Commercial vehicle right turning test method based on in-the-loop simulation

Abstract

The invention relates to the technical field of automobile testing, in particular to a commercial vehicle right turning testing method based on in-the-loop simulation. And according to a scene generation module, generating commercial vehicle right turning test scene data with a scene risk level. And constructing a commercial vehicle right turning test scene in the simulation software. And converting the commercial vehicle right turning test scene into video stream data and point cloud data, sending the video stream data and the point cloud data to the test vehicle and the head display device, and determining physiological data collected by the driver physical and mental monitoring system. And executing a commercial vehicle right turning test operation corresponding to the scene risk level. And according to the acquired vehicle data, the physiological data, the commercial vehicle right turning test scene data and the risk quantification model, determining a collision risk coefficient of the commercial vehicle right turning test. According to the method, the quantification precision of the collision risk of the traffic participants in the right-turning inner wheel difference blind area of the commercial vehicle can be improved.

Description

Technical Field

[0001] This specification relates to the field of automotive testing technology, and in particular to a commercial vehicle right-turn testing method based on in-loop simulation. Background Technology

[0002] Currently, with the rapid development of intelligent connected vehicles in China, policies, regulations, and safety technical standards are placing higher demands on the active safety performance of vehicles. In the commercial vehicle sector, the risk of accidents during right turns is particularly prominent due to the large blind spot caused by the inner wheel difference. Therefore, research on right-turn testing technology for commercial vehicles is of great significance for improving public road traffic safety and optimizing the functions of intelligent driving systems.

[0003] However, existing passenger vehicle turning test methods have significant shortcomings in assessing risks such as pedestrian intrusion in traffic scenarios, and the assessment results are often inaccurate and incomplete. In particular, there is a lack of effective risk quantification methods and risk avoidance strategies in right turn testing.

[0004] Therefore, this specification provides a test method for right turns of commercial vehicles based on in-loop simulation. Summary of the Invention

[0005] This specification provides a commercial vehicle right-turn testing method based on in-loop simulation, in order to partially solve the aforementioned problems existing in the prior art.

[0006] The following technical solution is adopted in this specification: This specification provides a commercial vehicle right-turn testing method based on in-loop simulation, including: S1. Generate test scenario data for commercial vehicles turning right based on the preset scenario generation module; S2. Based on the commercial vehicle right-turn test scenario data, construct a commercial vehicle right-turn test scenario in simulation software, the commercial vehicle right-turn test scenario including the test vehicle and the target object expected to collide with the test vehicle; and convert the commercial vehicle right-turn test scenario into video stream data and point cloud data; S3. The point cloud data is sent to the test vehicle; and the video stream data is simultaneously sent to the head-mounted display device worn by the test personnel in the test vehicle, so that the head-mounted display device displays the commercial vehicle right turn test scenario to the test personnel; the physiological data of the test personnel collected by the driver's physical and mental monitoring system connected to the test personnel is collected and determined; S4. Based on the commercial vehicle right turn test scenario data and the physiological data, as well as the preset risk quantification model, determine the risk coefficient of the commercial vehicle right turn test; S5. Based on the risk coefficient and the point cloud data, conduct the right turn test for the commercial vehicle; S6. Feed back the vehicle data during the commercial vehicle right turn test to the simulation software, and update the commercial vehicle right turn test scenario in the simulation software based on the fed-back vehicle data. S7. Convert the updated commercial vehicle right-turn test scenario data into point cloud data and video stream data.

[0007] S8. Repeat steps S3-S7 until the commercial vehicle right turn test is completed.

[0008] Based on the aforementioned technical means, this solution simulates collision scenarios in simulation software using virtual targets. Testers see the "danger" in the head-mounted display, but the actual vehicle (i.e., the test vehicle) does not actually face a collision. However, the collision risk coefficient calculated based on the simulated virtual collision scenario significantly improves the quantitative accuracy of collision risk assessment for traffic participants in the blind spot of the inner wheel difference when a commercial vehicle is turning right. At the same time, the solution introduces driver (i.e., test personnel) state parameters and threat parameters for joint decision-making, achieving comprehensive calculation of the collision risk coefficient and more accurately reflecting the risk boundary of the right-turn test process.

[0009] Furthermore, the driver's physical and mental monitoring system includes a heart rate monitor, an eye tracker, an electroencephalogram (EEG) sensor, and a skin conductance sensor. The physiological data in S3 include: The heart rate of the test subject is collected by the heart rate monitor, the eye pressure coefficient of the test subject is collected by the eye tracker, the electroencephalogram (EEG) signal of the test subject is collected by the EEG sensor, and the skin conductance signal is collected by the skin conductance sensor.

[0010] Based on the aforementioned technical means, by monitoring heart rate, eye pressure coefficient, electroencephalogram (EEG) signals, and electrodermal signals, the system can monitor the condition of test personnel during right-turn tests of commercial vehicles, conduct a comprehensive assessment of their physical condition, and provide early warnings when their physical condition is poor, even if no driving hazard occurs. This system can capture the state of test personnel who appear normal but are already overloaded, thereby improving the scientific rigor and sensitivity of the risk quantification model.

[0011] Furthermore, the expression for the risk quantification model is:

[0012] Among them, the The collision risk coefficient is mentioned above; For trajectory conflict time; Equivalent headway; The threat parameters of the target object to the test vehicle are quantified; For the tester's status parameters; , , These are the preset weights for the trajectory conflict time, the equivalent headway, and the threat parameter, respectively.

[0013] Furthermore, the commercial vehicle right turn test scenario data includes the distance vector at the expected collision point between the test vehicle and the target object at the current moment, the distance vector at the expected collision point between the target object and the test vehicle, the speed of the target object, and the speed direction of the target object; the vehicle data includes the speed of the test vehicle and the speed direction of the test vehicle. The expression for calculating the trajectory conflict time is:

[0014] in, The time of the trajectory conflict; for The distance vector at the expected collision point between the test vehicle and the target object at any given moment; for The distance vector between the target object and the expected collision point of the test vehicle at any given moment; This is a preset constant; Let V be the relative velocity vector between the test vehicle and the target object; Let be the unit vector pointing from the test vehicle to the target object; The angle between the velocity direction of the test vehicle and the velocity direction of the target object.

[0015] Furthermore, the commercial vehicle right turn test scenario data includes the distance between the target object and the expected collision point of the test vehicle at the current moment, and the speed of the target object; The expression for calculating the equivalent headway is:

[0016] in, The equivalent headway; The distance between the target object and the expected point of collision between the test vehicle; The velocity of the target object is given.

[0017] Furthermore, the commercial vehicle right-turn test scenario data includes the right-turn radius of the test vehicle at the current moment, the vehicle width, and the position of the target object; the vehicle data includes the test vehicle speed and the test vehicle position. The expression for calculating the threat parameter is:

[0018]

[0019] in, The threat parameter; The safety domain of the test vehicle; The distance between the position of the test vehicle and the position of the target object; Let be the right-turn radius of the test vehicle; The speed of the test vehicle; The preset communication delay; The width of the test vehicle; These are preset environmental uncertainty compensation parameters; These are the preset blind spot risk compensation parameters.

[0020] Furthermore, the expression for calculating the tester's state parameters is as follows:

[0021] in, The tester's status parameters; (i∈(1,2,3,4)) is one of the heart rate, the eye pressure coefficient, the electroencephalogram (EEG) signal, and the electrodermal signal; for The corresponding normal value; for The corresponding standard deviation.

[0022] This specification provides a commercial vehicle right-turn testing device based on in-loop simulation, including: The generation module is used to generate test scenario data for right turns of commercial vehicles with scenario risk levels based on the preset scenario generation module. The simulation module is used to construct a right-turn test scenario for commercial vehicles in simulation software based on the right-turn test scenario data of the commercial vehicles. The right-turn test scenario for commercial vehicles includes the test vehicle and the target object that is expected to collide with the test vehicle. The module also converts the right-turn test scenario for commercial vehicles into video stream data and point cloud data. The sending module is used to send the video stream data and the point cloud data to the test vehicle; and simultaneously send the video stream data to the head-mounted display device worn by the test personnel in the test vehicle, so that the head-mounted display device displays the commercial vehicle right turn test scenario to the test personnel; The execution module is used to perform a right-turn test operation for commercial vehicles corresponding to the risk level of the scenario; and to collect physiological data of the test personnel collected by the driver's physical and mental monitoring system connected to the test personnel; and to receive vehicle data of the test vehicle during the right-turn test operation for commercial vehicles. The determination module is used to determine the collision risk coefficient of the commercial vehicle right turn test based on the vehicle data, the physiological data, and the commercial vehicle right turn test scenario data, and a preset risk quantification model. The update module is used to update the commercial vehicle right turn test scenario in the simulation software based on the vehicle data. The conversion module is used to convert the updated commercial vehicle right-turn test scenario data into point cloud data and video stream data. Continue testing the module to repeat steps S3-S7 until the commercial vehicle right turn test is completed.

[0023] This specification provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned method for testing right turns of commercial vehicles based on in-loop simulation.

[0024] This specification provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement a commercial vehicle right-turn test method based on in-loop simulation.

[0025] The above-mentioned technical solutions adopted in this specification can achieve the following beneficial effects: This solution simulates collision scenarios in simulation software using virtual targets. Testers see the "danger" in the head-mounted display, but the actual vehicle (i.e., the test vehicle) does not actually face a collision. However, the collision risk coefficient is calculated based on the simulated virtual collision scenario, which significantly improves the quantitative accuracy of collision risk assessment for traffic participants in the inner wheel difference blind spot of commercial vehicles when turning right. At the same time, the solution introduces driver (i.e., test personnel) state parameters and threat parameters for joint decision-making, realizing a comprehensive calculation of the collision risk coefficient, which more accurately reflects the risk boundary of the right turn test process. Attached Figure Description

[0026] The accompanying drawings, which are included to provide a further understanding of this specification and form part of this specification, illustrate exemplary embodiments and are used to explain this specification, but do not constitute an undue limitation thereof. In the drawings: Figure 1 A flowchart illustrating a commercial vehicle right-turn testing method based on in-loop simulation provided in this specification. Figure 2 A schematic diagram of a commercial vehicle right-turn test device based on in-loop simulation provided in this specification; Figure 3 This specification provides a corresponding Figure 1 A schematic diagram of the structure of an electronic device. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of this specification clearer, the technical solutions of this specification will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments in this specification without creative effort are within the scope of protection of this application.

[0028] 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.

[0029] The technical solutions provided in the various embodiments of this specification are described in detail below with reference to the accompanying drawings.

[0030] Figure 1 A flowchart illustrating a commercial vehicle right-turn testing method based on in-loop simulation, provided for embodiments of this specification, includes the following steps: S1: Generate test scenario data for right turns of commercial vehicles with scenario risk levels based on the preset scenario generation module.

[0031] This specification describes the process of conducting a right-turn test for commercial vehicles based on in-the-loop simulation. In the embodiments described herein, this right-turn test can be executed by a server. However, this specification does not limit the type of device or platform used to perform the right-turn test; devices or platforms such as personal computers, mobile terminals, edge computing devices, and cloud computing devices can also be used. For ease of description, the following description uses a server as the execution entity.

[0032] In one or more embodiments of this specification, the server can generate commercial vehicle right-turn test scenario data with scenario risk levels according to a preset scenario generation module.

[0033] The scenario generation module decomposes the data corresponding to various elements involved in the commercial vehicle right-turn test scenario, such as the commercial vehicle model, target object model, road, and weather, into multi-dimensional structured feature vectors. Then, through a pre-trained generative model built into the scenario generation module, these multi-dimensional structured feature vectors are randomly combined to automatically generate various commercial vehicle right-turn test scenario data, including high-risk extreme long-tail scenarios, low-risk, and even risk-free conventional scenarios. Therefore, when generating commercial vehicle right-turn test scenario data using the scenario generation module, one or more scenarios can be randomly selected from the generated data for commercial vehicle right-turn testing. The scenario risk level of the commercial vehicle right-turn test scenario data is determined based on whether it falls under the categories of high-risk extreme long-tail scenarios, low-risk, or even risk-free conventional scenarios. This manual does not impose any restrictions on the setting of scenario risk levels. You can set them according to the actual situation. For example, you can set them to levels 1 to 3. High-risk extreme long-tail scenarios are level 3, low-risk scenarios are level 2, and risk-free normal scenarios are level 1.

[0034] S2: Based on the commercial vehicle right-turn test scenario data, construct a commercial vehicle right-turn test scenario in simulation software. The commercial vehicle right-turn test scenario includes the test vehicle and the target object expected to collide with the test vehicle. Convert the commercial vehicle right-turn test scenario into video stream data and point cloud data.

[0035] In one or more embodiments of this specification, the server constructs a commercial vehicle right-turn test scenario in simulation software based on commercial vehicle right-turn test scenario data. This constructed commercial vehicle right-turn test scenario includes a test vehicle (i.e., a vehicle making a right turn) and a target object that is expected to collide with the test vehicle. The target object expected to collide with the test vehicle refers to a target object with a fixed speed and direction of travel, arranged when the commercial vehicle right-turn test scenario is generated during the right-turn test. This target object, traveling at a fixed speed and direction of travel, will collide with the test vehicle performing the right-turn test at a certain future moment. Therefore, it can be seen that when the commercial vehicle right-turn test scenario is generated and simulated, information including the speed and direction of travel of the test vehicle and the target object at that moment, the distance between them, and the expected collision location, can be directly determined.

[0036] At the same time, the server will also convert the commercial vehicle right turn test scenario into video stream data and point cloud data.

[0037] S3: Send the video stream data and the point cloud data to the test vehicle; and simultaneously send the video stream data to the head-mounted display device worn by the test personnel in the test vehicle, so that the head-mounted display device displays the commercial vehicle right turn test scenario to the test personnel.

[0038] In one or more embodiments of this specification, although the right-turn test scenario for commercial vehicles is simulated in simulation software, the actual test vehicle in the test field (the actual test vehicle described herein is not the test vehicle simulated in the simulation software) is not in an actual right-turn test scenario with a collision risk. The actual test vehicle can conduct the right-turn test in an open field with no objects around it.

[0039] Therefore, in order to enable the actual test vehicle to "perceive" the right-turn test scenario of the commercial vehicle, the server sends the video stream data and point cloud data of the right-turn test scenario to the test vehicle. This allows the test vehicle to perceive the right-turn test scenario even though it cannot actually perceive the right-turn test scenario. The received point cloud data and video stream data are processed by the domain controller or actuator on the test vehicle to achieve the effect of perceiving the right-turn test scenario. This allows the test vehicle's domain controller or driver assistance system, or the test personnel to perform the right-turn test accordingly.

[0040] Furthermore, the server also sends the video stream data of the commercial vehicle right-turn test scenario to the head-mounted display worn by the test personnel. The head-mounted display can render the video stream data into virtual reality (VR) images to display the commercial vehicle right-turn test scenario to the test personnel. In this case, the test personnel can also "perceive" the right-turn test scenario and thus make driving operations. Of course, if the right-turn test is automatically performed by the test vehicle's driver assistance system or domain control, the test personnel do not need to make driving operations. The test personnel only need to take over the test vehicle when they "perceive" a problem with the driver assistance system's driving operation. It is worth noting that this head-mounted display can be a mixed reality (MR) head-mounted display.

[0041] S4: Perform the commercial vehicle right turn test operation corresponding to the scenario risk level; collect the physiological data of the test personnel collected by the driver physical and mental monitoring system connected to the test personnel; and receive the vehicle data of the test vehicle in the commercial vehicle right turn test operation.

[0042] In one or more embodiments of this specification, the test vehicle performs a right turn test operation corresponding to the risk level of the scenario. Simultaneously, the tester is connected to a driver physical and mental monitoring system. The server can collect and determine the physiological data of the tester collected by the driver physical and mental monitoring system connected to the tester. The driver physical and mental monitoring system includes a heart rate monitor, an eye tracker, an electroencephalogram (EEG) sensor, and a skin conductance sensor. Therefore, the physiological data collected by the driver physical and mental monitoring system includes the tester's heart rate collected by the heart rate monitor, the tester's eye pressure coefficient collected by the eye tracker, the tester's electroencephalogram (EEG) signals collected by the EEG sensor, and the skin conductance signals collected by the skin conductance sensor.

[0043] Furthermore, the server can receive vehicle data generated by the test vehicle during the right turn test of a commercial vehicle. This vehicle data can be data such as the speed of the test vehicle generated by the operation of the steering wheel, brake / accelerator pedal, gear, buttons, etc. by the determined test personnel or the driver assistance system, or the position of the test vehicle recorded by the positioning module (such as GPS) on the test vehicle.

[0044] S5. Based on the vehicle data, the physiological data, and the commercial vehicle right turn test scenario data, determine the collision risk coefficient for the commercial vehicle right turn test based on a preset risk quantification model.

[0045] In one or more embodiments of this specification, server vehicle data, physiological data, and commercial vehicle right-turn test scenario data are used to determine the collision risk coefficient of the commercial vehicle right-turn test based on a preset risk quantification model.

[0046] Specifically, the expression for the risk quantification model is:

[0047] in, This represents the collision risk factor. This refers to the time of trajectory conflict. This is the equivalent headway. This refers to the quantified threat parameters of the target object to the test vehicle. These are the status parameters for the testers. , , These are the preset weights for trajectory conflict time, equivalent headway, and threat parameters.

[0048] Furthermore, the commercial vehicle right-turn test scenario data includes the distance vector between the test vehicle and the target object at the current moment, the distance vector between the target object and the test vehicle at the expected collision point, the target object's velocity, and the target object's velocity direction. Vehicle data includes the test vehicle's velocity and velocity direction. Therefore, the relative velocity vector between the test vehicle and the target object, and the angle between the test vehicle's velocity direction and the target object's velocity direction can be calculated.

[0049] Therefore, the expression for calculating the trajectory conflict time is:

[0050] in, The trajectory conflict time is used to assess the collision risk of two objects whose directions of motion are at an angle. for The distance vector at the expected collision point between the test vehicle and the target object at time (i.e., the current time mentioned above). for The distance vector between the target object and the expected collision point between the test vehicle at any given time. This is a preset constant, which is usually set to a very small positive number based on experience to prevent the denominator from being 0 when the test vehicle is parallel to the target object. To test the relative velocity vector between the vehicle and the target object. This is the unit vector pointing from the test vehicle to the target object. To test the angle between the vehicle's velocity direction and the target object's velocity direction.

[0051] Furthermore, the data for the commercial vehicle right turn test scenario includes the distance between the target object and the expected collision point of the test vehicle at the current moment, as well as the speed of the target object.

[0052] The expression for calculating the equivalent headway is:

[0053] in, The equivalent headway is used to assess the time required for the test vehicle to reach the expected collision point after turning, while traveling at its current speed. The smaller the equivalent headway, the higher the risk. The distance between the target object and the expected point of collision with the test vehicle. The velocity of the target object.

[0054] Furthermore, the data for the commercial vehicle right-turn test scenario includes the test vehicle's right-turn radius, vehicle width, and the target object's position at the current moment. Vehicle data includes the test vehicle's speed and position. Therefore, the distance between the test vehicle's position and the target object's position can be calculated.

[0055] The expression for calculating the threat parameter is:

[0056]

[0057] in, This is a threat parameter. The safety domain for testing vehicles is two-dimensional and variable in shape, which can more accurately describe the dynamic space required by the test vehicle during complex movements such as turning. To test the distance between the position of the vehicle and the position of the target object. To test the right-turn radius of the vehicle. To test the vehicle's speed. The preset communication delay represents the total delay time in various data transmission processes, such as the delay time for the server to determine physiological data, the delay time for the test vehicle to receive point cloud data, and the sum of the delay time for the head-mounted display device to receive video stream data. To test the width of the vehicle body. These are preset environmental uncertainty compensation parameters. These are the preset blind spot risk compensation parameters.

[0058] Furthermore, the expression for calculating the tester's state parameters is as follows:

[0059] in, These are the status parameters for the testers. (i∈(1,2,3,4)) represents one of the following: heart rate, eye pressure coefficient, electroencephalogram (EEG) signal, or electrodermal signal. for The corresponding normal value is the preset value. The superscript 'n' is short for 'normal', indicating the normal value. for The corresponding standard deviation is also the preset value, which is the preset standard deviation. The superscript 'n' is the abbreviation for 'normal'.

[0060] S6: Based on the vehicle data, update the commercial vehicle right turn test scenario in the simulation software.

[0061] In one or more embodiments of this specification, the server can receive vehicle data during the commercial vehicle right turn test process and feed it back to the simulation software, and in the simulation software, update the commercial vehicle right turn test scenario based on the fed-back vehicle data.

[0062] S7: Convert the updated commercial vehicle right-turn test scenario data into point cloud data and video stream data.

[0063] S8: Repeat steps S3-S7 until the commercial vehicle right turn test is completed.

[0064] In one or more embodiments of this specification, the server converts the updated commercial vehicle right-turn test scenario data into point cloud data and sends it to the test vehicle, and converts the updated commercial vehicle right-turn test scenario data into video stream data and sends it to the head-mounted display device. Steps S3 to S7 are then repeated until the commercial vehicle right-turn test is completed.

[0065] The specific process of repeating S3 to S7 is described exemplarily as follows: The updated commercial vehicle right-turn test scenario data, converted into video stream data and point cloud data, is sent to the test vehicle. The updated commercial vehicle right-turn test scenario data, converted into video stream data, is sent to the head-mounted display device worn by the test personnel in the test vehicle, so that the head-mounted display device displays the updated commercial vehicle right-turn test scenario to the test personnel. A new commercial vehicle right-turn test operation corresponding to the scenario risk level is then executed, and new physiological data of the test personnel is collected by the driver's physical and mental monitoring system connected to the test personnel. New vehicle data of the test vehicle is received during the commercial vehicle right-turn test operation. Based on the new vehicle data, the new physiological data, and the updated commercial vehicle right-turn test scenario data, a new collision risk coefficient for the commercial vehicle right-turn test is determined based on a risk quantification model. The commercial vehicle right-turn test scenario is continued to be updated in the simulation software based on the new vehicle data. The updated commercial vehicle right-turn test scenario data is then converted into point cloud data and video stream data. Furthermore, after the commercial vehicle right-turn test is completed, the server can automatically summarize the various data generated during the commercial vehicle right-turn test and generate a standardized road vehicle expected functional safety (SOTIF) analysis report with one click.

[0066] The above describes one or more embodiments of a commercial vehicle right-turn test method based on in-loop simulation, as provided in this specification. Based on the same idea, this specification also provides a corresponding commercial vehicle right-turn test device based on in-loop simulation, such as... Figure 2 As shown.

[0067] Figure 2 This specification provides a schematic diagram of a commercial vehicle right-turn testing device based on in-loop simulation, specifically including: The generation module 200 is used to generate test scenario data for right turns of commercial vehicles with scenario risk levels based on the preset scenario generation module. Simulation module 202 is used to construct a commercial vehicle right-turn test scenario in simulation software based on the commercial vehicle right-turn test scenario data. The commercial vehicle right-turn test scenario includes a test vehicle and a target object that is expected to collide with the test vehicle. The simulation module 202 is used to convert the commercial vehicle right-turn test scenario into video stream data and point cloud data. The sending module 204 is used to send the video stream data and the point cloud data to the test vehicle; and simultaneously send the video stream data to the head-mounted display device worn by the test personnel in the test vehicle, so that the head-mounted display device displays the commercial vehicle right turn test scenario to the test personnel; The execution module 206 is used to execute the commercial vehicle right turn test operation corresponding to the scenario risk level; and to collect the physiological data of the test personnel collected by the driver physical and mental monitoring system connected to the test personnel; and to receive the vehicle data of the test vehicle in the commercial vehicle right turn test operation. The determination module 208 is used to determine the collision risk coefficient of the commercial vehicle right turn test based on the vehicle data, the physiological data and the commercial vehicle right turn test scenario data, and a preset risk quantification model. Update module 210 is used to update the commercial vehicle right turn test scenario in the simulation software based on the vehicle data; The conversion module 212 is used to convert the updated commercial vehicle right turn test scenario data into point cloud data and video stream data.

[0068] Continue testing module 214 to repeat steps S3-S7 until the commercial vehicle right turn test is completed.

[0069] Optionally, the driver's physical and mental monitoring system includes a heart rate monitor, an eye tracker, an electroencephalogram (EEG) sensor, and a skin conductance sensor. The physiological data in the execution module 206 also includes: the heart rate of the test subject collected by the heart rate monitor, the eye pressure coefficient of the test subject collected by the eye tracker, the electroencephalogram (EEG) signal of the test subject collected by the EEG sensor, and the skin conductance signal collected by the skin conductance sensor. Optionally, the expression for the risk quantification model in the determining module 208 is:

[0070] Among them, the The collision risk coefficient is mentioned above; For trajectory conflict time; Equivalent headway; The threat parameters of the target object to the test vehicle are quantified; For the tester's status parameters; , , These are the preset weights for the trajectory conflict time, the equivalent headway, and the threat parameter, respectively.

[0071] Optionally, the commercial vehicle right turn test scenario data includes the distance vector at the expected collision point between the test vehicle and the target object at the current moment, the distance vector at the expected collision point between the target object and the test vehicle, the speed of the target object, and the speed direction of the target object; the vehicle data includes the speed of the test vehicle and the speed direction of the test vehicle. The expression for calculating the trajectory conflict time in the determining module 208 is as follows:

[0072] in, The time of the trajectory conflict; for The distance vector at the expected collision point between the test vehicle and the target object at any given moment; for The distance vector between the target object and the expected collision point of the test vehicle at any given moment; This is a preset constant; Let V be the relative velocity vector between the test vehicle and the target object; Let be the unit vector pointing from the test vehicle to the target object; The angle between the velocity direction of the test vehicle and the velocity direction of the target object.

[0073] Optionally, the commercial vehicle right turn test scenario data includes the distance between the target object and the expected collision point of the test vehicle at the current moment, and the speed of the target object; The expression for calculating the equivalent headway in the determining module 208 is as follows:

[0074] in, The equivalent headway; The distance between the target object and the expected point of collision between the test vehicle; The velocity of the target object is given.

[0075] Optionally, the commercial vehicle right-turn test scenario data includes the right-turn radius of the test vehicle at the current moment, the vehicle width of the test vehicle, and the position of the target object; the vehicle data includes the speed of the test vehicle and the position of the test vehicle. The expression used by the determining module 208 to calculate the threat parameter is:

[0076]

[0077] in, The threat parameter; The safety domain of the test vehicle; The distance between the position of the test vehicle and the position of the target object; Let be the right-turn radius of the test vehicle; The speed of the test vehicle; The preset communication delay; The width of the test vehicle; These are preset environmental uncertainty compensation parameters; These are the preset blind spot risk compensation parameters.

[0078] Optionally, the expression for calculating the tester's state parameters in the determining module 206 is:

[0079] in, The tester's status parameters; (i∈(1,2,3,4)) is one of the heart rate, the eye pressure coefficient, the electroencephalogram (EEG) signal, and the electrodermal signal; for The corresponding normal value; for The corresponding standard deviation.

[0080] This specification also provides a computer-readable storage medium storing a computer program that can be used to execute the above-described... Figure 1 A test method for right turns of commercial vehicles based on in-loop simulation is provided.

[0081] This instruction manual also provides Figure 3 The diagram shows a schematic structural representation of the electronic device. Figure 3 As shown, at the hardware level, this electronic device includes a processor, internal bus, network interface, memory, and non-volatile memory, and may also include other hardware required for business operations. The processor reads the corresponding computer program from the non-volatile memory into memory and then runs it to achieve the above. Figure 1 The aforementioned method for testing right turns of commercial vehicles based on in-loop simulation.

[0082] Of course, in addition to software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of hardware and software. In other words, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0083] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0084] The above description is merely an embodiment of this specification and is not intended to limit this specification. Various modifications and variations can be made to this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of the claims of this specification.

Claims

1. A commercial vehicle right-turn test method based on in-loop simulation, characterized in that, include: S1. Generate test scenario data for right turns of commercial vehicles with scenario risk levels based on the preset scenario generation module; S2. Based on the commercial vehicle right-turn test scenario data, construct a commercial vehicle right-turn test scenario in simulation software, the commercial vehicle right-turn test scenario including the test vehicle and the target object expected to collide with the test vehicle; and convert the commercial vehicle right-turn test scenario into video stream data and point cloud data; S3. Send the video stream data and the point cloud data to the test vehicle; Simultaneously, the video stream data is sent to the head-mounted display device worn by the test personnel in the test vehicle, so that the head-mounted display device can display the commercial vehicle right turn test scenario to the test personnel; S4. Perform the commercial vehicle right turn test operation corresponding to the scenario risk level; and collect the physiological data of the test personnel collected by the driver physical and mental monitoring system connected to the test personnel; and receive the vehicle data of the test vehicle in the commercial vehicle right turn test operation; S5. Based on the vehicle data, the physiological data, and the commercial vehicle right turn test scenario data, determine the collision risk coefficient of the commercial vehicle right turn test based on a preset risk quantification model; S6. Based on the vehicle data, update the commercial vehicle right turn test scenario in the simulation software; S7. Convert the updated commercial vehicle right-turn test scenario data into point cloud data and video stream data; S8. Repeat steps S3-S7 until the commercial vehicle right turn test is completed.

2. The commercial vehicle right-turn test method based on in-loop simulation as described in claim 1, characterized in that, The driver's physical and mental monitoring system includes a heart rate monitor, an eye tracker, an electroencephalogram (EEG) sensor, and a skin conductance sensor. The physiological data in S3 include: The heart rate of the test subject is collected by the heart rate monitor, the eye pressure coefficient of the test subject is collected by the eye tracker, the electroencephalogram (EEG) signal of the test subject is collected by the EEG sensor, and the skin conductance signal is collected by the skin conductance sensor.

3. The commercial vehicle right-turn test method based on in-loop simulation as described in claim 2, characterized in that, The expression for the risk quantification model is: Among them, the The collision risk coefficient is mentioned above; For trajectory conflict time; Equivalent headway; The threat parameters of the target object to the test vehicle are quantified; For the tester's status parameters; , , These are the preset weights for the trajectory conflict time, the equivalent headway, and the threat parameter, respectively.

4. The commercial vehicle right-turn test method based on in-loop simulation as described in claim 3, characterized in that, The commercial vehicle right turn test scenario data includes the distance vector at the expected collision point between the test vehicle and the target object at the current moment, the distance vector at the expected collision point between the target object and the test vehicle, the speed of the target object, and the speed direction of the target object; the vehicle data includes the speed of the test vehicle and the speed direction of the test vehicle; The expression for calculating the trajectory conflict time is: in, The time of the trajectory conflict; for The distance vector at the expected collision point between the test vehicle and the target object at any given moment; for The distance vector between the target object and the expected collision point of the test vehicle at any given moment; This is a preset constant; Let V be the relative velocity vector between the test vehicle and the target object; Let be the unit vector pointing from the test vehicle to the target object; The angle between the velocity direction of the test vehicle and the velocity direction of the target object.

5. The commercial vehicle right-turn test method based on in-loop simulation as described in claim 3, characterized in that, The commercial vehicle right turn test scenario data includes the distance between the target object and the expected collision point of the test vehicle at the current moment, and the speed of the target object; The expression for calculating the equivalent headway is: in, The equivalent headway; The distance between the target object and the expected point of collision between the test vehicle; The velocity of the target object is given.

6. The commercial vehicle right-turn test method based on in-loop simulation as described in claim 3, characterized in that, The commercial vehicle right-turn test scenario data includes the right-turn radius of the test vehicle at the current moment, the vehicle width, and the position of the target object; the vehicle data includes the test vehicle speed and the test vehicle position. The expression for calculating the threat parameter is: in, The threat parameter; The safety domain of the test vehicle; The distance between the position of the test vehicle and the position of the target object; Let be the right-turn radius of the test vehicle; The speed of the test vehicle; The preset communication delay; The width of the test vehicle; These are preset environmental uncertainty compensation parameters; These are the preset blind spot risk compensation parameters.

7. The commercial vehicle right-turn test method based on in-loop simulation as described in claim 3, characterized in that, The expression for calculating the tester's state parameters is as follows: in, The tester's status parameters; (i∈(1,2,3,4)) is one of the heart rate, the eye pressure coefficient, the electroencephalogram (EEG) signal, and the electrodermal signal; for The corresponding normal value; for The corresponding standard deviation.

8. A commercial vehicle right-turn testing device based on in-loop simulation, characterized in that, include: The generation module is used to generate test scenario data for right turns of commercial vehicles with scenario risk levels based on the preset scenario generation module. The simulation module is used to construct a right-turn test scenario for commercial vehicles in simulation software based on the right-turn test scenario data of the commercial vehicles. The right-turn test scenario for commercial vehicles includes the test vehicle and the target object that is expected to collide with the test vehicle. The module also converts the right-turn test scenario for commercial vehicles into video stream data and point cloud data. A sending module is used to send the video stream data and the point cloud data to the test vehicle; Simultaneously, the video stream data is sent to the head-mounted display device worn by the test personnel in the test vehicle, so that the head-mounted display device can display the commercial vehicle right turn test scenario to the test personnel; The execution module is used to perform a right-turn test operation for commercial vehicles corresponding to the risk level of the scenario; and to collect physiological data of the test personnel collected by the driver's physical and mental monitoring system connected to the test personnel; and to receive vehicle data of the test vehicle during the right-turn test operation for commercial vehicles. The determination module is used to determine the collision risk coefficient of the commercial vehicle right turn test based on the vehicle data, the physiological data, and the commercial vehicle right turn test scenario data, and a preset risk quantification model. The update module is used to update the commercial vehicle right turn test scenario in the simulation software based on the vehicle data. The conversion module is used to convert the updated commercial vehicle right-turn test scenario data into point cloud data and video stream data. Continue testing the module to repeat steps S3-S7 until the commercial vehicle right turn test is completed.

9. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the method described in any one of claims 1 to 7.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method described in any one of claims 1 to 7.

Images