Automatic driving vehicle fog sensing test method and device, medium and equipment

Abstract

The invention provides an automatic driving vehicle fog perception test method and device, a medium and equipment, and the method comprises the steps: building a fog drop dynamic model based on a fluid mechanics principle, and generating a plurality of fog modes; determining operation parameters of a plurality of atomizers in the test area based on a fog mode corresponding to the test requirement; acquiring a fog state in the test area in the test area; controlling the automatic driving vehicle to execute an automatic driving test in the test area, and collecting operation data; determining the safety performance of the autonomous vehicle in the fog environment based on the operation data of the autonomous vehicle; according to the method, the stress, settlement and distribution conditions of fog drops are simulated by constructing a fog drop dynamic model, the operation parameters of an atomizer in a test area are controlled based on test requirements, and fog state monitoring of the test area is performed, so that closed-loop accurate control is realized, the accuracy of the fog state in the test area is improved, and the test efficiency is improved. And the adaptability and robustness of the fog environment test of the automatic driving vehicle are improved.

Description

Technical Field

[0001] This application relates to the field of autonomous vehicle testing technology, specifically to a method, apparatus, medium, and equipment for testing fog perception in autonomous vehicles. Background Technology

[0002] With the continuous development of autonomous driving technology, its perception and decision-making capabilities in complex environments have become a crucial factor affecting system safety and reliability. Fog is a typical scenario that interferes with the normal operation of autonomous driving systems. The tiny water droplets in fog strongly scatter light, causing blurred camera images and reduced contrast. Furthermore, while millimeter-wave radar has a certain penetration capability, it is affected by signal attenuation in dense fog, resulting in numerous noise points and reduced detection range in lidar point cloud data, severely impacting target recognition and positioning accuracy. These factors combined can easily lead to serious consequences such as path recognition failure, obstacle misjudgment, and abnormal control commands, thereby threatening the safe operation of autonomous vehicles.

[0003] Currently, testing the perception and decision-making capabilities of autonomous driving systems in foggy environments primarily relies on real-vehicle road tests and virtual simulation platforms. However, real-vehicle road tests are limited by uncontrollable natural weather conditions, long testing cycles, high costs, and potential safety hazards, making it difficult to meet the comprehensive verification requirements for system performance under extreme weather conditions. Existing virtual simulation platforms still have significant limitations in modeling fog optical effects and multi-sensor coupling interference, making it difficult to achieve high-precision reproduction of real foggy environments. Therefore, there is an urgent need to construct a closed-loop testing system capable of simulating various fog conditions in a laboratory environment and dynamically adjusting fog concentration and distribution. This would improve the adaptability and robustness of autonomous driving systems in foggy environments, providing reliable technical support for related algorithm optimization and system verification. Summary of the Invention

[0004] To address the aforementioned technical problems, this application is proposed. Embodiments of this application provide a method, apparatus, medium, and device for testing fog perception in autonomous vehicles.

[0005] According to one aspect of this application, a fog perception testing method for autonomous vehicles is provided, comprising: constructing a fog droplet dynamics model based on fluid dynamics principles; wherein the fog droplet dynamics model represents the force state, settling trajectory, and spatial distribution law of fog droplets in the air; generating multiple fog patterns based on the fog droplet dynamics model; wherein each fog pattern corresponds to a set of fog parameters; determining the operating parameters of multiple atomizers in a test area based on the fog pattern corresponding to the test requirements; collecting the fog state in the test area using environmental monitoring equipment; comparing the fog state in the test area with the fog parameters corresponding to the fog patterns to obtain a difference value; if the difference value is less than a preset value, controlling the autonomous vehicle to perform an autonomous driving test in the test area and collecting the operating data of the autonomous vehicle; and determining the safety performance of the autonomous vehicle in a fog environment based on the operating data of the autonomous vehicle.

[0006] In one embodiment, constructing a droplet dynamics model based on fluid dynamics principles includes: constructing a droplet dynamics model based on fluid dynamics principles to determine the droplet velocity and droplet fall angle.

[0007] In one embodiment, the step of constructing a droplet dynamics model based on fluid dynamics principles to determine the droplet velocity and droplet fall angle includes: the calculation formula for the droplet velocity is: ;in, It is the droplet velocity. It is the radius of the fog droplet. It is gravitational acceleration. It is the density of water. It is the air drag coefficient. It is the air density; the formula for calculating the droplet falling angle is: ;in, It is the angle at which the fog droplets fall. It's wind speed. It is the vertical falling speed of the fog droplets.

[0008] In one embodiment, determining the operating parameters of multiple atomizers within a test area based on the fog mode corresponding to the test requirements includes: dividing the multiple atomizers within the test area into multiple control sub-regions based on the fog mode corresponding to the test requirements; and determining the fog output and atomizer activation frequency of each control sub-region based on the fog mode corresponding to the test requirements.

[0009] In one embodiment, the step of using environmental monitoring equipment to collect fog conditions within the test area includes: using a camera, lidar, humidity sensor, and an anemometer to collect fog images, fog point clouds, fog concentration, and wind speed within the test area, respectively.

[0010] In one embodiment, the fog perception test method for autonomous vehicles further includes: if the difference value is greater than or equal to the preset value, adjusting the operating parameters of multiple atomizers in the test area until the difference value is less than the preset value.

[0011] In one embodiment, determining the safety performance of the autonomous vehicle in a foggy environment based on the vehicle's operating data includes: calculating the target recognition accuracy, path tracking error, and number of emergency braking operations of the autonomous vehicle based on the vehicle's operating data; and determining the safety performance of the autonomous vehicle in a foggy environment based on the target recognition accuracy, the path tracking error, and the number of emergency braking operations.

[0012] According to another aspect of this application, an autonomous vehicle fog perception testing device is provided, comprising: a fog droplet model construction module for constructing a fog droplet dynamics model based on fluid dynamics principles; wherein the fog droplet dynamics model represents the force state, sedimentation trajectory, and spatial distribution law of fog droplets in the air; a fog pattern generation module for generating multiple fog patterns based on the fog droplet dynamics model; wherein each fog pattern corresponds to a set of fog parameters; an atomization parameter determination module for determining the operating parameters of multiple atomizers in a test area based on the fog patterns corresponding to the test requirements; a fog state monitoring module for collecting the fog state in the test area using environmental monitoring equipment; a parameter difference comparison module for comparing the fog state in the test area with the fog parameters corresponding to the fog patterns to obtain a difference value; an operation data acquisition module for controlling the autonomous vehicle to perform an autonomous driving test in the test area and collecting the operation data of the autonomous vehicle if the difference value is less than a preset value; and a safety performance evaluation module for determining the safety performance of the autonomous vehicle in a fog environment based on the operation data of the autonomous vehicle.

[0013] According to another aspect of this application, a computer-readable storage medium is provided, the storage medium storing a computer program for performing any of the methods described above.

[0014] According to another aspect of this application, an electronic device is provided, comprising: a processor; a memory for storing processor-executable instructions; the processor being configured to perform any of the methods described above.

[0015] This application provides a fog perception testing method, device, medium, and equipment for autonomous vehicles. Based on fluid mechanics principles, a fog droplet dynamics model is constructed. This model represents the force state, settling trajectory, and spatial distribution of fog droplets in the air. Multiple fog patterns are generated based on the fog droplet dynamics model, each corresponding to a set of fog parameters. Based on the fog patterns corresponding to the testing requirements, the operating parameters of multiple atomizers within the test area are determined. Environmental monitoring equipment is used to collect fog conditions within the test area. The fog conditions within the test area are compared with the fog parameters corresponding to the fog patterns. The difference value is obtained; if the difference value is less than the preset value, the autonomous vehicle is controlled to perform autonomous driving test in the test area and the operation data of the autonomous vehicle is collected; based on the operation data of the autonomous vehicle, the safety performance of the autonomous vehicle in the fog environment is determined; that is, by constructing a fog droplet dynamics model to simulate the force, sedimentation and distribution of fog droplets, and controlling the operation parameters of the atomizer in the test area based on the test requirements, and monitoring the fog state in the test area, so as to achieve closed-loop precise control, improve the accuracy of the fog state in the test area, and thus improve the adaptability and robustness of the autonomous vehicle fog environment test. Attached Figure Description

[0016] The above and other objects, features, and advantages of this application will become more apparent from the more detailed description of the embodiments of this application in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the embodiments of this application to explain this application and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0017] Figure 1 This is a flowchart illustrating an exemplary embodiment of the present application of a method for testing fog perception in autonomous vehicles.

[0018] Figure 2 This is a schematic diagram of the structure of an autonomous vehicle fog perception test device provided in an exemplary embodiment of this application.

[0019] Figure 3 This is a structural diagram of an electronic device provided in an exemplary embodiment of this application. Detailed Implementation

[0020] Hereinafter, exemplary embodiments according to this application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this application, and not all embodiments of this application. It should be understood that this application is not limited to the exemplary embodiments described herein.

[0021] Figure 1This is a flowchart illustrating an exemplary embodiment of the fog perception testing method for autonomous vehicles provided in this application. Figure 1 As shown, the fog perception test method for autonomous vehicles includes the following steps: Step 110: Construct a droplet dynamics model based on fluid mechanics principles.

[0022] The droplet dynamics model represents the force state, settling trajectory, and spatial distribution of droplets in the air. Free-falling droplets in the air are mainly affected by gravity and air resistance. Gravity causes the droplets to accelerate downwards, while air resistance gradually increases with velocity, eventually reaching a stable terminal velocity. To accurately describe the motion behavior of droplets, this invention establishes a three-dimensional dynamic model of droplets, as shown in the following equation: ; in, It is the mass of the fog droplets. It is the acceleration due to gravity. The air drag coefficient, air density, The cross-sectional area of ​​the droplet. Where is the droplet radius, Let be the velocity vector of the droplets. Indicates the magnitude of the droplet velocity. Let be the direction vector of unit velocity. By solving the above differential equation, we can obtain the velocity and position information of the fog droplets in three-dimensional space as a function of time, and then simulate their dynamic sedimentation process in the fog environment. This model provides a key physical basis for subsequent prediction of fog diffusion behavior and modeling of sensor interference.

[0023] Step 120: Generate multiple fog patterns based on the fog droplet dynamics model.

[0024] Each fog mode corresponds to a set of fog parameters. To achieve high-precision reproduction of different fog types, this application constructs a fog mode classification system based on visibility level division, and establishes a multi-dimensional parameter mapping relationship by combining fuzzy clustering algorithm and empirical lookup table method. Based on different testing requirements, it automatically matches corresponding key physical parameters such as droplet size distribution, spatial density, humidity, and wind speed, thereby supporting the flexible generation of various fog scenarios such as light fog, medium fog, and dense fog.

[0025] Based on fog visibility standards, this application classifies indoor simulated fog into three categories: Table 1 Fog Pattern Table

[0026] For each fog pattern, a set of fog parameters that highly matches its physical characteristics is determined, including but not limited to: droplet size distribution parameters, number of droplets per unit volume, vertical droplet settling velocity, ambient wind speed, relative humidity, and optical scattering coefficient. These parameters have nonlinear coupling relationships. A fuzzy C-means clustering algorithm (FCM) is used to learn from historical data to establish a mapping rule from the target fog pattern to the above parameter set. The specific process is as follows: A large number of natural fog samples were collected, and information such as visibility, particle size distribution, humidity, and wind speed were extracted to construct a fog feature database. The FCM algorithm was used to cluster the data, identifying three fog feature clusters consistent with the classification criteria. A corresponding fog parameter configuration template was established for each cluster center. During testing, the corresponding parameter combination was quickly invoked based on the current target fog level to complete the fog modeling initialization. This method not only improves the accuracy of parameter configuration but also enhances the system's adaptability to complex fog conditions.

[0027] To more realistically simulate the temporal evolution of natural fog, the system introduces a first-order Markov chain model to model the changes in fog states. Specifically, let the set of fog states be: ; At any time t The state transition probabilities are described by the transition matrix P: ; in, Indicates from state Transition to state The probability of each element satisfies the normalization condition, i.e. .

[0028] By pre-setting a reasonable state transition probability matrix, the system can simulate various natural fog evolution processes, such as the gradual formation of morning fog, the sudden appearance of patchy fog, and the dissipation of fog, enhancing the realism and diversity of the test. For example, in the "gradual formation of morning fog" process, the system gradually increases the fog concentration along the path of "no fog → light fog → moderate fog"; in the "sudden appearance of patchy fog" process, the system simulates sudden strong fog phenomena through a high-probability "light fog → dense fog" transition; and in the "fog dissipation" stage, it mainly manifests as a transition from a high-concentration state to a low-concentration state. This modeling method not only improves the realism of fog simulation but also provides effective technical support for the performance verification of autonomous driving systems in non-steady-state fog environments.

[0029] Step 130: Based on the fog mode corresponding to the test requirements, determine the operating parameters of multiple atomizers in the test area.

[0030] To achieve precise control of fog distribution in indoor spaces, this application adopts a modular, programmable, multi-layer distributed fogging device arrangement scheme. This scheme supports independent adjustment of fog concentration in different areas and combines a zone control strategy to achieve flexible switching between global and local fog scenarios.

[0031] Specifically, this application can arrange multiple independent and controllable atomizing units in a grid pattern with equal spacing (e.g., 2m×2m) on the top of the greenhouse in the test area; the installation height of the atomizing units is 3~5 meters to ensure that the mist droplets are fully diffused and form a stable mist layer; and this application uses atomizers of various shapes, including ultrasonic atomizers suitable for light mist mode, high-pressure air compression nozzles suitable for medium / dense mist mode, and adjustable angle nozzles that support tilted mist output to simulate wind and mist mixing.

[0032] Step 140: Use environmental monitoring equipment to collect the fog status in the test area.

[0033] This application introduces a real-time visibility feedback mechanism, which uses a camera image clarity assessment module and a lidar point cloud penetration analysis module to jointly collect the fog status in the test area, in order to determine the current environmental status, dynamically adjust the fog level setting, and improve the adaptability and closed-loop response capability of the test process.

[0034] Step 150: Compare the fog state and fog mode corresponding to the test area to obtain the difference value.

[0035] Based on the aforementioned environmental perception and state observation results, this application introduces a feedback adjustment mechanism based on optimization search to achieve dynamic adjustment of fog intensity and distribution, and evaluates the performance of the autonomous driving system in foggy environments through data analysis. Specifically, by comparing the fog state and fog parameters corresponding to the fog mode in the test area, the difference value is obtained to determine whether the fog state in the current test area meets the test requirements.

[0036] Step 160: If the difference value is less than the preset value, control the autonomous vehicle to perform an autonomous driving test in the test area and collect the autonomous vehicle's operating data.

[0037] If the difference between the fog state and fog mode corresponding to the collected fog parameters in the test area is less than the preset value, it means that the fog state in the test area meets the test requirements. At this time, the autonomous vehicle can be controlled to perform autonomous driving test in the test area and the operation data of the autonomous vehicle can be collected to realize the test of the autonomous vehicle.

[0038] Step 170: Based on the operational data of the autonomous vehicle, determine the safety performance of the autonomous vehicle in foggy environments.

[0039] By analyzing the collected operational data of autonomous vehicles, the safety performance of autonomous vehicles in foggy environments can be determined.

[0040] This application provides a fog perception testing method for autonomous vehicles. Based on fluid dynamics principles, a fog droplet dynamics model is constructed. This model represents the force state, settling trajectory, and spatial distribution of fog droplets in the air. Multiple fog patterns are generated based on the model, each corresponding to a set of fog parameters. Operating parameters for multiple atomizers within the test area are determined based on the fog patterns corresponding to the test requirements. Environmental monitoring equipment is used to collect fog conditions within the test area. The fog conditions within the test area are compared with the fog parameters corresponding to the fog patterns to obtain a difference value. If the difference value is less than a preset value, the autonomous vehicle is controlled to perform an autonomous driving test within the test area, and its operating data is collected. Based on the operating data, the safety performance of the autonomous vehicle in a foggy environment is determined. In other words, by constructing a fog droplet dynamics model to simulate the force, settling, and distribution of fog droplets, and controlling the operating parameters of atomizers within the test area based on test requirements, and monitoring the fog conditions in the test area, closed-loop precise control is achieved, improving the accuracy of fog conditions within the test area, and thus enhancing the adaptability and robustness of autonomous vehicle fog environment testing.

[0041] In one embodiment, step 110 can be implemented by: constructing a droplet dynamics model based on fluid dynamics principles to determine the droplet velocity and droplet falling angle.

[0042] To achieve high-precision simulation of real fog environments, this application constructs a three-dimensional fog droplet motion model based on fluid dynamics principles and combines statistical distribution theory to generate a particle set that conforms to the characteristics of actual fog, so as to restore the force state, sedimentation trajectory and spatial distribution law of fog droplets in the air, including fog droplet velocity and fog droplet falling angle, thereby providing physical foundation support for subsequent fog concentration control, optical interference effect assessment and other modules.

[0043] In one embodiment, step 110 can be implemented as follows: the formula for calculating the fog velocity is: ;in, It is the droplet velocity. It is the radius of the fog droplet. It is gravitational acceleration. It is the density of water. It is the air drag coefficient. It refers to air density; the formula for calculating the angle of fall of fog droplets is: ;in, It is the angle at which the fog droplets fall. It's wind speed. It is the vertical falling speed of the fog droplets.

[0044] When a droplet falls through the air and reaches its terminal velocity, the net force acting on it is zero. At this point, we have: ; The expression for the mass of a droplet is: ； Combining the two formulas above, we get: ; in, It is the terminal velocity of the fog droplets, that is, the speed at which the fog droplets fall into the air and reach a steady state. It is the density of water. Take 0.47.

[0045] This formula can be used to estimate the terminal velocity of droplets of different sizes, and is one of the important parameters for subsequent fog scene modeling. Using this formula, corresponding droplet settling velocities can be set according to different fog levels, further supporting the dynamic simulation of fog spatial distribution.

[0046] To more realistically reflect the randomness of droplet size in natural fog, this invention uses the Gamma distribution to statistically model droplet size: ; in, It is a probability density function. These are shape parameters; It is a scale parameter; It is a gamma function. This distribution form has good flexibility and adaptability, and can fit the particle size statistics well under various fog conditions, from light fog to dense fog. It automatically matches the corresponding parameter combination according to the current fog type, and generates a set of fog droplet particles that conforms to the characteristics of that type of fog.

[0047] In real-world foggy environments, wind speed will deflect the falling trajectory of fog droplets. Let the wind speed be... The vertical falling speed of the droplets is Then the angle at which the fog droplets fall. It can be represented as: ; This formula is used to simulate the distribution of fog droplets in a mixed wind and fog state, enhancing the realism and diversity of fog simulation.

[0048] Before each simulation, a certain number of fog droplets are initialized based on the current fog intensity, duration, and region division. Each fog droplet is assigned the following attributes: initial position, initial velocity, radius, and lifetime. Subsequently, within each time step, the differential equation is solved using numerical integration methods (such as the fourth-order Runge-Kutta method), and its position and velocity information are updated in real time, thereby achieving dynamic simulation of the entire fog diffusion process.

[0049] In one embodiment, step 130 can be implemented as follows: based on the fog mode corresponding to the test requirements, the multiple atomizers in the test area are divided into multiple control sub-regions; based on the fog mode corresponding to the test requirements, the fog output and atomizer activation frequency of each control sub-region are determined.

[0050] The entire test area is divided into several mist control sub-zones (e.g., 5m×5m). Each control sub-zone is managed by a central controller that manages its atomizer group, supporting the following control modes: Globally synchronized fog generation: Atomizers with the same parameters are activated simultaneously in all areas; Localized mist enhancement: Increases atomizer density or increases liquid supply pressure only within a designated area; Dynamic moving fog simulation: By controlling the timing, the fog is moved "from one side to the other", simulating the process of a vehicle encountering changes in fog while moving.

[0051] The fog concentration can be dynamically adjusted in the following three ways: Adjusting atomizer density (static): Different numbers of atomizers can be configured for different areas, suitable for maintaining a fixed fog level over a long period of time; for example, the number of atomizers per square meter can range from 1 (light fog) to 4 (dense fog); Adjusting the liquid supply pressure (dynamically): The water supply pressure is adjusted using a variable frequency pump, thereby changing the amount of mist produced per unit time. ; in, This refers to the fog concentration. The constant coefficients, For the liquid supply pressure, It is an experience index (usually ranging from 1 to 1.5). Adjust the atomizer's on / off frequency: The program controls the atomizer's start and stop rhythm to simulate intermittent fog phenomena, such as morning fog and patchy fog.

[0052] In one embodiment, step 140 can be implemented by using a camera, lidar, humidity sensor and anemometer to collect fog images, fog point clouds, fog concentration and wind speed in the test area.

[0053] This application can use cameras to acquire image data and evaluate visual perception performance, use lidar to acquire point cloud data and detect false targets and noise interference, use humidity sensors to measure the current fog concentration, and use an anemometer to acquire wind speed information for fog droplet angle correction. Furthermore, it can use IMU and GPS to collect the operating status of autonomous vehicles.

[0054] By observing and modeling the aforementioned state variables in real time, a complete environment-system interaction graph can be constructed, providing a basic input for the next step of closed-loop feedback control.

[0055] In one embodiment, the above-mentioned autonomous vehicle fog perception test method may further include: if the difference value is greater than or equal to a preset value, adjusting the operating parameters of multiple atomizers in the test area until the difference value is less than the preset value.

[0056] This application can employ a feedback adjustment mechanism based on particle swarm optimization algorithm to find the optimal combination of test conditions, i.e. the optimal combination of atomizer operating parameters, in a preset mist parameter space.

[0057] The objective function is defined as follows: ; in, The vector of mist control parameters to be optimized (such as atomizer frequency, tilt angle, liquid supply pressure, etc.). The desired system output (such as the ideal path, target recognition result, etc.); This represents the actual output of the autonomous driving system in the current foggy environment. To control the action, 、 The weighting coefficients are used to balance tracking error and control costs. By continuously iterating and updating particle positions and velocities, the particle swarm optimization algorithm can approximate the optimal control strategy in the parameter space, achieving dynamic adjustment of fog intensity and distribution. Specifically, if the difference between the calculated system output (fog parameters corresponding to the fog mode) and the actual output (fog state in the test area) is greater than or equal to a preset value, the operating parameters of multiple atomizers in the test area are adjusted until the difference is less than the preset value.

[0058] In one embodiment, step 170 can be implemented as follows: based on the operating data of the autonomous vehicle, calculate the target recognition accuracy, path tracking error, and number of emergency braking operations of the autonomous vehicle; based on the target recognition accuracy, path tracking error, and number of emergency braking operations, determine the safety performance of the autonomous vehicle in foggy conditions.

[0059] To comprehensively evaluate the performance of the autonomous driving system in foggy conditions, this application calculates multiple key performance indicators to achieve a comprehensive assessment.

[0060] The formula for calculating target recognition accuracy is: ; in, For target recognition accuracy, , and These represent the number of true positive, false positive, and false negative samples, respectively.

[0061] The formula for calculating path tracking error is: ; in, It is path tracking error. These are the actual path coordinates. These are the reference path coordinates.

[0062] The formula for calculating the number of emergency braking operations is: ; in, Number of emergency braking operations express t Moment braking force The time is recorded as 1.

[0063] This application evaluates the safety of autonomous vehicles in foggy environments by calculating target recognition accuracy, path tracking error, and number of emergency braking events, and by combining these three performance indicators.

[0064] Figure 2 This is a schematic diagram of the structure of an autonomous vehicle fog perception testing device provided in an exemplary embodiment of this application. Figure 2As shown, the fog perception testing device 20 for autonomous vehicles includes: a fog droplet model construction module 21, used to construct a fog droplet dynamics model based on fluid dynamics principles; wherein, the fog droplet dynamics model represents the force state, sedimentation trajectory, and spatial distribution law of fog droplets in the air; a fog pattern generation module 22, used to generate multiple fog patterns based on the fog droplet dynamics model; wherein, each fog pattern corresponds to a set of fog parameters; a fogging parameter determination module 23, used to determine the operating parameters of multiple atomizers in the test area based on the fog pattern corresponding to the test requirements; a fog state monitoring module 24, used to collect the fog state in the test area using environmental monitoring equipment; a parameter difference comparison module 25, used to compare the fog state in the test area with the fog parameters corresponding to the fog pattern to obtain the difference value; an operation data acquisition module 26, used to control the autonomous vehicle to perform an autonomous driving test in the test area and collect the operation data of the autonomous vehicle if the difference value is less than a preset value; and a safety performance evaluation module 27, used to determine the safety performance of the autonomous vehicle in the fog environment based on the operation data of the autonomous vehicle.

[0065] This application provides an autonomous vehicle fog perception testing device. A fog droplet model construction module 21 constructs a fog droplet dynamics model based on fluid mechanics principles. This model represents the force state, settling trajectory, and spatial distribution of fog droplets in the air. A fog pattern generation module 22 generates multiple fog patterns based on the fog droplet dynamics model, each corresponding to a set of fog parameters. A fog parameter determination module 23 determines the operating parameters of multiple atomizers within the test area based on the fog patterns corresponding to the test requirements. A fog state monitoring module 24 collects fog state data within the test area using environmental monitoring equipment. A parameter difference comparison module 25 compares the fog state within the test area with... The fog parameters corresponding to the fog mode are used to obtain the difference value. If the difference value is less than the preset value, the data acquisition module 26 controls the autonomous vehicle to perform autonomous driving test in the test area and collects the operation data of the autonomous vehicle. The safety performance evaluation module 27 determines the safety performance of the autonomous vehicle in the fog environment based on the operation data of the autonomous vehicle. That is, by constructing a fog droplet dynamics model to simulate the force, sedimentation and distribution of fog droplets, and controlling the operation parameters of the atomizer in the test area based on the test requirements, and monitoring the fog state in the test area, a closed-loop precise control is achieved to improve the accuracy of the fog state in the test area, thereby improving the adaptability and robustness of the autonomous vehicle fog environment test.

[0066] In one embodiment, the above-mentioned droplet model construction module 21 can be further configured to: construct a droplet dynamics model based on fluid dynamics principles to determine the droplet velocity and droplet falling angle.

[0067] In one embodiment, the above-mentioned fog droplet model construction module 21 can be further configured such that the fog velocity is calculated using the following formula: ;in, It is the droplet velocity. It is the radius of the fog droplet. It is gravitational acceleration. It is the density of water. It is the air drag coefficient. It refers to air density; the formula for calculating the angle of fall of fog droplets is: ;in, It is the angle at which the fog droplets fall. It's wind speed. It is the vertical falling speed of the fog droplets.

[0068] In one embodiment, the atomization parameter determination module 23 can be further configured to: divide multiple atomizers in the test area into multiple control sub-regions based on the fog mode corresponding to the test requirements; and determine the fog output and atomizer activation frequency of each control sub-region based on the fog mode corresponding to the test requirements.

[0069] In one embodiment, the fog state monitoring module 24 can be further configured to: use a camera, lidar, humidity sensor and an anemometer to collect fog images, fog point clouds, fog concentration and wind speed in the test area.

[0070] In one embodiment, the aforementioned autonomous vehicle fog perception test device 20 can be further configured to: if the difference value is greater than or equal to a preset value, adjust the operating parameters of multiple atomizers in the test area until the difference value is less than the preset value.

[0071] In one embodiment, the safety performance evaluation module 27 can be further configured to: calculate the target recognition accuracy, path tracking error, and number of emergency braking operations of the autonomous vehicle based on its operating data; and determine the safety performance of the autonomous vehicle in foggy conditions based on the target recognition accuracy, path tracking error, and number of emergency braking operations.

[0072] Below, for reference Figure 3 This application describes an electronic device according to embodiments thereof. The electronic device may be either or both of a first device and a second device, or a standalone device independent of them, which may communicate with the first device and the second device to receive acquired input signals from them.

[0073] Figure 3 A block diagram of an electronic device according to an embodiment of this application is illustrated.

[0074] like Figure 3As shown, the electronic device 10 includes one or more processors 11 and memory 12.

[0075] The processor 11 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0076] The memory 12 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may execute the program instructions to implement the methods of the various embodiments of this application described above and / or other desired functions. Various contents such as input signals, signal components, and noise components may also be stored in the computer-readable storage medium.

[0077] In one example, the electronic device 10 may also include an input device 13 and an output device 14, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0078] When the electronic device is a standalone device, the input device 13 can be a communication network connector for receiving the collected input signals from the first device and the second device.

[0079] In addition, the input device 13 may also include, for example, a keyboard, a mouse, etc.

[0080] The output device 14 can output various information to the outside, including determined distance information, direction information, etc. The output device 14 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0081] Of course, for the sake of simplicity, Figure 3 Only some of the components of the electronic device 10 relevant to this application are shown in this illustration; components such as buses, input / output interfaces, etc., are omitted. In addition, the electronic device 10 may include any other suitable components depending on the specific application.

[0082] In addition to the methods and apparatus described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in the methods according to various embodiments of this application described in the "Exemplary Methods" section above.

[0083] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0084] Furthermore, embodiments of this application may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps in the methods according to various embodiments of this application described in the "Exemplary Methods" section above.

[0085] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0086] The basic principles of this application have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this application are merely examples and not limitations, and should not be considered as essential features of each embodiment of this application. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the application to the necessity of employing the aforementioned specific details for implementation.

[0087] The block diagrams of devices, apparatuses, devices, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0088] It should also be noted that in the apparatus, equipment, and methods of this application, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of this application.

[0089] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0090] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A fog perception test method for autonomous vehicles, characterized in that, include: Based on the principles of fluid mechanics, a fog droplet dynamics model is constructed; wherein, the fog droplet dynamics model represents the force state, sedimentation trajectory and spatial distribution law of fog droplets in the air; Based on the aforementioned droplet dynamics model, multiple fog patterns are generated; each fog pattern corresponds to a set of fog parameters. Based on the fog mode corresponding to the test requirements, the operating parameters of multiple atomizers in the test area are determined. Environmental monitoring equipment was used to collect data on the fog conditions within the test area. The difference value is obtained by comparing the fog state in the test area with the fog parameters corresponding to the fog mode; If the difference value is less than a preset value, the autonomous vehicle is controlled to perform an autonomous driving test in the test area, and the operating data of the autonomous vehicle is collected. Based on the operational data of the autonomous vehicle, the safety performance of the autonomous vehicle in foggy environments is determined.

2. The fog perception test method for autonomous vehicles according to claim 1, characterized in that, The construction of the droplet dynamics model based on fluid mechanics principles includes: Based on the principles of fluid mechanics, a droplet dynamics model is constructed to determine the droplet velocity and droplet falling angle.

3. The fog perception test method for autonomous vehicles according to claim 2, characterized in that, The process of constructing a droplet dynamics model based on fluid mechanics principles to determine droplet velocity and droplet fall angle includes: The formula for calculating the fog velocity is: ； in, It is the droplet velocity. It is the radius of the fog droplet. It is gravitational acceleration. It is the density of water. It is the air drag coefficient. It is air density; The formula for calculating the droplet falling angle is: ； in, It is the angle at which the fog droplets fall. It's wind speed. It is the vertical falling speed of the fog droplets.

4. The fog perception test method for autonomous vehicles according to claim 1, characterized in that, The determination of the operating parameters of multiple atomizers within the test area based on the fog mode corresponding to the test requirements includes: Based on the fog mode corresponding to the test requirements, the multiple atomizers in the test area are divided into multiple control sub-areas; Based on the fog mode corresponding to the test requirements, the fog output and atomizer activation frequency of each control sub-zone are determined.

5. The fog perception test method for autonomous vehicles according to claim 1, characterized in that, The use of environmental monitoring equipment to collect data on the fog conditions within the test area includes: The system uses a camera, lidar, humidity sensor, and anemometer to collect fog images, fog point clouds, fog concentration, and wind speed within the test area.

6. The fog perception test method for autonomous vehicles according to claim 1, characterized in that, The fog perception test method for autonomous vehicles also includes: If the difference value is greater than or equal to the preset value, the operating parameters of multiple atomizers in the test area are adjusted until the difference value is less than the preset value.

7. The fog perception test method for autonomous vehicles according to claim 1, characterized in that, The determination of the safety performance of the autonomous vehicle in foggy conditions based on the vehicle's operational data includes: Based on the operating data of the autonomous vehicle, the target recognition accuracy, path tracking error, and number of emergency braking operations of the autonomous vehicle are calculated. The safety performance of the autonomous vehicle in foggy conditions is determined based on the target recognition accuracy, the path tracking error, and the number of emergency braking operations.

8. A fog perception testing device for autonomous vehicles, characterized in that, include: The fog droplet model building module is used to construct fog droplet dynamic models based on fluid mechanics principles; wherein, the fog droplet dynamic model represents the force state, sedimentation trajectory and spatial distribution law of fog droplets in the air; A fog pattern generation module is used to generate multiple fog patterns based on the fog droplet dynamics model; wherein each fog pattern corresponds to a set of fog parameters; The atomization parameter determination module is used to determine the operating parameters of multiple atomizers in the test area based on the fog mode corresponding to the test requirements. A fog condition monitoring module is used to collect fog conditions within the test area using environmental monitoring equipment. The parameter difference comparison module is used to compare the fog state in the test area with the fog parameters corresponding to the fog mode to obtain the difference value; The data acquisition module is used to control the autonomous vehicle to perform an autonomous driving test in the test area if the difference value is less than a preset value, and to collect the operating data of the autonomous vehicle. The safety performance evaluation module is used to determine the safety performance of the autonomous vehicle in foggy environments based on the vehicle's operating data.

9. A computer-readable storage medium, characterized in that, The storage medium stores a computer program for performing the method described in any one of claims 1-7.

10. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is used to execute the method described in any one of claims 1-7.

Images