk field strength determined based on risk field parameters of the test site The following relationship must be satisfied: , in, , , These represent the risk gain coefficients for lane lines, physical boundaries, and test site terrain, respectively. This is the Euclidean distance from the vehicle's position to the center line of the lane. Lane width; The Euclidean distance from the vehicle's position to the boundary line (including lane lines and site boundary lines); This is a terrain risk function, the value of which is determined by the terrain geometry. With road surface adhesion coefficient Decide.

[0081] Risk field strength determined based on vehicle-side risk field parameters The following relationship must be satisfied: , in, For each gain coefficient, the first Gain coefficient of the risk field parameters at the vehicle end. =1,2,…,5, corresponding to kinetic energy level, roll stability, pitch stability, tire contact with the ground, and bottoming risk, respectively; To test vehicle quality; To test the vehicle's speed; For reference kinetic energy; For steering angle; acceleration due to gravity The wheelbase is the distance between the left and right wheels. The pitch angle; Average tire pressure; For reference tire pressure; This refers to the tire pressure sensitivity coefficient. This refers to the actual height above the ground. For reference ground clearance; For reference speed.

[0082] Risk field strength determined based on environmental risk field parameters The following relationship must be satisfied: , in, The current moment; For meteorological functions; Obstacles Projected area on the ground; To test vehicles and obstacles The distance; For reference distance; Basic risk coefficient; The obstacle size sensitivity index; The velocity sensitivity coefficient; The relative speed of other vehicles with respect to the test vehicle; Obstacles The orientation angle relative to the test vehicle; This is the orientation sensitivity index.

[0083] It should be noted that all reference values ​​in the above multidimensional risk model (including reference kinetic energy, reference tire pressure, reference ground clearance, reference speed, reference distance, etc.) are benchmark parameters that have been pre-calibrated experimentally or determined according to the standard operating conditions of the test vehicle and test site. All gain coefficients and sensitivity indices (including risk gain coefficient) are... , , Vehicle-side risk gain coefficient ( The parameters (e.g., 1, 2, ..., 5), tire pressure sensitivity index, obstacle size sensitivity index, speed sensitivity index, and orientation sensitivity index, are pre-observed through experimental data fitting or empirical calibration and stored in the cloud scheduling platform. The meteorological function is determined based on real-time meteorological data through a pre-defined mapping relationship (e.g., table lookup). The terrain risk function is determined based on terrain geometry and road surface adhesion coefficient through a pre-defined functional relationship or table lookup.

[0084] Furthermore, the gain coefficient or sensitivity index can be dynamically adjusted during the test based on real-time feedback data or changes in the test scenario to adapt to different test conditions or vehicle states.

[0085] S103. Based on the multi-dimensional risk field model, determine the adjustment strategy for the first task.

[0086] The first task adjustment strategy is used to indicate adjustments to the test route and / or test task.

[0087] Specifically, the cloud platform assesses the real-time risks of the test vehicle in the current test task based on the constructed multi-dimensional risk field model, and determines the first task adjustment strategy that matches the current risk situation based on the output of the multi-dimensional risk field model.

[0088] In one specific implementation, the multi-dimensional risk field model outputs the total risk field strength at the current moment. This total risk field strength characterizes the comprehensive risk level of the test vehicle at its current location, current vehicle state, and current environment. The cloud platform generates corresponding adjustment strategies based on the value of this total risk field strength. For example, when the total risk field strength is low, indicating a low current risk, the cloud platform can generate a first-task adjustment strategy to maintain the original test plan; when the total risk field strength is at a medium level, the cloud platform can generate a strategy to adjust the test route, instructing the test vehicle to avoid high-risk areas; when the total risk field strength is high, the cloud platform can generate a strategy to adjust the test task, such as instructing the test vehicle to decelerate, terminate the current test task, or perform a safe stop. The specific triggering conditions and adjustment range of the first-task adjustment strategy are related to the magnitude of the total risk field strength, and their correspondence can be determined through preset mapping rules or calibration curves.

[0089] In some embodiments, the first task adjustment strategy is generated in the cloud and then sent to the vehicle-side of the test vehicle via a wireless communication network (such as 5G or V2X). After receiving the adjustment strategy, the vehicle-side execution controller parses the instruction content and drives the corresponding actuators (such as the steering system, braking system, and drive system) to perform route adjustment or task change operations.

[0090] It is understood that the vehicle testing method provided in this application, by acquiring multiple risk field parameters to construct a multi-dimensional risk field model and adjusting the vehicle's testing tasks according to the model, achieves a multi-dimensional risk fusion assessment of the test vehicle during the measurement process. This avoids misjudgment of risks due to a single dimension, improves the accuracy of risk assessment, and ensures the safety and efficiency of the testing process. Furthermore, it can better cope with various complex testing scenarios and improve the adaptability of testing tasks.

[0091] Furthermore, such as Figure 4 As shown, S103 can be specifically implemented as the following steps S201-S202: S201. Determine the first risk field strength output by the multi-dimensional risk field model.

[0092] It should be understood that the first risk field strength is data output by the multi-dimensional risk field model, used to quantify the comprehensive risk level faced by the test vehicle at the current moment and location. For example, the first risk field strength can be a dimensionless scalar value; a larger value indicates a higher comprehensive risk level in the current test measurement.

[0093] In some embodiments, the risk field parameters (including test site risk field parameters, vehicle-side risk field parameters, and environmental risk field parameters) obtained at the current time and location of the test vehicle are input into the multi-dimensional risk field model, and the multi-dimensional risk field model calculates and outputs the corresponding risk quantification value in real time as the first risk field strength.

[0094] S202. Based on the comparison between the field strength of the first risk field and the risk threshold, determine the adjustment strategy for the first task.

[0095] In some embodiments, the risk threshold is a preset one or more critical values ​​used to determine the current test risk level. For example, the risk threshold may include one or more different thresholds to divide the risk field strength into multiple levels. This application does not limit the specific value of the risk threshold, and it can be calibrated and adjusted according to the actual conditions of the test site, the performance parameters of the test vehicle, and the safety requirements of the test task in practical applications.

[0096] In some embodiments, a mapping relationship between the comparison results and the task adjustment strategy is preset. The risk threshold divides the risk field strength into multiple threshold intervals, and each threshold interval corresponds to at least one task adjustment strategy. By comparing the first wind vectorization parameter with the risk threshold, it is determined which threshold interval the first risk field strength falls into, and the task adjustment strategy corresponding to the threshold interval is determined according to the preset mapping relationship, and is used as the first task adjustment strategy.

[0097] In some embodiments, the risk threshold includes a first risk threshold and a second risk threshold, wherein the first risk threshold is less than the second risk threshold. Based on the first risk threshold and the second risk threshold, the risk field strength can be divided into three consecutive threshold intervals, each of which corresponds to a different task adjustment strategy.

[0098] Specifically, the first task adjustment strategy satisfies any one of the following three conditions: Scenario 1: If the comparison result shows that the risk field strength is less than the first risk threshold, the first task adjustment strategy is used to instruct the continued execution of the first test task on the first test route.

[0099] It should be understood that if the risk field strength is less than the first risk threshold, it indicates that the current test risk is low and the test is relatively safe, requiring no adjustment. In this case, the first task scheduling strategy is used to instruct the test vehicle to perform the first test task on the current first test route.

[0100] Scenario 2: If the comparison result shows that the risk field strength is greater than or equal to the first risk threshold and less than the second risk threshold, the first task adjustment strategy is used to indicate that the test route is adjusted from the first test route to the second test route.

[0101] It should be understood that if the risk level is greater than or equal to the first risk threshold and less than the second risk threshold, it indicates that there is a potential risk. In this case, the first task adjustment strategy is used to instruct the test route to be adjusted from the first test route to the second test route, so that the test vehicle can avoid the risk area and move to a relatively safe location.

[0102] In some implementations, when the strength of the first risk field is greater than or equal to the first risk threshold but less than the second risk threshold, path replanning is triggered. Starting from the current location of the test vehicle and ending at a preset test endpoint, a second test route with lower risk is replanned within the drivable area. Specifically, when planning the second test route, the vehicle's current location is used as the starting point of the new route. Sections of the first test route that have been safely traversed are retained, and only the remaining sections that have not yet been traversed are replanned. The goal of the replanning is to ensure that the risk field strength at each location on the new route is as low as possible below the first risk threshold. If a route that fully meets this condition cannot be found, the route with the lowest maximum risk field strength along the entire route is selected as the second test route.

[0103] For example, path replanning can be implemented using the A* algorithm or Dijkstra's algorithm, where the cost function of each node includes the risk field strength of that node. The search process starts from the current position of the test vehicle and ends at the test endpoint, and the final output optimal path is the second test route.

[0104] Scenario 3: If the comparison result shows that the risk field strength is greater than or equal to the second risk threshold, the first task adjustment strategy is used to instruct the test vehicle to switch from the first test task to performing the second test task.

[0105] It should be understood that if the risk level is greater than or equal to the second risk threshold, it indicates a high current risk. In this case, continuing the first test task would lead to loss of vehicle control or a collision. Therefore, the first test task needs to be terminated immediately, and the test should be switched to the second test task, which has a lower risk level, to ensure test safety. The first task adjustment strategy is used to instruct the test vehicle to switch from the first test task to the second test task.

[0106] The first test task is a high-risk test task (such as high-speed lane change test, emergency braking test), and the second test task is a low-risk test task (such as low-speed straight driving test, vehicle standby).

[0107] In some implementations, when the risk level is greater than or equal to a second risk threshold, the test vehicle exits the currently executing first test task and clears the task control parameters associated with the first test task. Next, the test vehicle loads the task control parameters corresponding to the second test task, which may include, for example, the target speed, desired path, and maximum permissible lateral acceleration. Finally, the test vehicle travels according to the loaded task control parameters for the second test task and begins executing the second test task.

[0108] To achieve a complete risk assessment and task adjustment during the testing process, the risks of the test vehicle continue to be acquired in real time while the test vehicle is performing the second test task. Specifically, such as... Figure 5 As shown, the vehicle testing method also includes the following steps: S401. During the second test mission performed by the test vehicle, determine the second risk field strength of the test vehicle.

[0109] It should be noted that the second risk field strength has the same physical meaning as the aforementioned first risk field strength; both are used to quantify the overall risk level of the test vehicle at the current moment and location. The second risk field strength and the first risk field strength are only used to distinguish the risk field strengths determined by the test vehicle at different times or under different test tasks.

[0110] In some embodiments, the determination of the second risk field strength is the same as the determination of the first risk field strength in step S201. Specifically, the cloud continuously receives the vehicle-side risk field parameters and environmental risk field parameters uploaded by the test vehicle, and combines them with the test site risk field parameters stored locally in the cloud to calculate the second risk field strength in real time according to the same multi-dimensional risk field model. For example, during the execution of the second test task by the test vehicle, the cloud continuously calculates the risk value at the current moment, which is the second risk field strength.

[0111] S402. If the field strength of the second risk field is greater than or equal to the second risk threshold, determine the second task adjustment strategy.

[0112] Specifically, the field strength of the second risk field determined above is compared with the second risk threshold. If the field strength of the second risk field is greater than or equal to the second risk threshold, it indicates that the test vehicle still faces a high safety risk after switching to the second test mission and further adjustments are required. At this time, it is necessary to determine the adjustment strategy for the second mission.

[0113] This application embodiment further provides the specific details of the second task adjustment strategy.

[0114] Specifically, the second task adjustment strategy is used to instruct any of the following: a. Instruction to change the test route from the second test route to the third test route.

[0115] In some embodiments, if the second risk field strength remains greater than or equal to the second risk threshold during the execution of the second test task, it indicates that the currently adjusted second test route still carries a high risk and requires further optimization. In this case, the second task adjustment strategy instructs the test route to be adjusted from the current second test route to a third test route. Similar to the path replanning method in the aforementioned scenario two, the cloud performs path replanning with the current location of the test vehicle as the starting point and a preset test endpoint as the endpoint. The goal of the replanning is to make the risk field strength at each location on the new route as low as possible below the second risk threshold. If a route that fully meets this condition cannot be found, the route with the smallest maximum risk field strength along the entire route is selected as the third test route. For example, path replanning can be implemented using the A* algorithm or Dijkstra's algorithm.

[0116] b. Instruct the test vehicle to change from the second test mission to perform the third test mission.

[0117] The third test task is a pre-set low-risk test task.

[0118] In some embodiments, if adjusting the test route still cannot effectively reduce the risk, it is necessary to further reduce the risk level of the test task. In this case, a second task adjustment strategy is used to instruct the test vehicle to switch from the second test task to a third test task with a lower risk level. Specifically, the cloud-controlled test vehicle exits the second test task, loads the task control parameters corresponding to the third test task, and begins executing the third test task.

[0119] c. Instruct the test vehicle to stop in the preset emergency avoidance zone.

[0120] The preset safety zone is a pre-defined safe area within the test site. For example, the preset safety zone may include: an emergency parking lane, a buffer zone, a maintenance area entrance, the end of an open straight road, or a specially designated safety island within the test site.

[0121] In some embodiments, the high-precision map of the test site pre-marks the location information and attributes (such as area, entrance coordinates, maximum number of vehicles) of one or more emergency avoidance zones. When emergency avoidance parking is required, the cloud selects the one or more emergency avoidance zones closest to the current test vehicle as the target emergency avoidance zone and plans the driving route.

[0122] In some embodiments, the adjustment strategies described in a, b, and c above are executed sequentially according to a preset priority order: first, a is executed; if the risk field strength is still greater than or equal to the second risk threshold after adjusting the route, then b is executed; if the risk field strength is still greater than or equal to the second risk threshold after switching tasks, then c is executed finally to control the test vehicle to stop in the preset danger zone.

[0123] In actual testing, as the testing mission progresses, the completed test mileage of the test vehicle continuously increases. Cumulative wear, aging, or performance degradation may occur in various vehicle components, leading to changes in the vehicle's dynamic response characteristics and safety boundaries. If a fixed risk threshold is consistently used for risk assessment, it may fail to accurately reflect the vehicle's actual risk tolerance under its current condition, resulting in premature intervention or delayed response. Therefore, this application proposes dynamically adjusting the risk threshold. Specifically, as... Figure 6 As shown, before S202, the method further includes the following steps S501-S502: S501. Obtain the completed test mileage and vehicle health status information of the test vehicle.

[0124] The completed test mileage refers to the cumulative distance traveled by the test vehicle since the start of this test, which can be read through the test vehicle's mileage sensor or CAN bus.

[0125] In some embodiments, vehicle health status information is a set of characteristic parameters used to characterize the health status of the test vehicle. Exemplarily, vehicle health status information may include, but is not limited to: tire wear, vehicle battery state of health (SOH), brake system wear, and fault code records for various critical components. Vehicle health status parameters can be obtained through an on-board diagnostic (OBD) system, CAN bus, or the self-test modules of each component.

[0126] To obtain vehicle health status information during testing, health baseline values ​​are pre-set for each characteristic parameter in the vehicle health status information before the test begins. These baseline values ​​can be determined based on the factory calibration values ​​or experimental statistical values ​​of the characteristic parameters. During testing, real-time data on each characteristic parameter of the test vehicle is acquired, and the deviation of each parameter from its corresponding health baseline value is calculated to obtain the vehicle health status information.

[0127] S502. Determine the risk threshold based on the completed test mileage and vehicle health status information of the test vehicle.

[0128] It should be understood that as the testing progresses, the initial risk threshold needs to be dynamically adjusted to ensure the accuracy of the risk testing results.

[0129] In some embodiments, after acquiring vehicle health status information, a preset fusion algorithm is used to synthesize the vehicle health status information into an overall health index, wherein a higher value or better level of the overall health index indicates a better health status of the test vehicle. For example, the fusion algorithm is used to map individual deviations across multiple dimensions into a quantitative index representing the overall health status. Specifically, the fusion algorithm can employ any of the following: weighted summation, product fusion, taking the maximum or minimum value, rule-based fusion based on fuzzy logic, or data-driven fusion based on a machine learning model.

[0130] Furthermore, the risk threshold is dynamically adjusted based on the completed test mileage and overall health indicators. Generally, the risk threshold is negatively correlated with the completed test mileage; that is, as the completed test mileage increases, the risk threshold decreases accordingly. Simultaneously, the risk threshold is also positively correlated with the overall health indicators; that is, the risk threshold can be maintained at a higher level when health is better, and decreases accordingly when health declines. Specifically, the risk threshold can be determined based on the completed test mileage and overall health indicators through a preset function or lookup table.

[0131] In a specific example, the risk threshold can be calculated using the following formula: , in, The current moment; This indicates the real-time risk threshold. The values ​​are 0 and 1, corresponding to the first risk threshold and the second risk threshold, respectively. This is the initial value for the risk threshold; This is the mileage gain coefficient; This represents the completed test mileage; To test the total mileage; The vehicle health status function outputs the overall health index value mentioned above, which is used to characterize the impact of the vehicle's current health status on the risk threshold.

[0132] In some embodiments, the risk threshold is negatively correlated with the completed test mileage. That is, as the completed mileage of the test vehicle increases, the risk threshold used to determine the task adjustment strategy decreases accordingly. Specifically, the risk threshold is determined based on the completed test mileage using a preset step function, a linear decreasing function, or a lookup table.

[0133] In some embodiments, considering that the health status of the test vehicle (such as powertrain degradation, braking system wear, sensor aging, etc.) may change during long-term or high-intensity testing, thereby affecting the authenticity and accuracy of the vehicle-side risk field parameters, this application provides a possible implementation method that, without introducing test mileage to correct the risk threshold, dynamically corrects the vehicle-side risk field parameters based on the vehicle health status information to improve the accuracy of the multi-dimensional risk field model.

[0134] Specifically, such as Figure 7 As shown, S102 can also be implemented as follows: S601. Obtain the vehicle health status information of the test vehicle.

[0135] The process of obtaining the vehicle health status information of the test vehicle is described in S501 and will not be repeated here.

[0136] S602. Based on the vehicle health status information, the vehicle-side risk field parameters are corrected to obtain the corrected vehicle-side risk field parameters.

[0137] It should be understood that vehicle health status information comes from the vehicle's own data. Therefore, changes in vehicle health status information are related to changes in vehicle-side risk field parameters. The vehicle-side risk field parameters can be corrected based on the health status information to obtain the corrected vehicle-side risk field parameters.

[0138] In some embodiments, the correction method for the vehicle-end risk field parameters is determined based on vehicle health status information. The correction method includes, but is not limited to: multiplying the vehicle-end risk field parameters by a weighting coefficient determined based on vehicle health status information; or superimposing a correction amount determined based on vehicle health status information onto the vehicle-end risk field parameters; or inputting both vehicle health status information and vehicle-end risk field parameters into a preset correction model to obtain the corrected vehicle-end risk field parameters. The above correction methods can be determined through pre-analysis and experimental calibration. This application does not limit the specific form of the correction method, as long as it can correct the vehicle-end risk field parameters based on vehicle health status information to reduce deviation.

[0139] S603. Based on the corrected vehicle-side risk field parameters, test site risk field parameters, and environmental risk field parameters, construct a multi-dimensional risk field model for the test vehicle.

[0140] Specifically, a multi-dimensional risk field model of the test vehicle is constructed based on the corrected vehicle-side risk field parameters, satisfying the following relationship: , in, This indicates the field strength of the risk field output by the multidimensional risk model; The risk field strength is determined based on the risk field parameters of the test site; The risk field strength is determined based on the corrected vehicle-end risk field parameters; The risk field strength is determined based on environmental risk field parameters.

[0141] The process of a vehicle testing method is described below through an example. Figure 8 As shown, it includes the following steps: S1. Obtain the risk field parameters of the test vehicle.

[0142] S2. Based on the risk field parameters of the test vehicle, construct a multi-dimensional risk field model of the test vehicle.

[0143] S3. Determine the first risk field strength of the test vehicle based on the multi-dimensional risk field model.

[0144] S4. Compare the field strength of the first risk field with the risk threshold, and determine the adjustment strategy for the first task based on the comparison results.

[0145] Based on the comparison results of S4, execute S5a, S5b, or S5c respectively: S5a. If the comparison result shows that the field strength of the first risk field is less than the first risk threshold, the first task adjustment strategy is used to instruct the continued execution of the first test task on the first test route.

[0146] S5b. If the comparison result shows that the strength of the first risk field is greater than or equal to the first risk threshold and less than the second risk threshold, the first task adjustment strategy is used to indicate that the test route is adjusted from the first test route to the second test route.

[0147] S5c, If the comparison result shows that the first risk field is stronger than the second risk threshold, the first task adjustment strategy is used to instruct the test vehicle to switch from the first test task to the second test task.

[0148] S6. During the execution of the second test mission, determine the second risk field strength of the test vehicle.

[0149] S7. If the strength of the second risk field is greater than or equal to the second risk threshold, determine the second task adjustment strategy.

[0150] The second task adjustment strategy and related execution logic are described in S401-S402 and will not be repeated here.

[0151] S8. Determine whether the test is complete.

[0152] In some embodiments, the test can be considered complete once all test tasks are completed.

[0153] If yes, the current test process ends; otherwise, return to S1 to continue execution, thus achieving a closed loop.

[0154] As can be seen, the above mainly describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the above functions, the embodiments of this application provide corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the modules and algorithm steps of the various examples described in the embodiments disclosed herein, the embodiments of this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware 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.

[0155] This application embodiment can divide the vehicle testing device into functional modules according to the above method example. For example, each function can be divided into its own functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. Optionally, the module division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0156] Figure 9 This is a schematic diagram of a vehicle testing device provided in an embodiment of this application, used to implement the vehicle testing method provided in the above embodiments, such as... Figure 9 As shown, the vehicle testing device 600 includes an acquisition unit 601 and a processing unit 602. The acquisition unit 601 is used to acquire risk field parameters of the test vehicle during the execution of a first test task. The risk field parameters include test site risk field parameters, vehicle-end risk field parameters, and environmental risk field parameters. The processing unit 602 constructs a multi-dimensional risk field model of the test vehicle based on the risk field parameters of the test vehicle. Based on the multi-dimensional risk field model, it determines a first task adjustment strategy, which is used to indicate the adjustment of the test route and / or test task.

[0157] In some embodiments, the processing unit 602 is specifically used to determine the first risk field strength output by the multi-dimensional risk field model; and to determine a first task adjustment strategy based on the comparison result between the first risk field strength and the risk threshold.

[0158] In some embodiments, the risk threshold includes a first risk threshold and a second risk threshold, and the first task adjustment strategy satisfies any one of the following: if the comparison result shows that the field strength of the first risk field is less than the first risk threshold, the first task adjustment strategy is used to instruct the continued execution of the first test task on the first test route; if the comparison result shows that the field strength of the first risk field is greater than or equal to the first risk threshold and less than the second risk threshold, the first task adjustment strategy is used to instruct the test route to be adjusted from the first test route to the second test route; if the comparison result shows that the field strength of the first risk field is greater than the second risk threshold, the first task adjustment strategy is used to instruct the test vehicle to be adjusted from the first test task to perform the second test task.

[0159] In some embodiments, the processing unit 602 is further configured to determine the second risk field strength of the test vehicle during the execution of the second test task; and to determine a second task adjustment strategy if the second risk field strength is greater than or equal to a second risk threshold.

[0160] In some embodiments, the second task adjustment strategy is used to instruct any of the following: instructing the test route to be adjusted from the second test route to the third test route; instructing the test vehicle to be adjusted from the second test task to perform the third test task; wherein the third test task is a preset low-risk test task; instructing the test vehicle to stop in a preset avoidance zone.

[0161] In some embodiments, before determining the first task adjustment strategy based on the comparison result between the first risk field strength and the risk threshold, the acquisition unit 601 is further configured to acquire the completed test mileage and vehicle health status information of the test vehicle; the processing unit 602 is further configured to determine the risk threshold based on the completed test mileage and vehicle health status information of the test vehicle.

[0162] In some embodiments, the risk threshold is negatively correlated with the mileage of completed testing.

[0163] In some embodiments, the processing unit 602 is specifically used to acquire vehicle health status information of the test vehicle; correct the vehicle-side risk field parameters based on the vehicle health status information to obtain corrected vehicle-side risk field parameters; and construct a multi-dimensional risk field model of the test vehicle based on the corrected vehicle-side risk field parameters, test site risk field parameters, and environmental risk field parameters.

[0164] In the case where the functions of the integrated modules described above are implemented in hardware, this application provides a possible structural schematic diagram of the electronic device involved in the above embodiments. For example... Figure 10 As shown, the electronic device 700 includes: a processor 702, a communication interface 703, and a bus 704. Optionally, the electronic device 700 may also include a memory 701.

[0165] Processor 702 may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 702 may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 702 may also be a combination that implements computing functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0166] The communication interface 703 is used to connect to other devices via a communication network. This communication network can be Ethernet, wireless access network, wireless local area network (WLAN), etc.

[0167] The memory 701 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0168] As one possible implementation, the memory 701 can exist independently of the processor 702. The memory 701 can be connected to the processor 702 via a bus 704 and is used to store instructions or program code. When the processor 702 calls and executes the instructions or program code stored in the memory 701, it can implement the vehicle testing method provided in the embodiments of this application.

[0169] In another possible implementation, the memory 701 can also be integrated with the processor 702.

[0170] The 704 bus can be an extended industry standard architecture (EISA) bus, etc. The 704 bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 10 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0171] Through the above description of the implementation methods, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the service calling device can be divided into different functional modules to complete all or part of the functions described above.

[0172] This application also provides a computer-readable storage medium. All or part of the processes in the above method embodiments can be instructed by computer program instructions to related hardware to perform the process. This program can be stored in the aforementioned computer-readable storage medium. When executed on a computer, the computer program instructions cause the computer to perform the vehicle testing method as described in any of the above embodiments.

[0173] Exemplary examples of computer-readable storage media may include, but are not limited to: magnetic storage devices (e.g., hard disks, floppy disks, or magnetic tapes), optical discs (e.g., compact disks (CDs), digital versatile disks (DVDs), etc.), smart cards, and flash memory devices (e.g., erasable programmable read-only memory (EPROMs), cards, sticks, or key drives, etc.). The various computer-readable storage media described in this disclosure may represent one or more devices and / or other machine-readable storage media for storing information. The term "machine-readable storage medium" may include, but is not limited to, wireless channels and various other media capable of storing, containing, and / or carrying instructions and / or data.

[0174] This application also provides a computer program product comprising a computer program that, when run on a computer, causes the computer to perform any of the vehicle testing methods provided in the above embodiments.

[0175] In the description of the embodiments of this application, specific features, structures, materials or characteristics may be combined in any suitable manner in one or more embodiments or examples.

[0176] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A vehicle testing method, characterized in that, The method includes: During the execution of the first test task by the test vehicle, the risk field parameters of the test vehicle are acquired. The risk field parameters include test site risk field parameters, vehicle-end risk field parameters, and environmental risk field parameters. Based on the risk field parameters of the test vehicle, a multi-dimensional risk field model of the test vehicle is constructed. Determine the first risk field strength output by the multi-dimensional risk field model; determine a first task adjustment strategy based on the comparison between the first risk field strength and the risk threshold, wherein the risk threshold includes a first risk threshold and a second risk threshold, and the first task adjustment strategy is used to indicate the adjustment of the test route and / or test task; If the comparison result shows that the strength of the first risk field is greater than or equal to the first risk threshold and less than the second risk threshold, the first task adjustment strategy is used to instruct the replanning of the second test route within the drivable area, starting from the current position of the test vehicle and ending at a preset test endpoint. When replanning the second test route, sections of the first test route that have been safely traversed are retained, and only the remaining sections that have not yet been traversed are replanned. The goal of the replanning is to ensure that the strength of the risk field at each location on the second test route is lower than the first risk threshold. If a route that fully meets this condition cannot be found, the route with the smallest maximum risk field strength along the entire route is selected as the second test route.

2. The method according to claim 1, characterized in that, If the comparison result shows that the field strength of the first risk field is less than the first risk threshold, the first task adjustment strategy is used to instruct the first test task to continue to be executed on the first test route. If the comparison result shows that the first risk field is stronger than the second risk threshold, the first task adjustment strategy is used to instruct the test vehicle to switch from the first test task to performing the second test task.

3. The method according to claim 2, characterized in that, The method further includes: During the process of the test vehicle performing the second test task, the second risk field strength of the test vehicle is determined; If the second risk field strength is greater than or equal to the second risk threshold, a second task adjustment strategy is determined.

4. The method according to claim 3, characterized in that, The second task adjustment strategy is used to instruct any of the following: The instruction is to change the test route from the second test route to the third test route; The test vehicle is instructed to switch from the second test task to the third test task; wherein the third test task is a preset low-risk test task. The test vehicle was instructed to stop in a pre-defined safe zone.

5. The method according to any one of claims 2-4, characterized in that, Before determining the first task adjustment strategy based on the comparison result between the first risk field strength and the risk threshold, the method further includes: Obtain the completed test mileage and vehicle health status information of the test vehicle; The risk threshold is determined based on the completed test mileage and vehicle health status information of the test vehicle.

6. The method according to claim 5, characterized in that, The risk threshold is negatively correlated with the completed test mileage.

7. The method according to claim 1, characterized in that, The step of constructing a multi-dimensional risk field model of the test vehicle based on the risk field parameters of the test vehicle includes: Obtain the vehicle health status information of the test vehicle; Based on the vehicle health status information, the vehicle-side risk field parameters are corrected to obtain the corrected vehicle-side risk field parameters. Based on the corrected vehicle-side risk field parameters, the test site risk field parameters, and the environmental risk field parameters, a multi-dimensional risk field model of the test vehicle is constructed.

8. An electronic device, characterized in that, The electrons include: Processor and memory; The memory stores processor-executable instructions; when the processor is configured to execute the instructions, the electronic device performs the method of any one of claims 1-7.

9. A vehicle, characterized in that, The vehicle includes the electronic device of claim 8, which enables the vehicle to perform the method of any one of claims 1-7.

Images