Method, device and vehicle system for cleaning a window of a sensor of a vehicle

Abstract

The application provides a method, device and vehicle system for cleaning a window of a sensor of a vehicle. The method processes images collected by a shooting device, point clouds collected by a laser radar, weather information and current rainfall to obtain a dirt judgment result and a current dirt type. The dirt judgment result represents whether dirt appears on the window of the sensor, and the current dirt type is sludge-based dirt or rainwater-based dirt. In the case that the dirt judgment result represents that dirt appears on the window of the sensor, a first processing mode or a second processing mode is executed, so that the application can more accurately clean the window of the sensor compared with the prior art, and the detection result of the sensor is more consistent with the actual working condition, thereby solving the problem that the prior art uses a single image to identify dirt on the window of the sensor of the vehicle, which easily makes the dirt judgment result inconsistent with the actual situation, thereby causing a shielding effect on the driver's line of sight and easily causing serious safety hazards.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle control, in particular to a method and device for cleaning a sensor window of a vehicle and a vehicle system. BACKGROUND

[0002] An autonomous vehicle is equipped with a large number of optical sensors, such as cameras and laser radars, to perceive the external environment. These optical sensors have high cleanliness requirements for the surface of their windows. If the surface of the window of an optical sensor of an autonomous vehicle is covered with rainwater, mud, or other pollutants during driving, the vehicle will not be able to normally perceive real external environment information, which will further result in incorrect judgments and execution strategies and cause serious safety hazards.

[0003] The existing solution uses a single image to identify dirt on the window of a vehicle, which can result in a dirt determination result that does not match the actual situation, and further cause a blocking effect on the driver's line of sight and serious safety hazards. SUMMARY

[0004] The main purpose of the present application is to provide a method and device for cleaning a sensor window of a vehicle and a vehicle system to at least solve the problem that the existing solution uses a single image to identify dirt on the window of a vehicle, which can result in a dirt determination result that does not match the actual situation, and further cause a blocking effect on the driver's line of sight and serious safety hazards.

[0005] To achieve the above purpose, according to one aspect of the present application, a method for cleaning a sensor window of a vehicle is provided, which comprises:

[0006] acquiring an image collected by a shooting device, a point cloud collected by a laser radar, weather information, and a current rainfall, the current rainfall being a rainfall at a current time collected by a rainfall sensor, the weather information at least including a rainfall monitoring result and a wind speed, the rainfall monitoring result indicating whether it is raining in an environment where the vehicle is located;

[0007] processing the image collected by the shooting device, the point cloud collected by the laser radar, the weather information, and the current rainfall to obtain a dirt determination result and a current dirt type, the dirt determination result indicating whether dirt appears on the window of the sensor, and the current dirt type being mud-based dirt or rainwater-based dirt;

[0008] In a case where the dirt judgment result indicates that the window of the sensor is dirty, a first processing mode or a second processing mode is executed, the first processing mode indicating that the window is cleaned by a wiper, and the second processing mode indicating that the window is cleaned by water spraying and air spraying or only by air spraying, and in a case where the second processing mode is executed, the window is cleaned by water spraying and air spraying or only by air spraying according to the current dirt type.

[0009] Optionally, the first processing mode or the second processing mode is executed, including: in a case where the installation position of a target sensor is a windshield of the vehicle, the first processing mode is executed, the target sensor indicating a sensor whose window is dirty; and in a case where the installation position of the target sensor is a position other than the windshield of the vehicle, the second processing mode is executed.

[0010] Optionally, the window is cleaned by water spraying and air spraying or only by air spraying according to the current dirt type, including: in a case where it is determined that the current dirt type is the sludge type, the window is first cleaned by water spraying and then cleaned by air spraying to remove residual water drops; and in a case where it is determined that the current dirt type is the rain type, the window is cleaned by high-pressure gas generated by an air blower or an air compressor.

[0011] Optionally, the dirt judgment result and the current dirt type are obtained by processing the image collected by the shooting device, the point cloud collected by the laser radar, the weather information and the current rainfall, including: the first dirt degree and the first dirt type determination coefficient are obtained by processing the image collected by the shooting device by using a deep learning model; the second dirt degree and the second dirt type determination coefficient are obtained by processing the point cloud collected by the laser radar by using a cross-validation method; the third dirt degree and the third dirt type determination coefficient are obtained by processing the weather information in a mapping relationship; the fourth dirt degree and the fourth dirt type determination coefficient are obtained by processing the current rainfall in a mapping relationship; the first dirt degree, the second dirt degree, the third dirt degree and the fourth dirt degree are processed by weighted summation to obtain a final dirt result judgment value, and the first dirt type determination coefficient, the second dirt type determination coefficient, the third dirt type determination coefficient and the fourth dirt type determination coefficient are processed by weighted summation to obtain a final dirt type judgment value; the dirt judgment result is determined according to the size of the final dirt result judgment value, and the current dirt type is determined according to the size of the final dirt type judgment value.

[0012] Optionally, the first dirtiness degree, the second dirtiness degree, the third dirtiness degree and the fourth dirtiness degree are subjected to weighted summation processing to obtain a final dirtiness result judgment value, comprising:

[0013] Different weights are assigned to the first dirtiness degree, the second dirtiness degree, the third dirtiness degree and the fourth dirtiness degree;

[0014] Based on the assigned weights, the first dirtiness degree, the second dirtiness degree, the third dirtiness degree and the fourth dirtiness degree are subjected to weighted summation processing to obtain the final dirtiness result judgment value.

[0015] Optionally, assigning different weights to the first dirtiness degree, the second dirtiness degree, the third dirtiness degree and the fourth dirtiness degree comprises: determining a first preset weight corresponding to the first dirtiness degree, a second preset weight corresponding to the second dirtiness degree, a third preset weight corresponding to the third dirtiness degree and a fourth preset weight corresponding to the fourth dirtiness degree in a mapping relationship.

[0016] Optionally, the method further comprises: in the case of receiving a cleaning instruction, executing the first processing mode or the second processing mode based on the cleaning instruction.

[0017] Optionally, the method further comprises: obtaining the temperature of each actuator and the pressure and flow of each water spraying system to obtain monitoring data; and generating prompt information to prompt the size of the monitoring data or generating early warning information to prompt that the monitoring data is out of standard according to the size of the monitoring data.

[0018] According to another aspect of the present application, a window cleaning device of a sensor of a vehicle is provided, which comprises:

[0019] The acquisition unit is configured to acquire an image collected by a photographing device, a point cloud collected by a laser radar, weather information and a current rainfall, the current rainfall being a rainfall at a current time collected by a rainfall sensor, and the weather information including at least a rainfall monitoring result and a wind speed, the rainfall monitoring result indicating whether it is raining in an environment where the vehicle is located;

[0020] The first processing unit is configured to process the image collected by the photographing device, the point cloud collected by the laser radar, the weather information and the current rainfall to obtain a dirtiness judgment result and a current dirtiness type, the dirtiness judgment result indicating whether dirtiness appears on the window of the sensor, and the current dirtiness type being sludge-based dirtiness or rainwater-based dirtiness.

[0021] The second processing unit is configured to execute a first processing mode or a second processing mode in a case where the dirt judgment result indicates that the view window of the sensor is dirty, the first processing mode indicating that the rain wiper is controlled to clean the view window, and the second processing mode indicating that the view window is cleaned by spraying water and air or by spraying air only, and in a case where the second processing mode is executed, the view window is cleaned by spraying water and air or by spraying air only according to the current dirt type.

[0022] According to another aspect of the present application, a vehicle system is provided, comprising one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs comprise a program for executing any one of the methods.

[0023] According to the technical solution of the present application, the image collected by the shooting device, the point cloud collected by the laser radar, the weather information and the current rainfall are processed to obtain a dirt judgment result and a current dirt type, the dirt judgment result indicating whether the view window of the sensor is dirty, and the current dirt type being sludge type dirt or rainwater type dirt; in a case where the dirt judgment result indicates that the view window of the sensor is dirty, a first processing mode or a second processing mode is executed, so that the present application can more accurately clean the view window of the sensor compared with the prior art, the detection result of the sensor is more consistent with the actual working condition, and the problem that the prior art uses a single image to identify the dirt of the view window of the sensor of the vehicle, so that the dirt judgment result is not consistent with the actual situation, thereby causing the view of the driver to be blocked and serious safety hazards are easily caused, is solved. BRIEF DESCRIPTION OF DRAWINGS

[0024] The drawings accompanying the specification of the present application serve to provide a further understanding of the present application, the illustrative embodiments of the present application and their descriptions serve to explain the present application, and do not constitute an improper limitation on the present application. In the drawings:

[0025] Figure 1 A flowchart of a view window cleaning method of a sensor of a vehicle is shown according to an embodiment of the present application;

[0026] Figure 2 A schematic diagram of a view window cleaning method of a sensor of a vehicle is shown according to an embodiment of the present application;

[0027] Figure 3 A structural block diagram of a view window cleaning device of a sensor of a vehicle is shown according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] It should be noted that the embodiments and features of the embodiments in the present application can be combined with each other in the case of no conflict. The present application will be described in detail below with reference to the drawings and in combination with the embodiments.

[0029] In order for those skilled in the technical field to better understand the scheme of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the scope of protection of the present application.

[0030] It should be noted that the terms "first", "second" and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily have to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] As introduced in the background, in order to realize the perception of the external environment, the automatic driving vehicle is equipped with a large number of optical sensors such as cameras, laser radars, etc. The optical sensors have a high requirement for the cleanliness of the surface of their view window. If the surface of the view window of the optical sensor of the automatic driving vehicle is covered by rainwater, mud and other pollutants during driving, the real environment information outside the vehicle cannot be normally perceived, which further leads to incorrect judgment and execution strategy, causing serious safety hazards. In order to solve the problem that the existing scheme uses a single image to identify the dirt on the view window of the vehicle, which easily makes the dirt determination result inconsistent with the actual situation, and further causes the occlusion effect on the driver's sight and easily causes serious safety hazards, the embodiments of the present application provide a view window cleaning method, device and vehicle system of a sensor of a vehicle.

[0032] The technical solutions in the embodiments of the present application will be described clearly and completely below in combination with the drawings in the embodiments of the present application.

[0033] A method for cleaning a window of a sensor of a vehicle is provided in the present embodiment. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown.

[0034] Figure 1 FIG. 1 is a flowchart of a method for cleaning a window of a sensor of a vehicle according to an embodiment of the present application. As shown in the figure, the method comprises the following steps: Figure 1

[0035] In step S101, an image captured by a shooting device, a point cloud captured by a laser radar, weather information and a current rainfall are obtained. The current rainfall is the rainfall at the current time captured by a rainfall sensor. The weather information at least includes a rainfall monitoring result and a wind speed. The rainfall monitoring result indicates whether it is raining in the environment where the vehicle is located.

[0036] The weather information can further include whether it is a sunny day.

[0037] Specifically, as shown in FIG. 2, the method comprises the following steps: Figure 2 ​The window cleaning architecture of the sensors of the vehicle includes a camera imaging quality judgment module, a laser radar point cloud quality judgment module, a weather information module, a rainfall sensor module, and a manual trigger button module. The current dirty scene is judged, the current dirty type and dirty degree are determined, the corresponding cleaning means and parameters are selected, and the corresponding cleaning instructions are transmitted to the execution link / cleaning link. For the image collected by the shooting device: the camera imaging quality judgment module uses a photo with camera imaging quality results manually annotated, and an algorithm model trained by deep learning. The algorithm model can process each frame of image of each camera of the autonomous vehicle and judge whether the frame of image has dirt. If there is dirt, the algorithm model further outputs information in two dimensions of dirty type and dirty degree. For the point cloud collected by the laser radar: the laser radar point cloud quality judgment module counts the number and distribution uniformity of the point cloud received by the laser radar, and cross- verifies the detection data of the sensors such as the camera and the millimeter wave radar, and then judges whether there is dirt / obstruction on the surface of the laser radar. In a typical traffic scene, the number of point clouds received by the laser radar has an interval range. When the number of point clouds received by the laser radar is continuously and significantly less than the lower limit value of the interval, and other sensors (such as the camera and the millimeter wave radar) can detect an obstacle / traffic participant in a certain direction, and the laser radar has point cloud loss at the corresponding position, it can be considered that the laser radar has dirt / obstruction at the corresponding position. For the weather information: the weather information module constructs a real-time monitoring and forecasting system of meteorological information with a spatial granularity of 1 km and a time granularity of 5 minutes or even shorter for an autonomous vehicle fleet and a single vehicle. The system pushes the weather information to the autonomous vehicle fleet and the single vehicle in real time. For the current rainfall: the rainfall sensor module judges whether it is raining and the size of the rainfall through the installed rainfall sensor.

[0038] The upper computer includes a camera imaging quality judgment module, a laser radar point cloud quality judgment module, a weather information module, a rainfall sensor module, and a manual trigger button module. The lower computer includes a controller of a cleaning device (composed of a water spraying device, an air spraying device, and a wiper). The monitoring device includes sensors such as pressure, flow, and temperature. The monitoring device communicates with the lower computer through a serial port such as RS485 or Lin communication protocol. The upper computer and the lower computer communicate through CAN.

[0039] In step S102, the image collected by the shooting device, the point cloud collected by the laser radar, the weather information, and the current rainfall are processed to obtain a dirty judgment result and a current dirty type. The dirty judgment result represents whether the window of the sensor has dirt. The current dirty type is sludge type dirty or rain type dirty.

[0040] The deep learning model includes a convolutional neural network, a recurrent neural network, an attention mechanism model, and a point cloud processing network.

[0041] Specifically, the deep learning model can improve accuracy through a large amount of training data, effectively identify and analyze the image collected by the shooting device, the point cloud image, the weather information, and the rainfall data, so as to obtain a more accurate dirt degree evaluation result. The deep learning model can also automatically process and analyze multiple data sources, save labor and time costs, improve work efficiency, and quickly process a large amount of data and update the dirt degree evaluation result in real time to provide timely decision support.

[0042] In an embodiment of the present application, the shooting device image, the laser radar collected point cloud, the weather information, and the current rainfall are processed to obtain a dirt judgment result and a current dirt type, including: using a deep learning model to process the shooting device image to obtain a first dirt degree and a first dirt type determination coefficient; using a cross-validation method to process the laser radar collected point cloud to obtain a second dirt degree and a second dirt type determination coefficient; using a mapping relationship to process the weather information to obtain a third dirt degree and a third dirt type determination coefficient; using a mapping relationship to process the current rainfall to obtain a fourth dirt degree and a fourth dirt type determination coefficient; weighting and summing the first dirt degree, the second dirt degree, the third dirt degree, and the fourth dirt degree to obtain a final dirt result judgment value, and weighting and summing the first dirt type determination coefficient, the second dirt type determination coefficient, the third dirt type determination coefficient, and the fourth dirt type determination coefficient to obtain a final dirt type judgment value; determining the dirt judgment result according to the size of the final dirt result judgment value, and determining the current dirt type according to the size of the final dirt type judgment value.

[0043] Specifically, the dirtiness degree and the dirtiness type determination coefficient are also in the form of numerical values. The image captured by the camera is input into a pre-trained deep learning model, which can identify and quantify the dirtiness degree and type, and the output is the first dirtiness degree and the first dirtiness type determination coefficient. One or more algorithms are used to cross-validate the laser radar point cloud data, and the dirtiness degree of the laser radar surface is determined by the point cloud density drop and uneven distribution indicators, and the output is the second dirtiness degree and the second dirtiness type determination coefficient. The mapping relationship is used to map the corresponding third dirtiness degree and third dirtiness type determination coefficient according to the weather information. The current rainfall and weather information are the same, and will not be repeated here. By setting the corresponding threshold, the final dirtiness result is determined according to the size of the above-mentioned final dirtiness result determination value, and the current dirtiness type is determined according to the size of the above-mentioned final dirtiness type determination value. Here, it will not be repeated.

[0044] By combining the analysis of the deep learning model on the image, the cross-validation of the point cloud data, the mapping of the weather information, and the real-time monitoring of the rainfall, the dirtiness degree and type are comprehensively judged from multiple dimensions. This multi-source data fusion method can effectively improve the accuracy and reliability of the judgment, and reduce the possibility of misjudgment and omission. The introduction of weather information and rainfall monitoring enables the system to respond quickly according to real-time environmental conditions, predict potential dirtiness, especially for upcoming rain-related dirtiness, and prepare and respond in advance, enhancing the environmental adaptability and early warning capability of the system. By weighting and summing the dirtiness determination coefficients from different sources through algorithms, the system can automatically choose the optimal cleaning strategy according to the specific weight of each dirtiness type and degree without human intervention, improving the intelligent level of the cleaning system. Through effective judgment of the dirtiness degree and type, the system can intelligently select the cleaning method and intensity, avoiding over-cleaning or under-cleaning, and reasonably utilizing cleaning resources to reduce the operating cost of the cleaning system. The real-time monitoring and rapid processing mechanism enables the system to quickly respond to dirtiness changes and promptly start the cleaning process, reducing the perception delay and ensuring the real-time and accurate perception of the external environment information by the autonomous vehicle. Through real-time monitoring and intelligent analysis, the system can not only judge the dirtiness, but also diagnose the running state of the cleaning system, detect potential faults in time, and perform preventive maintenance, reducing the performance degradation of the sensor caused by system failure. Accurate dirtiness type and degree judgment combined with efficient cleaning solutions ensure that the sensor can maintain good working condition at any time, which directly relates to the vehicle's perception ability and driving safety for autonomous vehicles, significantly improving the safety of the overall system operation.

[0045] The first dirtiness degree, the second dirtiness degree, the third dirtiness degree, and the fourth dirtiness degree are weighted and summed to obtain a final dirtiness result determination value, including:

[0046] different weights are assigned to the first dirtiness degree, the second dirtiness degree, the third dirtiness degree and the fourth dirtiness degree;

[0047] Based on the assigned weights, the first dirtiness degree, the second dirtiness degree, the third dirtiness degree and the fourth dirtiness degree are weighted and summed to obtain the final dirtiness result judgment value.

[0048] Among them, different weights are assigned to the first dirtiness degree, the second dirtiness degree, the third dirtiness degree and the fourth dirtiness degree, including: in a mapping relationship, determining a first preset weight corresponding to the first dirtiness degree, a second preset weight corresponding to the second dirtiness degree, a third preset weight corresponding to the third dirtiness degree and a fourth preset weight corresponding to the fourth dirtiness degree.

[0049] Specifically, different weights can be assigned to different dirtiness degrees in a mapping relationship. Different sensors and dirt sources have different effects on autonomous vehicles, and assigning weights can more accurately reflect the influence of various dirt information on the overall perception system, so as to make cleaning decisions that are more in line with actual situations. By adjusting the weights, the system can dynamically optimize the cleaning strategy according to the changes of different environments and conditions. For example, in rainy days, the weight of rainfall information can be increased to pay more attention to the influence of rain on sensors. Even if a certain sensor or information source fails, the mechanism of assigning weights and weighted sum can ensure that the system makes reasonable cleaning judgments based on other valid information, enhancing the stability and reliability of the system. According to the specific dirtiness degree and type of each sensor, the system can intelligently decide the allocation of cleaning resources, such as the amount of cleaning agent, water pressure and air flow size, to avoid resource waste and improve cleaning efficiency. Through fine management, the system can respond more quickly and accurately to different dirt conditions, reducing the impact on sensor performance, thereby improving the overall operation efficiency of autonomous vehicles and the safety, comfort of users. In different operating environments and time conditions, the influence of dirt on sensors may be very different. The dynamic weight assignment mechanism enables the system to better adapt to various complex scenarios and ensure effective cleaning decisions in any situation.

[0050] In step S103, when the dirty judgment result indicates that the window of the sensor is dirty, a first processing mode or a second processing mode is executed, the first processing mode indicates that the wiper is controlled to clean the window, the second processing mode indicates that the window is cleaned by spraying water and air or only by spraying air, and when the second processing mode is executed, the window is cleaned by spraying water and air or only by spraying air according to the current dirty type.

[0051] In the above steps, the dirty judgment result and the current dirty type are obtained by processing the image collected by the shooting device, the point cloud collected by the laser radar, the weather information and the current rainfall, the dirty judgment result indicates whether the window of the sensor is dirty, and the current dirty type is sludge type dirty or rain type dirty; when the dirty judgment result indicates that the window of the sensor is dirty, the first processing mode or the second processing mode is executed, so that the application can clean the window of the sensor more accurately compared with the prior art, the detection result of the sensor is more consistent with the actual working condition, and the problem that the prior art uses a single image to identify the dirty of the window of the sensor of the vehicle, so that the dirty judgment result is not consistent with the actual situation, and the driver's line of sight is blocked and serious safety hazards are easily caused is solved.

[0052] In step S103, when the dirty judgment result indicates that the window of the sensor is dirty, a first processing mode or a second processing mode is executed, the first processing mode indicates that the wiper is controlled to clean the window, the second processing mode indicates that the window is cleaned by spraying water and air or only by spraying air, and when the second processing mode is executed, the window is cleaned by spraying water and air or only by spraying air according to the current dirty type.

[0053] The sensors on the windshield can be cleaned using the existing wiper system of the vehicle, which not only reduces the use of additional water and air spraying equipment, but also effectively utilizes existing vehicle hardware resources, reducing the complexity and cost of the cleaning system. The windshield sensors use wiper cleaning, which fully considers the specific needs of the windshield during driving, such as removing raindrops, dust, etc., to ensure good decontamination effect. For sensors in other locations of the vehicle, water and / or air spraying is used to directly clean the specific environment where the target sensor is located. For sensors in non-windshield locations, direct water spraying may leave water droplets, which can affect the optical performance of the sensor. The water spraying and air spraying strategy can effectively remove water droplets, avoiding secondary pollution and ensuring the dryness and cleanliness of the sensor surface. Sensors in different locations of the vehicle may face different forms of pollution and cleaning needs. For example, sensors behind the windshield may be mainly affected by raindrops and dust, while sensors on the roof or tail of the vehicle may be more prone to mud contamination. This design can adapt to various complex environments by intelligently selecting cleaning methods to ensure the cleanliness of all sensors. The selection and execution of this processing method are fully controlled by the controller based on the sensor location, reducing the need for human intervention and improving the automation and intelligence level of the cleaning process, ensuring the timeliness and accuracy of cleaning. The cleaning of sensors on the windshield is completed through the wiper system, which does not cause additional interference to the vehicle driving, while the cleaning of sensors in other locations is completed quickly during vehicle driving or stopping, without affecting the normal operation of autonomous driving.

[0054] Among them, according to the above current dirt type, the above view window is cleaned by using water spraying and air spraying, or only using air spraying, including: in the case of determining that the above current dirt type is the above mud type dirt, first using water spraying to remove, and then using air spraying to clean the remaining water droplets; in the case of determining that the above current dirt type is the above rain type dirt, using high-pressure gas generated by a blower or an air compressor to clean the above view window with dirt.

[0055] Specifically, for sludge-like dirt, which is usually sticky and difficult to remove by air flow alone, using water spray to flush first can effectively remove the mud, and the subsequent air spray step quickly removes water marks, avoiding water stains on the optical sensor surface, improving cleaning efficiency. For rainwater-like dirt, direct air spray cleaning can quickly evaporate or blow away water droplets, avoiding unnecessary water waste and quickly restoring sensor performance. Adopting the appropriate cleaning method is crucial to protect the optical surface of the sensor. Water spray cleaning is suitable for removing sticky dirt, while air spray is suitable for removing liquid residues. This strategy ensures that the sensor surface is not damaged while maintaining optimal optical performance. By intelligently selecting the cleaning method, unnecessary cleaning steps are avoided, reducing the consumption of cleaning materials (such as water), lowering maintenance costs and energy consumption of the cleaning system. At the same time, efficient cleaning reduces the frequency of sensor failure caused by dirt, indirectly reducing vehicle maintenance and repair costs. This strategy can flexibly adjust the cleaning method according to the actual pollution situation, quickly adapt and effectively clean whether it is a muddy road or a rainy day, ensuring consistent performance of the sensor in different environments. Timely and correct cleaning methods can quickly restore the normal working state of the sensor, reduce the perception errors caused by dirt, and thus improve the safety and reliability of autonomous vehicles, especially in harsh weather conditions.

[0056] In an embodiment of the present application, the method further comprises: in the case of receiving a cleaning instruction, executing the first processing mode or the second processing mode based on the cleaning instruction.

[0057] Specifically, for the manual trigger button module, the automatic driving vehicle end and the remote monitoring end are equipped with physical / virtual buttons, which can be triggered by the on-board personnel or remote monitoring personnel when necessary to send cleaning instructions.

[0058] In an embodiment of the present application, the method further comprises: obtaining the temperature of each actuator and the pressure and flow of each water spray system to obtain monitoring data; and generating a prompt message to prompt the size of the monitoring data or generating a warning message to prompt that the monitoring data is out of standard according to the size of the monitoring data.

[0059] Specifically, for the monitoring device, the pressure and flow of the main road and important branches are monitored and recorded in real time through pressure sensors and flow sensors arranged in the main road and branch of the air / water spray system; in addition, temperature sensors are arranged on the main actuators (air compressor / air blower / water pump, etc.) of the cleaning link / module to monitor and record the temperature rise of these actuators in real time. When the pressure, flow or temperature is abnormal, corresponding fault diagnosis is made, and on-board personnel, remote monitoring personnel and vehicle maintenance personnel are reminded to repair through screen pop-up windows, voice, SMS, etc.

[0060] It is noted that the steps illustrated in the flowcharts of the figures can be executed by computer systems such as a group of computing devices, and that although the steps are presented in the order shown, the steps can be executed in a different order than those shown or described.

[0061] The vehicle sensor window cleaning device provided by the embodiments of the present application can be used to execute the vehicle sensor window cleaning method provided by the embodiments of the present application. The device is used to realize the above-mentioned embodiments and preferred embodiments, and will not be described again. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware can also be implemented and conceived.

[0062] The vehicle sensor window cleaning device provided by the embodiments of the present application is described below.

[0063] Figure 3 is a structural block diagram of a vehicle sensor window cleaning device provided according to an embodiment of the present application. As shown in Figure 3 The device includes:

[0064] The acquisition unit 31 is configured to acquire the image collected by the photographing device, the point cloud collected by the laser radar, weather information, and current rainfall. The current rainfall is the rainfall at the current time collected by the rainfall sensor. The weather information includes at least rainfall monitoring results and wind speed. The rainfall monitoring results represent whether it is raining in the environment where the vehicle is located.

[0065] The first processing unit 32 is configured to process the image collected by the photographing device, the point cloud collected by the laser radar, the weather information, and the current rainfall to obtain a dirt judgment result and a current dirt type. The dirt judgment result represents whether the sensor window is dirty. The current dirt type is sludge-based dirt or rainwater-based dirt.

[0066] The second processing unit 33 is configured to execute a first processing mode or a second processing mode in the case where the dirt judgment result represents that the sensor window is dirty. The first processing mode represents controlling the wiper to clean the window. The second processing mode represents cleaning the window by spraying water and air or only by spraying air. In the case of executing the second processing mode, the window is cleaned by spraying water and air or only by spraying air according to the current dirt type.

[0067] In the device, the dirty judgment result and the current dirty type are obtained by processing the image collected by the shooting device, the point cloud collected by the laser radar, the weather information and the current rainfall, the dirty judgment result represents whether the window of the sensor is dirty, and the current dirty type is sludge dirty or rainwater dirty; in the case that the dirty judgment result represents that the window of the sensor is dirty, the first processing mode or the second processing mode is executed, so that the application can clean the window of the sensor more accurately compared with the prior art, the detection result of the sensor is more consistent with the actual working condition, and thus the problem that the prior art uses a single image to identify the dirty of the window of the sensor of the vehicle, so that the dirty judgment result is not consistent with the actual situation, and the driver's sight is blocked and serious safety hazards are easily caused is solved.

[0068] In an embodiment of the application, the second processing unit includes a first processing module and a second processing module, the first processing module is used to execute the first processing mode when the installation position of the target sensor is the windshield of the vehicle, and the target sensor represents the sensor whose window is dirty; and the second processing module is used to execute the second processing mode when the installation position of the target sensor is other than the windshield in the vehicle.

[0069] In an embodiment of the application, the second processing unit includes a third processing module and a fourth processing module, the third processing module is used to first remove the dirt by spraying water and then clean the remaining water droplets by spraying air when it is determined that the current dirty type is the sludge dirty; and the fourth processing module is used to clean the dirty window by using high-pressure gas generated by an air blower or an air compressor when it is determined that the current dirty type is the rainwater dirty.

[0070] In an embodiment of the present application, the first processing unit includes a fifth processing module, a sixth processing module, a seventh processing module, an eighth processing module, a ninth processing module, and a tenth processing module. The fifth processing module is configured to process the image collected by the camera using a deep learning model to obtain a first dirt level and a first dirt type determination coefficient. The sixth processing module is configured to process the point cloud collected by the laser radar using a cross-validation method to obtain a second dirt level and a second dirt type determination coefficient. The seventh processing module is configured to process the weather information in a mapping relationship to obtain a third dirt level and a third dirt type determination coefficient. The eighth processing module is configured to process the current rainfall in a mapping relationship to obtain a fourth dirt level and a fourth dirt type determination coefficient. The ninth processing module is configured to perform weighted sum processing on the first dirt level, the second dirt level, the third dirt level, and the fourth dirt level to obtain a final dirt result determination value, and perform weighted sum processing on the first dirt type determination coefficient, the second dirt type determination coefficient, the third dirt type determination coefficient, and the fourth dirt type determination coefficient to obtain a final dirt type determination value. The tenth processing module is configured to determine the dirt determination result according to the size of the final dirt result determination value, and determine the current dirt type according to the size of the final dirt type determination value.

[0071] In an embodiment of the present application, the ninth processing module includes a first processing submodule and a second processing submodule. The first processing submodule is configured to assign different weights to the first dirt level, the second dirt level, the third dirt level, and the fourth dirt level. The second processing submodule is configured to perform weighted sum processing on the first dirt level, the second dirt level, the third dirt level, and the fourth dirt level based on the assigned weights to obtain the final dirt result determination value.

[0072] In an embodiment of the present application, the first processing submodule includes a third processing submodule configured to determine a first preset weight corresponding to the first dirt level, a second preset weight corresponding to the second dirt level, a third preset weight corresponding to the third dirt level, and a fourth preset weight corresponding to the fourth dirt level in a mapping relationship.

[0073] In an embodiment of the present application, the device further includes a third processing unit configured to execute the first processing mode or the second processing mode based on a cleaning instruction when the cleaning instruction is received.

[0074] In an embodiment of the present application, the device further comprises a fourth processing unit and a fifth processing unit: the fourth processing unit is configured to acquire the temperature of each actuator and the pressure and flow of each water spraying system to obtain monitoring data; and the fifth processing unit is configured to generate prompt information to prompt the size of the monitoring data or generate early warning information to prompt that the monitoring data is out of range according to the size of the monitoring data.

[0075] The window cleaning device of the sensor of the vehicle comprises a processor and a memory, the acquisition unit, the first processing unit and the second processing unit are stored in the memory as program units, and the corresponding functions are realized by the processor executing the program units stored in the memory. The modules are located in the same processor; or, the modules are located in different processors in any combination.

[0076] The processor comprises a core, and the core retrieves the corresponding program unit from the memory. The core can be one or more, and the problem that the existing scheme uses a single image to identify the dirt of the window of the vehicle is solved by adjusting the core parameters, so that the dirt determination result is easy to be inconsistent with the actual situation, thereby causing the occlusion effect on the driver's sight and easily causing serious safety hazards.

[0077] The memory can include non-permanent memory in a computer readable medium, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.

[0078] The embodiment of the present application provides a computer readable storage medium, and the computer readable storage medium comprises a stored program, wherein the computer readable storage medium controls a device where the computer readable storage medium is located to execute the window cleaning method of the sensor of the vehicle when the program runs.

[0079] The embodiment of the present application provides a processor, and the processor is used for running a program, wherein the processor executes the window cleaning method of the sensor of the vehicle when the program runs.

[0080] The embodiment of the present application provides a device, the device comprises a processor, a memory and a program stored on the memory and executable on the processor, when the processor executes the program, at least the following steps are implemented: acquiring an image collected by a shooting device, a point cloud collected by a laser radar, weather information and current rainfall, the image collected by the shooting device is a video of a window of a vehicle shot by the shooting device, and the point cloud collected by the laser radar is a point cloud image of the window of the vehicle scanned by the laser radar; a deep learning model is used to process the image collected by the shooting device, the point cloud collected by the laser radar, the weather information and the current rainfall respectively, to obtain a first dirt degree, a second dirt degree, a third dirt degree and a fourth dirt degree, and weighted sum processing is performed on the first dirt degree, the second dirt degree, the third dirt degree and the fourth dirt degree to obtain a final judgment value, and whether dirt appears on the window is determined according to the size of the final judgment value; in the case that it is determined that dirt appears on the window, a first processing mode or a second processing mode is executed, the first processing mode represents controlling a wiper to clean the window, and the second processing mode represents cleaning the window in a water spraying and air spraying mode or only in an air spraying mode. The device in the present application can be a server, a PC, a PAD, a mobile phone and the like.

[0081] The present application also provides a computer program product, when executed on a data processing device, is suitable for executing a program initialized with at least the following method steps: acquiring an image collected by a shooting device, a point cloud collected by a laser radar, weather information and current rainfall, the image collected by the shooting device is a video of a window of a vehicle shot by the shooting device, and the point cloud collected by the laser radar is a point cloud image of the window of the vehicle scanned by the laser radar; a deep learning model is used to process the image collected by the shooting device, the point cloud collected by the laser radar, the weather information and the current rainfall respectively, to obtain a first dirt degree, a second dirt degree, a third dirt degree and a fourth dirt degree, and weighted sum processing is performed on the first dirt degree, the second dirt degree, the third dirt degree and the fourth dirt degree to obtain a final judgment value, and whether dirt appears on the window is determined according to the size of the final judgment value; in the case that it is determined that dirt appears on the window, a first processing mode or a second processing mode is executed, the first processing mode represents controlling a wiper to clean the window, and the second processing mode represents cleaning the window in a water spraying and air spraying mode or only in an air spraying mode.

[0082] The application also provides a vehicle system, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs comprise a program for executing any of the above methods. By processing the image collected by the shooting device, the point cloud collected by the laser radar, the weather information and the current rainfall, a dirty judgment result and a current dirty type are obtained, the dirty judgment result represents whether the window of the sensor is dirty, and the current dirty type is sludge type dirty or rainwater type dirty; in the case that the dirty judgment result represents that the window of the sensor is dirty, a first processing mode or a second processing mode is executed, so that the application can more accurately clean the window of the sensor compared with the prior art, so that the detection result of the sensor is more consistent with the actual working condition, thereby solving the problem that the prior art uses a single image to identify the dirty of the window of the sensor of the vehicle, so that the dirty judgment result is not consistent with the actual situation, thereby causing the driver's line of sight to be blocked and easily causing serious safety hazards.

[0083] Obviously, those skilled in the art should understand that the modules or steps of the application described above can be realized by general computing devices, which can be concentrated on a single computing device or distributed on a network composed of multiple computing devices, and they can be realized by program codes executable by the computing devices, so that they can be stored in storage devices and executed by the computing devices, and in some cases, the steps shown or described can be executed in different order, or they can be manufactured into individual integrated circuit modules, or multiple modules or steps can be manufactured into a single integrated circuit module. Therefore, the application is not limited to any specific combination of hardware and software.

[0084] Those skilled in the art should understand that the embodiments of the application can be provided as methods, systems, or computer program products. Therefore, the application can be in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the application can be in the form of a computer program product implemented on one or more computer usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer usable program codes.

[0085] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.

[0086] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.

[0087] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks.

[0088] In one typical configuration, the computing device includes one or more processors, input / output interfaces, network interfaces, and memory.

[0089] The memory can include non-persistent memory and / or persistent memory, such as flash memory, read-only memory (ROM), and / or volatile or non-volatile random access memory (RAM), among others. The memory is an example of computer-readable media.

[0090] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer-readable media does not include transitory media such as modulated data signals and carriers.

[0091] It should also be noted that the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, so that processes, methods, articles or devices including a series of elements not only include those elements, but also include other elements not explicitly listed or inherent to such processes, methods, articles or devices. Without more limitations, the element defined by the statement "including a" does not exclude the presence of additional identical elements in the process, method, article or device including the element.

[0092] From the above description, it can be seen that the above-mentioned embodiments of the present application achieve the following technical effects:

[0093] 1) The window cleaning method of the sensor of the vehicle of the present application, by processing the image collected by the shooting device, the point cloud collected by the laser radar, the weather information and the current rainfall, obtaining the dirt judgment result and the current dirt type, the dirt judgment result represents whether the window of the sensor is dirty, and the current dirt type is sludge type dirt or rain type dirt; in the case that the dirt judgment result represents that the window of the sensor is dirty, the first processing mode or the second processing mode is executed, so that the present application can more accurately clean the window of the sensor compared with the prior art, so that the detection result of the sensor is more consistent with the actual working condition, thereby solving the problem that the prior art uses a single image to identify the dirt of the window of the sensor of the vehicle, which is easy to make the dirt determination result inconsistent with the actual situation, thereby causing the driver's line of sight to be blocked and easy to cause serious safety hazards.

[0094] 2) The window cleaning device of the sensor of the vehicle of the application, by processing the image collected by the shooting device, the point cloud collected by the laser radar, the weather information and the current rainfall, the dirty judgment result and the current dirty type are obtained, the dirty judgment result represents whether the window of the sensor is dirty, the current dirty type is sludge type dirty or rain type dirty; in the case of dirty judgment result representing that the window of the sensor is dirty, the first processing mode or the second processing mode is executed, so that the application can more accurately clean the window of the sensor compared with the prior art, so that the detection result of the sensor is more consistent with the actual working condition, thereby solving the problem that the prior art uses a single image to identify the dirty of the window of the sensor of the vehicle, which is easy to make the dirty judgment result inconsistent with the actual situation, and further causes the occlusion effect of the driver's sight and easily causes serious safety hazard.

[0095] The above only describes the preferred embodiments of the application and is not intended to limit the application. Those skilled in the art can make various modifications and changes to the application. Any modification, equivalent replacement, improvement, etc. within the spirit and principles of the application shall be included in the protection scope of the application.

Claims

1. A method of cleaning a window of a sensor of a vehicle, characterized by, The method comprises the following steps: acquiring images collected by a shooting device, point clouds collected by a laser radar, weather information and current rainfall, the current rainfall being rainfall at a current time collected by a rainfall sensor, the weather information at least including rainfall monitoring results and wind speed, the rainfall monitoring results representing whether it is raining in an environment where the vehicle is located; processing the images collected by the shooting device, the point clouds collected by the laser radar, the weather information and the current rainfall to obtain a dirty judgment result and a current dirty type, the dirty judgment result representing whether a view window of a sensor is dirty, the current dirty type being sludge type dirty or rainwater type dirty, the sensor at least including a rainfall sensor, a shooting device and a laser radar; in a case where the dirty judgment result represents that the view window of the sensor is dirty, performing a first processing mode or a second processing mode, the first processing mode representing controlling a rain wiper to clean the view window, the second processing mode representing cleaning the view window by means of water spraying and air spraying or cleaning the view window by means of air spraying only, wherein in a case where the second processing mode is performed, the view window is cleaned by means of water spraying and air spraying or cleaned by means of air spraying only according to the current dirty type, processing the images collected by the shooting device, the point clouds collected by the laser radar, the weather information and the current rainfall to obtain a dirty judgment result and a current dirty type, comprising: processing the images collected by the shooting device by means of a deep learning model to obtain a first dirty degree and a first dirty type determination coefficient; processing the point clouds collected by the laser radar by means of cross-validation to obtain a second dirty degree and a second dirty type determination coefficient; processing the weather information by means of a mapping relationship to obtain a third dirty degree and a third dirty type determination coefficient; processing the current rainfall by means of a mapping relationship to obtain a fourth dirty degree and a fourth dirty type determination coefficient; performing weighted sum processing on the first dirty degree, the second dirty degree, the third dirty degree and the fourth dirty degree to obtain a final dirty result judgment value, and performing weighted sum processing on the first dirty type determination coefficient, the second dirty type determination coefficient, the third dirty type determination coefficient and the fourth dirty type determination coefficient to obtain a final dirty type judgment value; determining the dirty judgment result according to a size of the final dirty result judgment value, and determining the current dirty type according to a size of the final dirty type judgment value.

2. The method of claim 1, wherein, performing the first processing mode or the second processing mode, comprising: in a case where a mounting position of a target sensor is a windshield of the vehicle, performing the first processing mode, the target sensor representing a sensor whose view window is dirty; in a case where the mounting position of the target sensor is a position other than the windshield in the vehicle, performing the second processing mode.

3. The method of claim 1, wherein, According to the current dirt type, the window is cleaned by using water spraying and air spraying, or only by using air spraying, comprising: In the case of determining that the current dirt type is the sludge type dirt, first using water spraying to remove, and then using air spraying to clean the remaining water droplets; In the case of determining that the current dirt type is the rain type dirt, using high-pressure gas generated by a blower or an air compressor to clean the dirty window.

4. The method of claim 1, wherein, The first dirt degree, the second dirt degree, the third dirt degree and the fourth dirt degree are weighted and summed to obtain a final dirt result judgment value, comprising: Different weights are assigned to the first dirt degree, the second dirt degree, the third dirt degree and the fourth dirt degree; Based on the assigned weights, the first dirt degree, the second dirt degree, the third dirt degree and the fourth dirt degree are weighted and summed to obtain the final dirt result judgment value.

5. The method of claim 4, wherein, Different weights are assigned to the first dirt degree, the second dirt degree, the third dirt degree and the fourth dirt degree, comprising: In a mapping relationship, a first preset weight corresponding to the first dirt degree, a second preset weight corresponding to the second dirt degree, a third preset weight corresponding to the third dirt degree and a fourth preset weight corresponding to the fourth dirt degree are determined.

6. The method of claim 1, wherein, The method further comprises: In the case of receiving a cleaning instruction, the first processing mode or the second processing mode is executed based on the cleaning instruction.

7. The method according to any one of claims 1 to 6, characterized in that, The method further comprises: Obtain the temperature of each actuator and the pressure and flow of each water spraying system to obtain monitoring data; According to the size of the monitoring data, a prompt information is generated to prompt the size of the monitoring data, or a warning information is generated to prompt that the monitoring data is out of standard.

8. A window cleaning device for a sensor of a vehicle, characterized in that Comprising: An acquisition unit is configured to acquire an image collected by a shooting device, a point cloud collected by a laser radar, weather information and a current rainfall, the current rainfall is a rainfall at a current time collected by a rainfall sensor, and the weather information at least includes a rainfall monitoring result and a wind speed, the rainfall monitoring result indicates whether it is raining in an environment where a vehicle is located; A first processing unit is configured to process the image collected by the shooting device, the point cloud collected by the laser radar, the weather information and the current rainfall to obtain a dirt judgment result and a current dirt type, the dirt judgment result indicates whether a window of a sensor is dirty, the current dirt type is sludge type dirt or rain type dirt, and the sensor at least includes the rainfall sensor, the shooting device and the laser radar; The second processing unit is configured to execute a first processing mode or a second processing mode when the dirty judgment result indicates that the window of the sensor is dirty, the first processing mode indicating that the wiper is controlled to clean the window, and the second processing mode indicating that the window is cleaned by spraying water and air or by spraying air only, and when the second processing mode is executed, the window is cleaned by spraying water and air or by spraying air only according to the current dirty type. The first processing unit includes a fifth processing module, a sixth processing module, a seventh processing module, an eighth processing module, a ninth processing module, and a tenth processing module. The fifth processing module is configured to process the image collected by the shooting device by using a deep learning model to obtain a first dirty degree and a first dirty type judgment coefficient. The sixth processing module is configured to process the point cloud collected by the laser radar by using a cross-validation method to obtain a second dirty degree and a second dirty type judgment coefficient. The seventh processing module is configured to process the weather information in a mapping relationship to obtain a third dirty degree and a third dirty type judgment coefficient. The eighth processing module is configured to process the current rainfall in a mapping relationship to obtain a fourth dirty degree and a fourth dirty type judgment coefficient. The ninth processing module is configured to perform weighted summation processing on the first dirty degree, the second dirty degree, the third dirty degree, and the fourth dirty degree to obtain a final dirty result judgment value, and perform weighted summation processing on the first dirty type judgment coefficient, the second dirty type judgment coefficient, the third dirty type judgment coefficient, and the fourth dirty type judgment coefficient to obtain a final dirty type judgment value. The tenth processing module is configured to determine the dirty judgment result according to the size of the final dirty result judgment value, and determine the current dirty type according to the size of the final dirty type judgment value.

9. A vehicle system characterized by, One or more processors, memories, and one or more programs, wherein the one or more programs are stored in the memories and configured to be executed by the one or more processors, and the one or more programs include a program for executing the method of any one of claims 1 to 7. One or more processors, memories, and one or more programs, wherein the one or more programs are stored in the memories and configured to be executed by the one or more processors, and the one or more programs include a program for executing the method of any one of claims 1 to 7.

Images