Windshield wiper control methods, windshield wiper systems and vehicles

Abstract

This application provides a windshield wiper control method, a windshield wiper system, and a vehicle, relating to the field of electronic control technology. The method includes: acquiring data detected by a rain sensor and a perception sensor, the perception sensor including at least one of radar and a vision sensor; determining a target scene based on the data detected by the rain sensor and the perception sensor, the target scene being at least one of a heavy rain scene, a light rain scene, a foreign object attachment scene, and a no-rain scene; and issuing a control command to instruct the wiper blades to execute the wiping mode corresponding to the target scene. This application, by combining and processing the detection data from the rain sensor and the perception sensor, can improve detection accuracy, thereby solving the problems of difficult and false wiping, and improving the user experience.

Description

Technical Field

[0001] This application relates to the field of electronic control technology, and in particular to a windshield wiper control method, windshield wiper system and vehicle. Background Technology

[0002] As the level of automotive intelligence continues to improve, automatic wiper functions have been developed and applied to vehicles. By wiping the windshield in a timely manner, clear visibility can be ensured, thereby improving the driving experience.

[0003] Currently, automatic wiper functions primarily rely on rain sensors to detect rainfall levels and control the wiper motor to operate at different speeds based on the rainfall intensity. This, in turn, controls the wiper blades to wipe the windshield at varying speeds. However, limitations in the rain sensor's detection area, or insufficient sensitivity to fine raindrops, can lead to situations where it's raining but the wipers aren't working; or, foreign objects adhering to the detection area can interfere with the detection results, causing false triggering and resulting in the wipers starting to wipe even when it's not raining.

[0004] Therefore, a smarter solution is urgently needed to address the problems of difficulty in starting to scrape and accidental scraping. Summary of the Invention

[0005] This application provides a windshield wiper control method, a windshield wiper system, and a vehicle. By combining and processing the detection data from a rain sensor and a perception sensor, the detection accuracy can be improved, thereby solving the problems of difficult and false wiping and improving the user experience.

[0006] To achieve the above objectives, this application adopts the following technical solution: Firstly, a windshield wiper control method is provided, the method comprising: acquiring data detected by a rain sensor and a perception sensor, the perception sensor including at least one of radar and a vision sensor; determining a target scene based on the data detected by the rain sensor and the perception sensor, the target scene being at least one of a heavy rain scene, a light rain scene, a foreign object attachment scene, and a rainless scene; and issuing a control command, the control command being used to instruct the windshield wiper to perform wiping according to the wiping mode corresponding to the target scene.

[0007] In this embodiment, the wiping mode is used to indicate the operating mode of the windshield wipers. The wiping mode may include one or more of the following: off mode, single-swipe mode, automatic mode, intermittent mode, and continuous mode. Of course, the wiping mode can also be other modes, and this application is not limited to these.

[0008] In this embodiment, by acquiring data detected by rain sensors and perception sensors, multi-source data from various types of sensors, such as rain sensors and perception sensors, can be fused to determine whether the vehicle's current environment is rainy, the corresponding rainfall scenario if it is rainy, and whether it is a scenario with foreign objects attached or a rainless scenario if it is not raining. Because the detection process combines data from multiple types of perception sensors, it provides richer and more accurate criteria for determining the target scenario, thus improving the accuracy of the determined target scenario and allowing for a more accurate wiping mode to be adapted to the target scenario. Compared to existing technologies, this application, by combining data detected by rain sensors and perception sensors, can solve problems such as difficulty in initiating wiping and accidental wiping initiation.

[0009] In one possible implementation of the first aspect, determining a target scene based on data detected by the rain sensor and the sensing sensor includes: determining whether the data detected by the rain sensor is greater than a first preset threshold; if so, determining whether a first preset condition is met based on the data detected by the sensing sensor, wherein meeting the first preset condition indicates heavy rainfall; and if the first preset condition is met, determining that the target scene is a heavy rainfall scene.

[0010] In this embodiment, the sensing sensor has higher detection precision and accuracy. Therefore, after roughly determining whether there is rain using a rain gauge, the data detected by the sensing sensor can be used to make a more precise judgment on the target scene. Whether there is actual rain is determined by whether the data detected by the sensing sensor meets a first preset condition. When the data detected by the sensing sensor meets the first preset condition, the judgment results of the sensing sensor and the rain gauge are consistent, indicating that there is actual rain and heavy rainfall.

[0011] In one possible implementation of the first aspect, after determining whether a first preset condition is met based on the data detected by the sensing sensor, the method further includes: if not, determining whether a second preset condition is met based on the data detected by the sensing sensor, wherein meeting the second preset condition is used to indicate foreign object attachment; if meeting the second preset condition, determining the target scene as the foreign object attachment scene; if not meeting the second preset condition, determining the target scene as the rainless scene.

[0012] In this embodiment, the sensing sensor has higher detection precision and accuracy. Therefore, after roughly determining whether there is rain using a rain gauge, the data detected by the sensing sensor can be used to make a precise judgment on the target scene. Whether there is actual rain is determined by whether the data detected by the sensing sensor meets a first preset condition. When the data detected by the sensing sensor does not meet the first preset condition, the judgment results of the sensing sensor and the rain gauge are inconsistent, indicating that there is no rain and the data detected by the rain gauge is abnormal. At this time, whether there is foreign object attached can be determined by whether the data detected by the sensing sensor meets a second preset condition. When the data detected by the sensing sensor meets the second preset condition, it is determined that there is foreign object; when it does not meet the second preset condition, it is determined that there is no foreign object attached.

[0013] In one possible implementation of the first aspect, the heavy rainfall scenario includes at least a heavy rain scenario and a moderate rain scenario; after determining that the target scenario is a heavy rainfall scenario, the method further includes: based on the data detected by the rain sensor, determining whether it is greater than a second preset threshold, wherein the second preset threshold is greater than the first preset threshold; if yes, then the target scenario is determined to be the heavy rain scenario; if no, then the target scenario is determined to be the moderate rain scenario.

[0014] In this embodiment of the application, based on the data detected by the rain sensor and the sensing sensor, it has been determined that the current environment is actually raining and the rainfall is heavy. On this basis, the data detected by the rain sensor can be used again to further subdivide the heavy rainfall scenario. Therefore, by determining whether the data detected by the rain sensor is greater than the second preset threshold, it can be determined whether the current environment is a heavy rain scenario or a moderate rain scenario under the heavy rainfall scenario.

[0015] In one possible implementation of the first aspect, after determining whether the rainfall exceeds a first preset threshold based on the data detected by the rain sensor, the method further includes: if not, determining whether a third preset condition is met based on the data detected by the sensing sensor, wherein meeting the third preset condition indicates low rainfall; if meeting the third preset condition, determining the target scenario as a low rainfall scenario.

[0016] In this embodiment, the sensing sensor has higher detection precision and accuracy. Therefore, after roughly determining whether there is rain using a rain gauge, the data detected by the sensing sensor can be used to make a more precise judgment on the target scene. Whether there is actual rain is determined by whether the data detected by the sensing sensor meets a third preset condition. When the data detected by the sensing sensor meets the third preset condition, the judgment results of the sensing sensor and the rain gauge are inconsistent, indicating that the rain gauge's detection result is incorrect, and the sensing sensor has detected a light rain scene that the rain gauge cannot detect. In this case, the detection result of the sensing sensor is taken as the standard, indicating that the environment is indeed raining and the rainfall is light. When the data detected by the sensing sensor does not meet the third preset condition, it is determined to be interference such as dust or haze, which can be ignored.

[0017] In one possible implementation of the first aspect, the light rainfall scenario includes at least a light rain scenario and a drizzle scenario; after determining that the target scenario is a light rainfall scenario, the method further includes: based on the data detected by the rain sensor, determining whether it is greater than a third preset threshold, the third preset threshold being less than a first preset threshold; if yes, then the target scenario is determined to be the light rain scenario. If no, then the target scenario is determined to be the drizzle scenario.

[0018] In this embodiment of the application, based on the data detected by the rain sensor and the sensing sensor, it has been determined that the current environment is actually raining and the rainfall is light. On this basis, the data detected by the rain sensor can be used again to further subdivide the light rain scenario. Therefore, by determining whether the data detected by the rain sensor is greater than the third preset threshold, it can be determined whether the current environment is a light rain scenario or a drizzle scenario.

[0019] In one possible implementation of the first aspect, acquiring data detected by a rain gauge sensor includes: acquiring a rainfall intensity signal collected by the rain gauge sensor; the method further includes: determining the changing trend and relative change value of the rainfall intensity signal based on the rainfall intensity signal.

[0020] In this embodiment of the application, when acquiring the detection data of the rain gauge sensor, the rainfall intensity signal detected by the rain gauge sensor can be acquired, and the changing trend and relative value of the rainfall intensity signal can be determined. The changing trend of the rainfall intensity signal can reflect the changing trend of rainfall, and the relative change value of the rainfall intensity signal can reflect the relative magnitude of the change in rainfall.

[0021] In one possible implementation of the first aspect, when the sensing sensor includes a radar, wherein the radar is a lidar and / or a millimeter-wave radar, acquiring the data detected by the sensing sensor includes: acquiring point cloud data collected by the radar; the method further includes: determining the overall density of suspended particles based on the point cloud data.

[0022] The overall density of suspended particles refers to the total mass of all particles (such as raindrops) in a unit volume of air.

[0023] In one possible implementation of the first aspect, determining the overall density of suspended particles based on the point cloud data includes: processing the point cloud data to determine a stray value and a laser intensity difference between adjacent frames; and determining the overall density of suspended particles based on the stray value and the laser intensity difference between adjacent frames.

[0024] In this embodiment of the application, when acquiring radar detection data, point cloud data detected by the radar can be acquired, and the overall density of suspended particles can be determined based on the point cloud data. The changing trend of the overall density of suspended particles can reflect the changing trend of rainfall, and the magnitude of the overall density of suspended particles can reflect the magnitude of rainfall.

[0025] In one possible implementation of the first aspect, processing the point cloud data to determine spurious values ​​and laser intensity differences between adjacent frames includes: clustering the point cloud data to determine the spurious values; and processing the point cloud data using a dynamic target tracking algorithm to determine the laser intensity differences between adjacent frames.

[0026] In the embodiments of this application, a larger stray value indicates a larger overall density of suspended particles.

[0027] Furthermore, when laser light irradiates suspended particles, its intensity decreases due to scattering caused by particle size, material, and distance. Therefore, the intensity difference at the same spatial location in adjacent frames reflects the dynamic distribution changes of the particles. The greater the difference in laser intensity between adjacent frames, the greater the overall density of the suspended particles.

[0028] In one possible implementation of the first aspect, the first preset condition includes: the overall density of the suspended particles shows an upward trend and is greater than a preset slope; the second preset condition includes: the overall density of the suspended particles is greater than a preset density threshold; and the third preset condition includes: the overall density of the suspended particles shows an upward trend and is less than the preset slope.

[0029] In one possible implementation of the first aspect, when the sensing sensor includes a vision sensor, acquiring the data detected by the sensing sensor includes: acquiring an image collected by the vision sensor; the method further includes: determining image features of the image, the image features including image gradients.

[0030] Image features refer to a set of attributes that indicate the characteristics or content of an image.

[0031] In this embodiment of the application, when acquiring detection data from the vision sensor, images collected by the vision sensor can be acquired, and image features such as image gradients can be determined. The magnitude of the image gradient can reflect the image's sharpness and the presence of foreign objects, etc.

[0032] In one possible implementation of the first aspect, the first preset condition includes: the image gradient is less than a first gradient threshold; the second preset condition includes: the image gradients corresponding to multiple regions in the image are different; the third preset condition includes: the image gradient is less than a second gradient threshold, and the second gradient threshold is greater than the first gradient threshold.

[0033] Image gradients describe the rate of change of pixel values ​​in an image. A larger image gradient usually indicates a sharper image; conversely, a smaller image gradient usually indicates a blurrier image.

[0034] In one possible implementation of the first aspect, the image features further include image variance and / or spatial consistency.

[0035] Image variance reflects the degree of dispersion of pixel gray values. The larger the variance, the higher the image contrast, and the clearer it is usually; conversely, the smaller the variance, the lower the image contrast, and the blurrier it is usually.

[0036] Spatial consistency measures the degree of geometric matching between two images or two image patches. Higher spatial consistency indicates that the content in the images is largely the same; lower spatial consistency indicates that the content in the images differs significantly.

[0037] In a second aspect, a windshield wiper system is provided, comprising: a rain sensor, a wiper controller, a wiper motor, and a wiper brush; the wiper controller is connected to the rain sensor, the wiper motor, and a sensing sensor, respectively, and the wiper motor is connected to the wiper brush; the sensing sensor includes at least one of radar and a vision sensor; the wiper controller is configured to execute the wiper control method provided in the first aspect or any possible implementation thereof; the wiper controller is configured to issue the control command to the wiper motor; and the wiper motor is configured to, in response to the control command, control the wiper brush to perform wiping according to the wiping mode corresponding to the target scene.

[0038] The wiper controller is used to send control commands to the wiper motor.

[0039] Thirdly, a vehicle is provided, the vehicle including a central controller, sensing sensors, and a wiper system, the wiper system including a rain sensor, a wiper controller, a wiper motor, and wiper blades; the sensing sensors include at least one of radar and a vision sensor; the central controller is connected to the sensing sensors, the rain sensor, and the wiper controller respectively, and the wiper motor is connected to the wiper blades; the central controller is configured to execute a wiper control method as provided in the first aspect or any possible implementation thereof; the wiper motor is configured to control the wiper blades to perform wiping according to a wiping mode corresponding to the target scene in response to the control command.

[0040] The central controller is used to send control commands to the wiper motor through the wiper controller.

[0041] In one possible implementation of the third aspect, the radar is a lidar and / or millimeter-wave radar, and the vision sensor is a forward-facing vision sensor.

[0042] Fourthly, a vehicle is provided, including a processor and a memory, the processor being coupled to the memory, the memory storing a computer program including computer instructions; the processor being configured to run the computer program or instructions such that the vehicle performs the methods provided in the first aspect or any possible implementation thereof.

[0043] Fifthly, a readable storage medium is provided, the readable storage medium including instructions that, when executed by at least one processor of the device, cause the device to perform the method as described in the first aspect or any possible implementation thereof.

[0044] In a sixth aspect, a computer program product is provided, the computer program product including instructions that, when at least one processor of a device executes the instructions, cause the device to perform the method as described in the first aspect or any possible implementation thereof.

[0045] In a seventh aspect, a chip is provided, the chip including a processor; the processor is configured to perform the method as described in the first aspect or any possible implementation thereof.

[0046] It is understood that the beneficial effects of the second to seventh aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0047] Figure 1 A schematic diagram of the structure of a windshield wiper system provided in the prior art;

[0048] Figure 2This is a schematic diagram of the structure of a rain gauge sensor provided in an embodiment of this application; Figure 3 This application provides a functional schematic diagram of a vehicle according to an embodiment of the present application. Figure 4 This is a schematic diagram of a sensor layout on a vehicle provided in an embodiment of this application; Figure 5 A schematic diagram of the device connection relationship of a windshield wiper system is provided for an embodiment of this application; Figure 6 This application provides another schematic diagram of device connection relationships related to a wiper system. Figure 7 A schematic flowchart illustrating a windshield wiper control method provided in an embodiment of this application; Figure 8 This is a schematic diagram of the structure of another rain sensor provided in an embodiment of this application; Figure 9 This application provides a schematic diagram of a process for generating point cloud data using a lidar system. Figure 10 A schematic diagram illustrating a process for determining the overall density of suspended particles based on point cloud data, provided for an embodiment of this application; Figure 11 A schematic diagram illustrating a process for determining image features based on image data, provided as an embodiment of this application; Figure 12 A flowchart illustrating yet another wiper control method provided in this application embodiment; Figure 13 A flowchart illustrating yet another wiper control method provided in this application embodiment; Figure 14 A flowchart illustrating yet another wiper control method provided in this application embodiment; Figure 15 A flowchart illustrating yet another wiper control method provided in this application embodiment; Figure 16 This is a flowchart illustrating another wiper control method provided in an embodiment of this application. Detailed Implementation

[0049] The embodiments of this application will now be described with reference to the accompanying drawings. Obviously, the described embodiments are merely some, and not all, of the embodiments of this application. Those skilled in the art will recognize that, with the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0050] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms are interchangeable where appropriate; this is merely a way of distinguishing objects with the same attributes in the embodiments of this application. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, so that a process, method, system, product, or apparatus that comprises a series of elements is not necessarily limited to those elements but may include other elements not explicitly listed or inherent to those processes, methods, products, or apparatuses.

[0051] In the embodiments of this application, "instruction" can include direct and indirect instructions, as well as explicit and implicit instructions. The information indicated by a certain piece of information (hereinafter referred to as instruction information) is called the information to be instructed. In specific implementation, there are many ways to indicate the information to be instructed, such as, but not limited to, directly indicating the information to be instructed, such as the information to be instructed itself or its index. It can also indirectly indicate the information to be instructed by indicating other information, where there is a correlation between the other information and the information to be instructed; or it can indicate only a part of the information to be instructed, while the other parts are known or pre-agreed upon. For example, the instruction can be implemented by using a pre-agreed (e.g., protocol predefined) arrangement of various information, thereby reducing the instruction overhead to a certain extent. This application does not limit the specific method of instruction. It is understood that for the sender of the instruction information, the instruction information can be used to indicate the information to be instructed; for the receiver of the instruction information, the instruction information can be used to determine the information to be instructed.

[0052] To facilitate understanding, the relevant terms and concepts that may be involved in the embodiments of this application will be introduced below.

[0053] 1. Millimeter-wave radar.

[0054] Millimeter-wave radar refers to radar that uses millimeter waves (wavelengths from 1mm to 10mm, frequencies from 30GHz to 300GHz) as its detection medium. It transmits millimeter-wave signals, receives the echoes reflected from targets, and then uses the Doppler effect to calculate the target's range, velocity, and azimuth. In other words, millimeter-wave radar relies on the reflection characteristics of radio waves to sense the outside world, without depending on light. While its detection accuracy is low, it is highly resistant to adverse weather conditions such as rain, snow, fog, and sandstorms, and is unaffected by light intensity.

[0055] 2. LiDAR.

[0056] LiDAR (Light Detection and Ranging) refers to a radar system that uses a laser beam as its detection medium. It emits high-frequency laser pulses, measures the time difference or phase difference between the emitted and received echoes, and calculates the distance between the target and the radar using the Time of Flight (TOF) method. Simultaneously, by combining this with the laser's scanning angle, it constructs a three-dimensional point cloud map of the surrounding environment, thereby accurately identifying the target's shape, location, and outline. While it offers high detection accuracy, it suffers from poor weather resistance due to rain, snow, fog, dust storms, and other adverse weather conditions that cause laser scattering. Furthermore, it is unaffected by light intensity.

[0057] 3. Point cloud data.

[0058] Point cloud data refers to a collection of discrete points in three-dimensional space formed after radar scans the surrounding environment. Each point has three-dimensional spatial coordinates, which can accurately mark the position information of objects within the detection range. Some points also include information such as reflection intensity and movement speed, enabling electronic devices (such as autonomous vehicles) to clearly perceive the size, position, and dynamic information of targets such as obstacles, pedestrians, and buildings.

[0059] 4. Area Controller (Vehicle Integration Unit, VIU).

[0060] A zone controller, also known as a zone control unit (ZCU), is an electronic control unit located in a specific area of ​​a vehicle. It is responsible for managing the electrical loads, sensors, actuators, and network communications within that area. It communicates with the central computing unit via a high-speed in-vehicle network (such as Ethernet or Variable Rate Controller Area Network (CAN with Flexible Data-Rate, CANFD)) to coordinate the operation of the entire vehicle's electronic systems.

[0061] 5. Body Domain Controller (BDC).

[0062] In some examples, the domain controller can be divided into several domains (also called "functional domains") according to the functions of various parts of the vehicle, such as intelligent driving domain, cockpit domain, chassis domain, powertrain domain, body domain, etc. Based on this, the vehicle domain controller can be any one or more of the following, including but not limited to: intelligent driving domain controller, cockpit domain controller, chassis domain controller, powertrain domain controller, and body domain controller.

[0063] The intelligent driving domain controller is primarily used to provide autonomous driving perception and decision-making services, such as receiving, processing, and judging image information, processing and calculating data, navigation and route planning, and rapid judgment and decision-making in real-time situations. The intelligent driving domain controller needs to handle algorithms at the perception, decision-making, and control levels, placing the highest demands on both its hardware and software. The body domain controller is mainly used to control various body functions, including but not limited to controlling headlights, taillights, interior lights, door locks, windows, sunroof, wipers, power tailgate, smart key, air conditioning, antennas, and gateway communication.

[0064] 6. Neural networks.

[0065] A neural network is a network formed by connecting multiple individual neural units together. That is, the output of one neural unit can be the input of another neural unit. The input of each neural unit can be connected to the local receptive field of the previous layer to extract the features of the local receptive field. The local receptive field can be a region composed of several neural units.

[0066] 7. Backpropagation Algorithm Neural networks can employ backpropagation (BP) to correct the parameters of the initial neural network model during training, thereby reducing the reconstruction error loss. Specifically, forward propagation of the input signal to the output generates error loss; this error loss information is then propagated back to update the parameters of the initial neural network model, leading to convergence of the error loss. The backpropagation algorithm is an error-loss-driven backpropagation process aimed at obtaining the optimal parameters of the neural network model, such as the weight matrix.

[0067] The above is a brief introduction to the terms used in the embodiments of this application, and will not be repeated below.

[0068] As the level of automotive intelligence continues to improve, automatic wiper functions have been developed and applied to vehicles. By wiping the windshield in a timely manner, clear visibility can be ensured, thereby improving the driving experience.

[0069] Currently, automatic wiper functions mainly rely on rain sensors to detect the amount of rain and control the wiper motor to work at different speeds based on the amount of rain. In turn, the wiper motor can control the wiper blades to wipe the windshield at different speeds.

[0070] For example, Figure 1 A schematic diagram of a wiper system provided for related technologies.

[0071] like Figure 1As shown, the windshield wiper system 110 may include a rain sensor 111, a wiper controller 112, a wiper motor 113, and a wiper blade 114 connected in sequence. The rain sensor 111 can be installed on the inside of the vehicle's windshield, near the rearview mirror. The rain sensor detects the amount of rainfall and sends signals indicating different rainfall amounts to the wiper controller 112. Based on the different rainfall amounts, the wiper controller 112 sends different control signals to the wiper motor 113, so that the wiper motor 113 can control the wiper blade 114 to wipe the windshield at different speeds based on the different control signals.

[0072] For example, Figure 2 This is a schematic diagram of the structure of a rain sensor provided in an embodiment of this application.

[0073] like Figure 2 As shown, this rain sensor 111, also known as a solar rain sensor, detects rainfall amount through the principle of infrared light reflection from glass. The rain sensor 111 may include stacked infrared emitting tubes, infrared receiving tubes, optical elements, and a silicone pad. The side of the silicone pad furthest from the optical element is in contact with the windshield. The infrared receiving tube can be a photodiode (PD); the optical element can be a lens.

[0074] Based on this structure, the infrared light emitted by the infrared emitter passes through the lens, silicone pad, and windshield, and is totally reflected on the inner surface of the windshield on the side away from the silicone pad. After total reflection, the infrared light is focused by the lens and received by the photodiode. A tiny current is generated in the photodiode that receives the infrared light, and this current can be converted into a voltage across a resistor. This voltage can be called the rainfall intensity signal.

[0075] When raindrops hit the windshield, some infrared light is refracted into the air by the raindrops. The proportion of infrared light reflected from the inner surface of the glass onto the photodiode decreases, leading to a reduction in the current generated in the photodiode and affecting the voltage across the resistor. This, in turn, causes a change in the output rainfall intensity signal. Different rainfall intensity signals output by the rain sensor 111 can indirectly determine the amount of rain outside the windshield, and then send signals indicating different rainfall amounts to the wiper controller 112 to initiate wiping.

[0076] While the aforementioned wiper systems are relatively stable and largely free the driver from the need to manually activate the wipers, the small detection area of ​​the rain sensor limits its sensitivity to fine raindrops. This can lead to situations where it's raining but the wipers aren't working; or, foreign objects (such as leaves, catkins, mud, or sludge) can adhere to the detection area, interfering with the results and causing false triggering, resulting in the wipers starting to work even when it's not raining. In other words, existing rain sensor-based systems suffer from problems such as difficulty in initiating wipers and false triggering.

[0077] In view of this, embodiments of this application provide a windshield wiper control method. In this embodiment, by acquiring data detected by a rain sensor and a perception sensor, the target scene can be determined by combining the data from the rain sensor and the perception sensor, whether it is a heavy rain scene, a light rain scene, a scene with foreign objects attached, or a rainless scene. Based on the determined specific target scene, corresponding control commands are issued to instruct the wiper blades to execute the wiping mode corresponding to the specific scene. Because the detection process combines detection data from multiple types of perception sensors, such as radar and vision sensors, it provides richer and more accurate judgment criteria for determining the target scene. Therefore, it can improve the accuracy of the determined target scene, thereby allowing for a more accurate wiping mode to be adapted to the target scene. Compared to the prior art, this application, by combining data detected by a rain sensor and a perception sensor, can solve the aforementioned problems of difficult and false wiping activation.

[0078] To facilitate understanding, the structure of the vehicle will be described below.

[0079] The embodiments provided in this application can be applied to various vehicles, including but not limited to: road vehicles, water vehicles, air vehicles, industrial equipment, agricultural equipment, or recreational equipment. The vehicle can be defined in a broad sense. For example, a vehicle can be a means of transportation (such as cars, buses, subways, high-speed trains, motorcycles, flying cars, trains, etc.), an industrial vehicle (such as forklifts, trailers, tractors, etc.), a construction vehicle (such as excavators, bulldozers, cranes, etc.), agricultural equipment (such as lawnmowers, harvesters, etc.), amusement equipment, toy vehicles, boats, hovercrafts, submarines, airplanes, helicopters, etc. The embodiments in this application do not limit the specific type, form, or function of the vehicle.

[0080] Figure 3 This is a functional schematic diagram of a vehicle 100 provided as an embodiment of this application. For example... Figure 3As shown, the vehicle 100 may include various subsystems, such as a wiper system 110, a sensing system 120, and a computing platform 130. Optionally, the vehicle 100 may include more or fewer subsystems, and each subsystem may include one or more components. Furthermore, each subsystem and component of the vehicle 100 may be interconnected via wired or wireless means.

[0081] The perception system 120 may include several sensors for sensing information about the environment surrounding the vehicle 100. For example, the perception system 120 may include a positioning system, which may be a global positioning system (GPS), a BeiDou system, or another positioning system. The perception system 120 may include one or more of the following: an inertial measurement unit (IMU), a lidar 121, a millimeter-wave radar 122, an ultrasonic radar, and a camera device (also referred to as a vision sensor 123).

[0082] In this embodiment, the LiDAR 121 can be positioned on the roof or inside the cabin, while the millimeter-wave radar 122 can be positioned inside the front bumper or behind the windshield, or in other locations. This application does not limit the number or placement of the LiDAR 121 and millimeter-wave radar 122. The LiDAR 121 and millimeter-wave radar 122 can be used to acquire point cloud data of the target scene. The visual sensor 123 can be positioned above and inside the windshield, such as near or behind the rearview mirror, or in other locations. This application does not limit the number or placement of the visual sensor 123. The visual sensor 123 can be used to acquire image data of the target scene.

[0083] Figure 4 This is a schematic diagram of a sensor layout on a vehicle provided in an embodiment of this application.

[0084] like Figure 4 As shown, the rain sensor 124 in the wiper system 110 is positioned above the inside of the windshield, close to the glass. The lidar 121 is positioned on the roof, the millimeter-wave radar 122 is positioned inside the front bumper, and the vision sensor 123 is positioned at the rearview mirror inside the windshield.

[0085] Some or all of the functions of vehicle 100 can be controlled by computing platform 130. Computing platform 130 may include processors 131 to 13n (n being a positive integer). A processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a central processing unit (CPU), microprocessor unit (MPU), graphics processing unit (GPU) (which can be understood as a type of microprocessor), or digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. These logical relationships are fixed or reconfigurable. For example, the processor may be a hardware circuit implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as a field-programmable gate array (FPGA). In reconfigurable hardware circuits, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement some or all of the functions of the aforementioned units. Furthermore, the processor can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), tensor processing unit (TPU), deep learning processing unit (DPU), etc. In addition, the computing platform 130 may also include a memory for storing instructions. Some or all of the processors 131 to 13n can call the instructions in the memory to implement the corresponding functions.

[0086] The computing platform 130 can control the functions of the vehicle 100 based on inputs received from various subsystems, such as the wiper system 110 and the sensing system 120. In some embodiments, the computing platform 130 can be used to provide control over many aspects of the vehicle 100 and its subsystems.

[0087] In this embodiment of the application, the processor in the vehicle 100 is used to execute... Figure 7 , Figures 10 to 15 The corresponding wiper control method is described in the embodiment. It should be noted that the specific manner in which the processor executes the aforementioned steps differs from that in this application. Figures 7 to 15 The various method embodiments are based on the same concept, and the technical effects they bring are the same as those in this application. Figures 7 to 15 The corresponding method embodiments are the same, and for details, please refer to the description in the method embodiments shown above in this application, which will not be repeated here.

[0088] In this embodiment, the processor in vehicle 100 can be connected to other related parts via Ethernet, CAN / CAN FD bus, LIN bus and A2B bus to achieve data communication and collaborative control.

[0089] Optionally, the above components are just an example. In actual applications, the components in each of the above modules may be added or deleted as needed.

[0090] Understandably, vehicle 100 may also include more or fewer subsystems, and each subsystem may include multiple components. For example, vehicle may also include a travel system, etc., the specifics of which will not be elaborated in the embodiments of this application. Figure 2 This should not be construed as a limitation on the embodiments of this application. It is understood that each subsystem and component of the vehicle 100 can be interconnected via wired or wireless means.

[0091] Figure 5 This is a schematic diagram of the device connection relationship of a wiper system 110 provided in an embodiment of this application.

[0092] As an implementation method, combined Figure 1 , Figure 2 and Figure 5 As shown, the wiper system 110 may include a rain sensor 111, a wiper controller 112, a wiper motor 113, and a wiper brush 114 connected in sequence. In addition, the wiper controller 112 is also connected to the sensing sensors in the sensing system 120, such as the lidar 121, the millimeter-wave radar 122, and the vision sensor 123.

[0093] With sufficient computing power, the wiper controller 112 can perform... Figure 7 , Figures 10 to 15 The wiper control method provided in the corresponding embodiment includes, for example: acquiring data detected by the rain sensor 111 and the sensing sensor; determining the target scene based on the data detected by the rain sensor and the sensing sensor, and issuing control commands to the wiper motor 112.

[0094] In this embodiment of the application, the wiper controller 112 can be Figure 3 The processor shown, or the wiper controller 112, can be a zone controller, or it can be integrated as part of the zone controller; this application does not limit this.

[0095] Figure 6 This is a schematic diagram of the device connection relationship of a wiper system provided in an embodiment of this application.

[0096] As another implementation method, combined Figure 2 and Figure 6 As shown, the wiper system 110 may include a rain sensor 111, a wiper controller 112, a wiper motor 113, and a wiper brush 114 connected in sequence. Here, the central controller is connected to the wiper controller 112, the rain sensor 111, and the sensing sensors in the sensing system, such as the lidar 121, the millimeter-wave radar 122, and the vision sensor 123.

[0097] Therefore, the central controller 112 can execute Figure 7 , Figures 10 to 15 The wiper control method provided in the corresponding embodiment includes, for example: acquiring data detected by the rain sensor 111 and the sensing sensor; determining the target scene based on the data detected by the rain sensor and the sensing sensor, and issuing control commands to the wiper controller 112.

[0098] In this embodiment of the application, the central controller can be Figure 3 The processor shown, or the central controller 112, can be a region controller, intelligent driving domain controller, or body domain controller. Alternatively, the central controller 112 can also be integrated as a part of the region controller, intelligent driving domain controller, or body domain controller. This application does not limit this.

[0099] Next, combined Figures 7 to 15 The wiper control method provided in the embodiments of this application will be described in detail.

[0100] Figure 7 This is a flowchart illustrating a windshield wiper control method provided in an embodiment of this application. Figure 7 As shown, this method can be applied to the above. Figure 3 In the vehicle shown. The method may include steps S110 to S130, which will be described one by one below.

[0101] S110. Acquire data detected by a rain sensor and a perception sensor, wherein the perception sensor includes at least one of a radar and a vision sensor.

[0102] Alternatively, it can be used Figure 5 The wiper controller shown acquires data from the rain sensor and the sensing sensor; or, utilizes... Figure 6 The central controller shown acquires data detected by the rain sensor and the sensing sensor.

[0103] (1) The process of acquiring data detected by the rain gauge is as follows: As one feasible approach, the structure and working principle of rain gauges can be referenced from [the relevant documentation / reference]. Figure 2 The description.

[0104] The structure and working principle of the rain gauge are as follows: Figure 2 As shown, the data detected by the rain sensor is... Figure 2 The infrared receiver tube shown outputs the rainfall intensity signal.

[0105] Optionally, if the data detected by the rain gauge sensor is a rainfall intensity signal, then after acquiring the data detected by the rain gauge sensor, the method may further include: determining the changing trend and / or relative change value of the rainfall intensity signal based on the rainfall intensity signal.

[0106] The changing trend of rainfall intensity signals can include trends such as increasing, decreasing, stabilizing, or abrupt changes.

[0107] It should be understood that a continuously increasing trend in the rainfall intensity signal indicates an increase in rainfall; a continuously decreasing trend indicates a decrease in rainfall; a stable trend indicates relatively stable rainfall; and a step-like change in the rainfall intensity signal indicates the presence of foreign objects, such as leaves, catkins, silt, or mud, adhering to the detection area of ​​the rainfall sensor.

[0108] The above are merely examples of several trends in rainfall intensity signals, and this application is not limited thereto.

[0109] The relative change in rainfall intensity signal refers to the difference between the currently collected rainfall intensity signal and a reference value (such as the value when there is no rain or the value obtained when the rain sensor first starts detecting). By continuously calculating the difference between the collected rainfall intensity signal and the reference value, the difference can be used to dynamically reflect changes in rainfall.

[0110] As another possible approach Figure 8 This is a schematic diagram of another rain sensor provided in an embodiment of this application.

[0111] exist Figure 2 Based on the rain sensor shown, Figure 8 The rain sensor shown may also include a signal processing module, which is connected to the infrared receiver. The signal processing module performs preliminary processing on the rainfall intensity signal output by the infrared receiver, determining and outputting the changing trend and relative change value of the rainfall intensity signal.

[0112] In this embodiment of the application, when acquiring the detection data of the rain gauge sensor, the rainfall intensity signal detected by the rain gauge sensor can be acquired, and the changing trend and relative value of the rainfall intensity signal can be determined. The changing trend of the rainfall intensity signal can reflect the changing trend of rainfall, and the relative change value of the rainfall intensity signal can reflect the relative change value of rainfall.

[0113] (2) The process of acquiring radar detection data is as follows: Optionally, when the sensing sensor includes radar, the radar can be lidar and / or millimeter-wave radar, or other types of radar.

[0114] For example, the sensing sensor may include lidar and / or millimeter-wave radar, and acquiring the data detected by the sensing sensor may indicate acquiring point cloud data output by lidar and / or millimeter-wave radar. The point cloud data may refer to point cloud data directly acquired by lidar and / or millimeter-wave radar, or it may refer to pre-processed point cloud data; this application is not limited in this respect.

[0115] Taking lidar as an example, Figure 9 This is a schematic diagram illustrating the process of generating point cloud data using a lidar system, as provided in an embodiment of this application.

[0116] like Figure 9 As shown, this method can be executed by a lidar and may specifically include steps S201 to S204.

[0117] S201, The lidar emits a laser and collects the echo signal.

[0118] For example, the wavelength of the laser emitted by a lidar can be 1550nm or 905nm, etc.

[0119] In this embodiment, the lidar uses a longer wavelength (e.g., 1550nm) to detect farther distances. Furthermore, in rainy weather, longer wavelength lasers scatter less than shorter wavelength lasers, resulting in stronger penetration. Combined with higher emission power, longer wavelength lasers offer more stable detection capabilities in complex weather conditions, with less attenuation of the effective detection range.

[0120] S202. Based on the echo signal, the echo power Pr of the lidar is determined using the radar equation.

[0121] The expression for the radar equation is: Pr = (Pt) Gt Gr λ 2 σ) / ((4π) 3 R 4 L).

[0122] Where Pt is the transmit power; Gt is the transmit antenna gain; Gr is the receive antenna gain; λ is the operating wavelength; σ is the target radar cross section (RCS); R is the distance of the radar to the target; and L is the total system loss factor.

[0123] S203. Determine the time difference Δt of the echo power Pr.

[0124] For example, a timer can be started when the lidar emits a laser; the timer can be stopped after the echo signal is detected. Thus, the duration recorded by the timer can be read, which is the time difference Δt of the echo power Pr, or it can also be called the flight time Δt.

[0125] S204. Based on the time difference Δt, determine the target distance and generate point cloud data.

[0126] The formula for determining the target distance is: D = (c Δt) / 2; D is the target distance, c is the speed of light, approximately 3 × 10⁻⁶. 8 m / s.

[0127] Based on the formula for determining the target distance mentioned above, it can be seen that the distance traveled by the light path within that time difference can be determined by multiplying the speed of light by the time difference. Since the light path is a round trip distance, it needs to be divided by 2 to determine the distance between the lidar and the target.

[0128] After determining the target distance D, it is necessary to combine the scanning angle of the laser beam to convert the polar coordinates into three-dimensional rectangular coordinates.

[0129] The conversion formula is: x=D cos cosθ, y=D cos sinθ, z=D sin D is the target distance determined above, and θ is the horizontal azimuth angle. It is the vertical pitch angle.

[0130] By combining the above conversion formula, the scanning system continuously changes the direction of the laser beam to sample the space point by point. Then, for each sampled point, its three-dimensional coordinates (x, y, z) and reflection intensity can be obtained. This massive collection of spatial points constitutes point cloud data describing the three-dimensional structure of the environment.

[0131] Optionally, if the acquired lidar detection data is point cloud data, the method may further include, after acquiring the lidar detection data, determining the overall density of suspended particles based on the point cloud data. Here, the overall density of suspended particles refers to the total mass of all particles (such as raindrops) per unit volume of air.

[0132] Figure 10 This is a schematic diagram illustrating a process for determining the overall density of suspended particles based on point cloud data, as provided in an embodiment of this application.

[0133] like Figure 10 As shown, the method can be executed by the wiper controller or the central controller, and may specifically include steps S211 to S212.

[0134] S211. Process the point cloud data to determine the spurious value and the difference in laser intensity between adjacent frames.

[0135] Optionally, clustering can be performed on the point cloud data to determine spurious values.

[0136] For example, the first step is to collect point cloud data by region; the second step is to determine the number of raindrops (i.e., the number of noise points) marked in the point cloud data collected in each region, since raindrops mainly appear as "noise points" in point cloud data; the third step is to count the raindrop point cloud density per unit volume.

[0137] For example, the three-dimensional space containing raindrop point clouds can be divided into a regular cubic grid (or voxels), with each voxel having a volume of Vvoxel = Δx × Δy × Δz, where Δx, Δy, and Δz are the side lengths of the voxel in the three directions, respectively. Assuming the volume of a voxel is 0.1 m × 0.1 m × 0.1 m, the raindrop point cloud can be mapped to the corresponding voxel based on its three-dimensional coordinates (x, y, z), and the number of raindrop points Nvoxel contained within that voxel can be counted. Then, based on the formula ρ = Nvoxel / Vvoxel, the raindrop point cloud density ρ (in points per cubic meter) within the corresponding volume of that voxel can be calculated.

[0138] The fourth step is to obtain the three-dimensional distribution of raindrop point cloud density in the entire space by traversing all voxels. For the raindrop point cloud density in the entire space, calculate any statistical value such as the mean, median or variance, and use the statistical value as the stray value.

[0139] It should be understood that the above is merely an example of determining spurious values, and the method for determining spurious values ​​may include other steps, which are not limited in this application. Furthermore, the above process can also be referred to as a clustering process.

[0140] Optionally, a dynamic target tracking algorithm can be used to process the point cloud data to determine the difference in laser intensity between adjacent frames.

[0141] For example, the first step involves preprocessing and target segmentation of the point cloud data. For instance, for point cloud data from two adjacent frames (e.g., frame t and frame t+1), preprocessing such as denoising and downsampling is performed. Then, clustering (as in the example above) is used to divide the point cloud into multiple independent target clusters (e.g., the point group corresponding to raindrops), while simultaneously recording the laser intensity value and 3D coordinates of each point. The second step involves associating cross-frame targets determined by a dynamic target tracking algorithm. For example, each target cluster is treated as a tracking target, and a dynamic target tracking algorithm (e.g., based on Kalman filter prediction + Hungarian algorithm matching) is used to associate the target clusters from frame t to frame t+1. The third step involves calculating the laser intensity difference between matching point pairs. For example, for two point cloud clusters of the same associated target (e.g., cluster A and cluster A'), a one-to-one matching relationship is established between points within the cluster. Then, for each pair of matching points, the difference between the laser intensity of frame t+1 and the laser intensity of frame t is calculated. This yields the laser intensity difference between adjacent frames.

[0142] It should be understood that the above is only an example of determining the difference in laser intensity between adjacent frames. The method for determining the difference in laser intensity between adjacent frames may also include other steps, which are not limited in this application.

[0143] S212. Determine the overall density of suspended particles based on stray values ​​and the difference in laser intensity between adjacent frames.

[0144] Optionally, the physical correlation between stray values ​​and the difference in laser intensity between adjacent frames and the overall density of suspended particles can be quantified, and a mapping relationship can be established through weighted fusion or model fitting.

[0145] It should be understood that suspended particles (such as raindrops) are scanned by lidar as small point clouds, which are then marked as noise points (or stray points). The higher the overall density of suspended particles in the air, the more particles are present per unit space, resulting in a greater number of stray points detected by the lidar and a higher stray value. Therefore, it is clear that a higher stray value indicates a higher overall density of suspended particles.

[0146] Furthermore, when laser light irradiates suspended particles, its intensity decreases due to scattering caused by particle size, material, and distance. Therefore, the intensity difference at the same spatial location in adjacent frames reflects the dynamic distribution changes of the particles. The higher the overall density of suspended particles in the air, the more intense the scattering of the laser light, resulting in greater high-intensity fluctuations at the same location in adjacent frames. Therefore, it is clear that a larger difference in laser intensity between adjacent frames indicates a higher overall density of suspended particles.

[0147] Based on the physical correlation between the above two indicators and the density of suspended particles, the stray value and the difference in laser intensity between adjacent frames can be normalized. For example, the stray value can be mapped to the interval [0, 1]. Similarly, the average absolute value of the difference in laser intensity between adjacent frames can be mapped to the interval [0, 1]. Then, the normalized stray value and the difference in laser intensity between adjacent frames can be weighted and summed according to their physical contributions to obtain the overall density of suspended particles. Alternatively, based on the physical correlation between the above two indicators and the density of suspended particles, the stray value and the difference in laser intensity between adjacent frames can be input into a trained model to determine the overall density of suspended particles.

[0148] It should be understood that the above is merely an example of determining the overall density of suspended particles, and the method for determining the overall density of suspended particles may also include other steps, which are not limited in this application.

[0149] In this embodiment of the application, when acquiring radar detection data, point cloud data detected by the radar can be acquired, and the overall density of suspended particles can be determined based on the point cloud data. The changing trend of the overall density of suspended particles can reflect the changing trend of rainfall, and the magnitude of the overall density of suspended particles can reflect the magnitude of rainfall.

[0150] (3) The process of acquiring data detected by the visual sensor is as follows: Optionally, when the sensing sensor includes a vision sensor, acquiring the data detected by the sensing sensor can indicate acquiring the image output by the vision sensor. This image can refer to an image directly acquired by the vision sensor, or it can refer to a pre-processed image; this application is not limited in this regard. For example, the image can be an RGB image.

[0151] For example, the vision sensor can be a forward-facing vision sensor used to acquire an image of the area in front of the vehicle. It can also be one or more of rear-facing, side-facing, and surround-view vision sensors; this application does not limit the orientation of the vision sensor.

[0152] For example, the visual sensor can be any one of a super telephoto camera, a telephoto camera, a main camera, a wide-angle camera, or an ultra-wide-angle camera. This application does not limit the type or number of visual sensors.

[0153] Optionally, after acquiring the image detected by the visual sensor, the method may further include: determining the image features of the image.

[0154] Image features refer to a set of attributes that indicate the characteristics or content of an image; for example, image features can typically include color features, texture features, shape features, and spatial relationship features.

[0155] In the embodiments of this application, the image feature may include one or more of image gradient, image variance, and spatial consistency.

[0156] Image gradients describe the rate of change of pixel values ​​in an image. A larger image gradient usually indicates a sharper image; conversely, a smaller image gradient usually indicates a blurrier image.

[0157] For example, as an example, the color image can first be converted to grayscale to simplify calculations. Then, the horizontal gradient Gx and vertical gradient Gy can be calculated separately using convolution kernels. The horizontal gradient Gx and vertical gradient Gy are then combined to obtain the total gradient reflecting the image sharpness. As another example, the grayscale image can be divided into blocks, and gradient calculations can be performed on image blocks at different locations to obtain gradients reflecting the sharpness of the image blocks.

[0158] The above is merely an example of determining image gradients; the method may also include other steps, which are not limited in this application.

[0159] Image variance reflects the degree of dispersion of pixel gray values. The larger the variance, the higher the image contrast, and the clearer it is usually; conversely, the smaller the variance, the lower the image contrast, and the blurrier it is usually.

[0160] For example, as an example, a color image can first be converted to a grayscale image, the average brightness of all pixels can be calculated, and then the average of the squares of the deviations of the pixel values ​​from the mean can be calculated. This average result is the image variance that reflects the sharpness of the image. As another example, the grayscale image can be divided into blocks, and the variance of the image blocks at different locations can be calculated to obtain the variance that reflects the sharpness of the image blocks.

[0161] The above is merely an example for determining image variance; the method may also include other steps, which are not limited in this application.

[0162] Spatial consistency measures the degree of geometric matching between two images or two image patches. Higher spatial consistency indicates that the content in the images is largely the same; lower spatial consistency indicates that the content in the images differs significantly.

[0163] For example, spatial consistency can be calculated between two adjacent frames or two frames spaced a certain number of frames or time intervals from each other captured by a visual sensor. If the geometric transformation relationships presented by the feature point matching pairs are consistent, it indicates that the two images depict the same scene or object and there are no significant differences. As another example, the image can be divided into blocks, and spatial consistency can be calculated for image blocks at adjacent or different locations. If the content presented by the image blocks is relatively consistent, it indicates that the content consistency in the image is high and there are no significant differences.

[0164] The above is merely an example for determining spatial consistency; the method may also include other steps, which are not limited in this application.

[0165] Alternatively, a trained neural network model can be used to extract image features, such as one or more of image gradient, image variance, and spatial consistency.

[0166] The parameters of the neural network model are obtained iteratively through backpropagation by comparing the differences between the sample images used for training and the output images. This neural network model can be a diffusion model, a convolutional network model, etc., and this application does not limit it to any particular type.

[0167] It should be understood that the above are merely a few examples of sensing sensors. When sensing sensors include other types of sensors, data detected by other types of sensors can also be acquired to increase the diversity of detection data sources. This application does not limit the type or number of sensing sensors.

[0168] In this embodiment of the application, when acquiring detection data from the vision sensor, images collected by the vision sensor can be acquired, and image features such as image gradient, image variance, or spatial consistency can be determined. The magnitude of image features can reflect the image's sharpness and the presence of foreign objects, etc.

[0169] S120. Based on the data detected by the rain sensor and the perception sensor, determine the target scene. The target scene is at least one of the following: heavy rainfall scene, light rainfall scene, foreign object attachment scene, and no rain scene.

[0170] Optionally, the target scene can be determined based on the rainfall intensity signal acquired by the rain sensor, or the changing trend and relative change value of the rainfall intensity signal. Wherein, when the acquired data is a rainfall intensity signal, the changing trend and / or relative change value of the rainfall intensity signal can be determined first by performing the method described in step S110 (1) above, and then used to determine the target scene.

[0171] Optionally, the target scene can be determined based on point cloud data acquired by radar or the overall density of suspended particles. When the acquired data is point cloud data, the method described in step S110 (2) above can be executed to first determine the overall density of suspended particles and then use it to determine the target scene.

[0172] Optionally, the target scene can be determined based on the image acquired by the visual sensor, or the image features. When the acquired data is an image, the image features can be determined first by performing the method described in step S110 (3) above, and then used to determine the target scene.

[0173] It should be understood that based on data detected by rain sensors and perception sensors, it is possible to determine whether the vehicle's current environment is rainy and, if so, the amount of rainfall. Here, "rainless" refers to a rainless scenario; "rainy" can be determined based on set conditions (such as...). Figure 11 and Figure 12 The first preset threshold and the first preset condition shown in the figure subdivide the scene into heavy rainfall scene and light rainfall scene. Among them, heavy rainfall scene and light rainfall scene are two relative scenes. Different conditions can divide different rainfall levels into heavy rainfall scene or light rainfall scene. This application does not limit this.

[0174] It should be noted that rainfall can be classified according to daily precipitation. For example, daily precipitation of 0-0.1 mm is drizzle; daily precipitation of 0.1 mm-9.9 mm is light rain; daily precipitation of 10.0 mm-24.9 mm is moderate rain; daily precipitation of 25.0 mm-49.9 mm is heavy rain; daily precipitation of 50.0 mm-99.9 mm is torrential rain; daily precipitation of 100.0 mm-249.9 mm is extremely heavy rain; and daily precipitation of ≥250.0 mm is exceptionally heavy rain.

[0175] For example, in the embodiments of this application, the heavy rainfall scenario may include heavy rain scenario and moderate rain scenario, and may also include rainstorm, torrential rain and extremely heavy rain scenarios, while the light rainfall scenario may include light rain scenario and drizzle scenario.

[0176] It should also be understood that, based on the data detected by the rain sensor and the perception sensor, it can be determined whether the rain sensor on the vehicle is attached to a foreign object. If it is, then the scenario can be identified as a foreign object attachment scenario.

[0177] S130: Issue controller instructions. The control instructions are used to instruct the wiper blades to execute the wiping mode corresponding to the target scene.

[0178] As one implementation method, if using Figure 5 The wiper controller shown acquires data detected by the rain sensor and the perception sensor. After determining the target scene based on the data detected by the rain sensor and the perception sensor, the wiper controller can send a control command to the wiper motor. In response to the control command, the wiper motor can control the wiper blades to perform the wiping mode corresponding to the target scene.

[0179] As another implementation method, if using Figure 6The central controller, as shown, acquires data detected by the rain sensor and the perception sensor. After determining the target scene based on the data detected by the rain sensor and the perception sensor, the central controller can also send control commands to the wiper motor through the wiper controller. In response to the control commands, the wiper motor can control the wiper blades to perform the wiping mode corresponding to the target scene.

[0180] In this application embodiment, the scraping mode may include one or more of the following: off mode, single-use mode, automatic mode, intermittent mode, and continuous mode. Of course, other scraping modes are also possible, and this application is not limited to them.

[0181] The wiper modes include: Off mode (meaning the wipers stop working); Single mode (meaning the wipers automatically return to their original position after one wipe); Automatic mode (meaning the wipers automatically control their start, stop, and speed based on rainfall); Intermittent mode (meaning the wipers operate at regular intervals); and Continuous mode (meaning the wipers operate continuously at a certain speed).

[0182] For example, the intermittent mode can be further divided into different intermittent modes based on different frequencies, such as short-duration intermittent mode, standard intermittent mode, long-duration intermittent mode, etc., which are not limited in this application.

[0183] For example, the continuous mode can be further divided into different continuous modes based on different speeds, such as low-speed continuous mode, standard continuous mode, high-speed continuous mode, etc., which is not limited in this application.

[0184] Optionally, in Figures 2 to 6 , Figure 8 The wiper system shown may also include a water spray pump connected to the wiper controller. When the control command issued includes a water spray command to the water spray pump, the water spray pump sprays water onto the windshield in response to the water spray command.

[0185] The scraping mode may include a separate water spraying mode, which is used to instruct the water pump to spray water; or, the single-shot mode of the scraping mode may include the water spraying mode. Of course, other modes may also be used in conjunction with the water spraying mode, and this application does not limit this.

[0186] This application provides a windshield wiper control method. By connecting the wiper controller or central controller to both a rain sensor and a perception sensor (such as radar or vision sensors), the method acquires data detected by the rain sensor and the perception sensor. Based on multi-source data from various types of sensors, it fuses this data to determine whether the vehicle's current environment is rainy, the corresponding rainfall level if it is rainy, and whether it is a scenario with foreign objects attached or a rainless scenario if it is not raining. Because the detection process combines data from multiple types of perception sensors, it provides richer and more accurate criteria for determining the target scenario, thus improving the accuracy of the determined target scenario and allowing for a more accurate wiping mode to be adapted to the target scenario. Compared to existing technologies, this application, by combining data from rain sensors and perception sensors, can solve problems such as difficulty in initiating wiping and false initiation of wiping.

[0187] Figure 11 and Figure 12 This is a flowchart illustrating the process of determining a target scenario, as provided in an embodiment of this application.

[0188] like Figure 11 As shown, the above step S120 may include steps S1201 to S1215, which will be described in detail below.

[0189] S1201. Determine whether the relative change value detected by the rain gauge sensor is greater than a first preset threshold. If yes, proceed to S1202; if no, proceed to S1210.

[0190] Optionally, when the wiper system is turned on, or when the rain sensor detects a high-intensity signal, an event can be reported, and then, in response to the reported event, step S1201 can be triggered.

[0191] The first preset threshold may include a first relative change value threshold for the rainfall intensity signal. The first preset threshold can be set and adjusted as needed, and this application does not limit it.

[0192] For example, suppose the first relative change threshold can be set to a relative change value greater than 125mm over a 200ms period. Thus, the relative change value of the rain sensor over a 200ms period can be obtained and compared with the first relative change threshold. If it is greater than the first relative change threshold, it indicates that the rainfall intensity signal has changed significantly, and the current environment can be roughly judged to be rainy based on the data detected by the rain sensor.

[0193] Optionally, step S1201 may further include: determining whether the trend of the rainfall intensity signal detected by the rain gauge is non-decreasing (e.g., including increasing, stable, and step-change). If both conditions involving relative change value and trend are met, then S1202 is executed; if at least one condition is not met, then S1210 is executed.

[0194] In this embodiment of the application, the detection method of the rain sensor is relatively simple. The data detected by the rain sensor can be used to make a rough judgment on the target scene. Therefore, by determining whether the data detected by the rain sensor is greater than the first preset threshold, it can be roughly determined whether there is rain.

[0195] S1202. Based on the data detected by the sensing sensor, determine whether a first preset condition is met. Meeting the first preset condition indicates heavy rainfall. If the first preset condition is met, proceed to S1203; if the first preset condition is not met, proceed to S1204.

[0196] The first preset condition can be set and combined based on the type of sensing sensor.

[0197] Optionally, if the sensing sensor includes radar, the first preset condition may include: the overall density of suspended particles shows an upward trend and is greater than a preset slope. If the sensing sensor includes a vision sensor, the first preset condition may at least include: the image gradient is less than a first gradient threshold. If the sensing sensor includes both radar and a vision sensor, the first preset condition may include: the overall density of suspended particles shows an upward trend and is greater than a preset slope, and the image gradient is less than a first gradient threshold.

[0198] The preset slope and the first gradient threshold can be set as needed, and this application does not limit them.

[0199] It should be noted that when suspended particles show an upward trend, the preset slope is used to distinguish the speed of the ascent. If the slope is greater than the preset slope, it indicates a significant ascent, corresponding to a significant increase in rainfall in the environment; if the slope is less than the preset slope, it indicates a slight ascent, corresponding to a slight increase in rainfall in the environment. The image gradient is used to distinguish the image clarity and determine whether there are rain streaks, water marks, and sky conditions in the global field of view. If the gradient is less than the first gradient threshold, it indicates that the image is relatively blurry, corresponding to rain in the environment and heavy rainfall; if the gradient is greater than or equal to the first gradient threshold, it indicates that the image is relatively clear, corresponding to no rain in the environment.

[0200] For example, Figure 12 This is a flowchart illustrating a process for determining whether a first preset condition is met.

[0201] like Figure 12As shown, in S12011, first determine whether the overall density of the suspended particles is on an upward trend and greater than the preset slope. If it is on an upward trend and greater than the preset slope, then continue to execute S12012; if it is not on an upward trend and greater than the preset slope, then it is determined that the first preset condition is not met, and S1204 can be executed.

[0202] S12012. Determine whether the image gradient is less than the first gradient threshold (e.g., IG < 15). If it is less than the first gradient threshold, then the first preset condition is met, and S1203 can be executed. If it is not less than the first gradient threshold, that is, greater than or equal to the first gradient threshold, then the first preset condition is not met, and S1204 can be executed.

[0203] In this embodiment, the sensing sensor has higher detection precision and accuracy. Therefore, after roughly determining whether there is rain using a rain gauge, the data detected by the sensing sensor can be used to make a more precise judgment on the target scene. Whether there is actual rain is determined by whether the data detected by the sensing sensor meets a first preset condition. When the data detected by the sensing sensor meets the first preset condition, the judgment results of the sensing sensor and the rain gauge are consistent, indicating that there is actual rain and heavy rainfall.

[0204] Furthermore, steps S1201 and S1202 described above can be executed simultaneously, and this application does not limit this.

[0205] S1203. The target scenario is determined to be a heavy rainfall scenario.

[0206] For example, after determining that the target scenario is a heavy rain scenario, a first control command can be issued to the wiper motor, wherein the first control command is used to indicate the automatic mode; in response to the first control command, the wiper motor can control the wiper blades to perform in the automatic mode corresponding to the heavy rain scenario.

[0207] In this embodiment, the correspondence between different scenarios and wiper modes can be preset and stored in the wiper controller, central controller, or connected memory. When determining a target scenario, the corresponding target wiper mode can be queried and determined based on the correspondence between different scenarios and wiper modes; then, the control command carrying the target wiper mode corresponding to the target scenario is sent to the wiper motor for execution.

[0208] Optionally, after step S1203 above, as follows: Figure 15 As shown, the method may further include steps S1207 to S1209.

[0209] S1207. Determine whether the relative change value detected by the rain gauge sensor is greater than the second preset threshold. The second preset threshold is greater than the first preset threshold. If yes, proceed to S1208; if no, proceed to S1209.

[0210] The second preset threshold may include a second relative change value threshold for the rainfall intensity signal. The second preset threshold can be set and adjusted as needed, and this application does not impose any limitations on it.

[0211] For example, assuming the second relative change value threshold is set to a relative change value greater than 180mm over a 200ms period, the relative change value of the rain sensor over a 200ms period can be obtained and compared with the second relative change value threshold. If it is greater than the second relative change value threshold, it indicates that the rainfall intensity signal has changed significantly. Based on the data detected by the rain sensor, it can be further refined to determine which specific heavy rainfall scenario the current environment is in.

[0212] In this embodiment of the application, based on the data detected by the rain sensor and the sensing sensor, it has been determined that the current environment is actually raining and the rainfall is heavy. On this basis, the data detected by the rain sensor can be used again to further subdivide the heavy rainfall scenario. Therefore, by determining whether the data detected by the rain sensor is greater than the second preset threshold, it can be determined whether the current environment is a heavy rain scenario or a moderate rain scenario under the heavy rainfall scenario.

[0213] S1208. The target scenario is determined to be a heavy rain scenario.

[0214] For example, after determining that the target scenario is a heavy rain scenario, a second control command can be issued to the wiper motor, wherein the second control command is used to indicate a high-speed continuous mode; in response to the second control command, the wiper motor can control the wiper blades to perform in accordance with the high-speed continuous mode corresponding to the heavy rain scenario.

[0215] In the embodiments of this application, scenarios with rainfall levels above the heavy rain scenario level (such as rainstorm scenario, torrential rain scenario, and extremely heavy rain scenario, etc.) can all adopt the execution strategy corresponding to the heavy rain scenario.

[0216] S1209. The target scene is determined to be a moderate rain scene.

[0217] For example, after determining that the target scenario is a moderate rain scenario, a third control command can be issued to the wiper motor, wherein the third control command is used to indicate the standard continuous mode; in response to the third control command, the wiper motor can control the wiper brush to perform according to the standard continuous mode corresponding to the moderate rain scenario.

[0218] Optionally, multiple other threshold ranges can be set to further subdivide the heavy rainfall scenario into moderate rain, heavy rain, rainstorm, and torrential rain scenarios, and then different wiping modes can be associated with different scenarios.

[0219] Optionally, after determining the target scenario, the corresponding control command can be determined by combining other information such as the current vehicle speed and acceleration to indicate different wiper modes.

[0220] In this embodiment, the correspondence between different scenarios, vehicle speeds, and wiper modes can be preset and stored in the wiper controller, central controller, or connected memory. When a target scenario is determined, the corresponding target wiper mode can be queried and determined based on this correspondence. Then, a control command carrying the target wiper mode corresponding to the target scenario is sent to the wiper motor for execution.

[0221] S1204. After determining in step S1202 that the first preset condition is not met, determine whether the data detected by the sensing sensor meets the second preset condition. Meeting the second preset condition is used to indicate foreign object attachment. If the second preset condition is met, proceed to S1205; if the second preset condition is not met, proceed to S1206.

[0222] The second preset condition can be set and combined based on the type of sensing sensor.

[0223] Optionally, if the sensing sensor includes radar, the second preset condition may include: the overall density of suspended particles is greater than a preset density threshold. If the sensing sensor includes a vision sensor, the second preset condition may at least include: the image gradients corresponding to multiple regions in the image are different. If the sensing sensor includes both radar and a vision sensor, the second preset condition may include: the overall density of suspended particles is greater than a preset density threshold and the image gradients corresponding to multiple regions in the image are different.

[0224] The preset density threshold can be set as needed, and this application does not limit it.

[0225] It should be noted that the preset density threshold is used to distinguish whether there are foreign objects attached to the rain sensor. If the density is greater than the preset threshold, it indicates that there are foreign objects attached; if it is less than the preset density threshold, it indicates that there are no foreign objects. The image gradient is used to distinguish the image sharpness and determine whether there are rain streaks, water marks, and sky conditions in the global field of view. If the image gradients corresponding to multiple regions in the image are the same, it means that different regions of the image are relatively sharp and there are no foreign objects in the shooting area; if the image gradients corresponding to multiple regions in the image are different, it means that the sharpness of different regions of the image is different, and there are foreign objects in the shooting area with reduced sharpness.

[0226] For example, Figure 13This is a flowchart illustrating a process for determining whether a second preset condition is met.

[0227] like Figure 13 As shown, in S12041, first determine whether the overall density of the suspended particles is greater than the preset density threshold. If it is greater than the preset density threshold, continue to execute S12042; if it is not greater than the preset density, it is determined that the second preset condition is not met, and S1206 can be executed.

[0228] S12042. Determine whether the image gradients of multiple regions are different. If they are different, then the second preset condition is met, and S1205 can be executed. If they are not different, that is, the image gradients of multiple regions are the same, then the second preset condition is not met, and S1206 can be executed.

[0229] In this embodiment, the sensing sensor has higher detection precision and accuracy. Therefore, after roughly determining whether there is rain using a rain gauge, the data detected by the sensing sensor can be used to make a precise judgment on the target scene. Whether there is actual rain is determined by whether the data detected by the sensing sensor meets a first preset condition. When the data detected by the sensing sensor does not meet the first preset condition, the judgment results of the sensing sensor and the rain gauge are inconsistent, indicating that there is no rain and the data detected by the rain gauge is abnormal. At this time, whether there is foreign object attached can be determined by whether the data detected by the sensing sensor meets a second preset condition. When the data detected by the sensing sensor meets the second preset condition, it is determined that there is foreign object; when it does not meet the second preset condition, it is determined that there is no foreign object attached.

[0230] S1205. The target scene is determined to be a foreign object attachment scene.

[0231] For example, after determining that the target scenario is a foreign object attachment scenario, a fourth control command can be issued to the wiper motor. The fourth control command is used to indicate a single-use mode and cooperate with the water spray mode. In response to the fourth control command, the wiper motor can control the wiper blades to perform the single-use mode corresponding to the foreign object attachment scenario. At the same time, the water pump can spray water onto the windshield.

[0232] S1206. Determine the target scene as a rainless scene.

[0233] For example, after determining that the target scenario is a rainless scenario, a fifth control command can be issued to the wiper motor, wherein the fifth control command is used to indicate the off mode; in response to the fifth control command, the wiper motor can control the wiper blades to perform in the off mode corresponding to the rainless scenario, and stop the previously performed actions.

[0234] S1210: After determining in step S1201 that the relative change value detected by the rain gauge sensor is not greater than the first preset threshold, determine whether the data detected by the sensing sensor meets the third preset condition. Meeting the third preset condition indicates that the rainfall is low. If the third preset condition is met, execute S1211; if the third preset condition is not met, return to S1201 and start detecting again.

[0235] The third preset condition can be set and combined based on the type of sensing sensor.

[0236] Optionally, if the sensing sensor includes radar, the third preset condition may include: the overall density of suspended particles shows an upward trend and is less than a preset slope. If the sensing sensor includes a vision sensor, the third preset condition may at least include: the image gradient is less than a second gradient threshold, and the second gradient threshold is greater than a first gradient threshold. If the sensing sensor includes both radar and a vision sensor, the third preset condition may include: the overall density of suspended particles shows an upward trend and is less than a preset slope, and the image gradient is less than a second gradient threshold.

[0237] The preset slope and the second gradient threshold can be set as needed, and this application does not limit them.

[0238] It should be noted that when suspended particles show an upward trend, the preset slope is used to distinguish the speed of the rise. If the slope is greater than the preset slope, it indicates a significant rise, corresponding to a significant increase in rainfall in the environment; if the slope is less than the preset slope, it indicates a slight rise, corresponding to a slight increase in rainfall in the environment. The image gradient is used to distinguish the image sharpness and determine whether there are rain streaks, water marks, and sky conditions in the global field of view. If the gradient is less than the second gradient threshold, it indicates that the image is relatively blurry, corresponding to rain in the environment but with a small amount of rainfall; if the gradient is greater than or equal to the second gradient threshold, it indicates that the image is relatively clear, corresponding to no rain in the environment.

[0239] For example, Figure 14 This is a flowchart illustrating a process for determining whether a third preset condition is met.

[0240] like Figure 14 As shown, in S12101, first determine whether the overall density of the suspended particles is increasing and less than the preset slope. If it is increasing and less than the preset slope, then continue to execute S12102; if it is not increasing and less than the preset slope, then it is determined that the third preset condition is not met, and S1201 can continue to execute.

[0241] S12102. Determine if the image gradient is less than the second preset threshold (e.g., IG < 30). If it is less than the second gradient threshold, then the third preset condition is met, and S1211 can continue to be executed. If it is not less than the second gradient threshold, that is, greater than or equal to the second gradient threshold, then the third preset condition is not met, and S1201 can continue to be executed.

[0242] In this embodiment, the sensing sensor has higher detection precision and accuracy. Therefore, after roughly determining whether there is rain using a rain gauge, the data detected by the sensing sensor can be used to make a more precise judgment on the target scene. Whether there is actual rain is determined by whether the data detected by the sensing sensor meets a third preset condition. When the data detected by the sensing sensor meets the third preset condition, the judgment results of the sensing sensor and the rain gauge are inconsistent, indicating that the rain gauge's detection result is incorrect, and the sensing sensor has detected a light rain scene that the rain gauge cannot detect. In this case, the detection result of the sensing sensor is taken as the standard, indicating that the environment is indeed raining and the rainfall is light. When the data detected by the sensing sensor does not meet the third preset condition, it is determined to be interference such as dust or haze, which can be ignored.

[0243] In addition, steps S1201 and S1210 can also be executed simultaneously, and this application does not limit this.

[0244] S1211. The target scenario is determined to be a light rain scenario.

[0245] For example, after determining that the target scenario is a light rain scenario, a sixth control command can be issued to the wiper motor, wherein the sixth control command is used to indicate the intermittent mode; in response to the sixth control command, the wiper motor can control the wiper brush to perform in the intermittent mode corresponding to the light rain scenario.

[0246] Optionally, after step S1211 above, as follows: Figure 15 As shown, the method may further include steps S1212 to S1214.

[0247] S1212. Determine whether the relative change value detected by the rain gauge is greater than the third preset threshold. The third preset threshold is less than the first preset threshold, and the first preset threshold is less than the second preset threshold. If yes, proceed to S1213; otherwise, proceed to S1214.

[0248] The third preset threshold may include a third relative change value threshold for the rainfall intensity signal. The third preset threshold can be set and adjusted as needed, and this application does not limit it.

[0249] For example, assuming the third relative change value threshold is set to a relative change value of less than 20 mm over a 200 ms period, the relative change value of the rain sensor over a 200 ms period can be obtained and compared with the third relative change value threshold. If it is greater than the third relative change value threshold, it indicates that the rainfall intensity signal has changed very little. Based on the data detected by the rain sensor, it can be further refined to determine which specific scenario of light rainfall is currently present.

[0250] In this embodiment of the application, based on the data detected by the rain sensor and the sensing sensor, it has been determined that the current environment is actually raining and the rainfall is light. On this basis, the data detected by the rain sensor can be used again to further subdivide the light rain scenario. Therefore, by determining whether the data detected by the rain sensor is greater than the third preset threshold, it can be determined whether the current environment is a light rain scenario or a drizzle scenario.

[0251] S1213. Determine the target scene as a light rain scene.

[0252] For example, after determining that the target scenario is a light rain scenario, a seventh control command can be issued to the wiper motor, wherein the seventh control command is used to indicate a low-speed continuous mode; in response to the second control command, the wiper motor can control the wiper brush to perform in the low-speed continuous mode corresponding to the light rain scenario.

[0253] S1214. Determine the target scene as a drizzle scene.

[0254] For example, after determining that the target scenario is a drizzle scenario, an eighth control command can be issued to the wiper motor, wherein the eighth control command is used to indicate a short-term intermittent mode; in response to the eighth control command, the wiper motor can control the wiper brush to perform in accordance with the short-term intermittent mode corresponding to the drizzle scenario.

[0255] In the embodiments of this application, all scenarios with rainfall below the drizzle scenario level can adopt the execution strategy corresponding to the drizzle scenario.

[0256] Optionally, multiple other threshold ranges can be set to further subdivide the light rain scenario into light rain, drizzle, light rain, and fine rain, and then different wiping modes can be associated with different scenarios.

[0257] It should be noted that radars of different precisions have different hardware configurations and therefore different degrees of signal attenuation when measuring distant fixed targets. Therefore, in the above process, the judgment thresholds for the overall density of suspended particles of different radars in the first, second, and third preset conditions can be set to different values ​​as needed, and this application does not limit this.

[0258] Image features may also include image variance and / or spatial consistency. Therefore, in the first preset condition, the second preset condition, and the third preset condition, a judgment condition regarding image variance and / or spatial consistency may be added.

[0259] For example, if the sensing sensor includes a vision sensor, the first preset condition may further include: determining whether the image variance is less than a first variance threshold; the second preset condition may further include: determining whether the image variances of multiple regions are different; the third preset condition may further include: determining whether the image variance is less than a second variance threshold. The second variance threshold is greater than the first variance threshold.

[0260] In the above process, the threshold for judging image variance (such as the first variance threshold and the second variance threshold) in the first preset condition, the second preset condition and the third preset condition can be set as needed, and this application does not limit it.

[0261] For example, if the sensing sensor includes a vision sensor, the first preset condition may further include: determining whether the spatial consistency meets the first gear range; the second preset condition may further include: determining whether the spatial consistency meets the second gear range; and the third preset condition may further include: determining whether the spatial consistency meets the third gear range.

[0262] In the above process, the judgment thresholds for spatial consistency in the first, second, and third preset conditions (such as the upper and lower limits corresponding to the first, second, and third gear ranges, respectively) can be set as needed, and this application does not limit this.

[0263] In this embodiment, by connecting the wiper controller or central controller to both rain sensors and perception sensors (such as radar and vision sensors), data detected by the rain sensors and perception sensors is acquired. This allows for the fusion of multi-source data from various sensors, including rain sensors and perception sensors, to determine whether the vehicle's current environment is rainy, the corresponding rainfall level if it is rainy, and whether it is a scenario with foreign objects attached or a rainless scenario if it is not raining. Because the detection process combines data from multiple types of perception sensors, it provides richer and more accurate criteria for determining the target scenario, thus improving the accuracy of the determined target scenario and enabling the adaptation of more accurate wiping modes to the target scenario.

[0264] Compared to existing technologies, rain sensors may miss drizzle scenes, but perception sensors can sensitively detect them. Therefore, this application solves the problem of difficult shaving activation by utilizing the higher detection capability of the perception sensor. Furthermore, rain sensors may be falsely triggered, while the perception sensor, by combining data from multiple sensors and achieving high accuracy, can effectively reduce false shaving activation. This application's solution significantly improves the driving experience in rainy conditions and reduces safety issues caused by rain.

[0265] In this embodiment, after determining each target scenario and issuing corresponding control commands to the wiper motor, and the wiper motor responding to the control commands and controlling the wiper brush to perform the wiping mode corresponding to the target scenario, this application can further determine whether the wiping effect meets the standard based on the data detected by the sensing sensor. If yes, the current state is maintained or extended; if not, a new strategy can be executed based on the new data detected by the sensing sensor.

[0266] In addition, embodiments of this application can also use only the data detected by the sensing sensor to determine the target scene and control accordingly.

[0267] Figure 16 This is a flowchart illustrating another windshield wiper control method provided in an embodiment of this application. Figure 16 As shown, this method can be applied to the above. Figure 3 In the vehicle shown. The method may include steps S210 to S230.

[0268] S210. Acquire data detected by a sensing sensor, which includes at least one of radar and vision sensors.

[0269] The process of acquiring radar detection data and visual sensor detection data can be referred to in step S110 above, and will not be repeated here.

[0270] S220. Based on the data detected by the sensing sensor, determine the target scene. The target scene is at least one of the following: heavy rainfall scene, light rainfall scene, foreign object attachment scene, and no rain scene.

[0271] The target scenario can be referred to in step S120 above, and will not be repeated here.

[0272] It should be noted that the process of determining the target scene based on the data detected by the perception sensor can refer to the above steps S1202, 1204 and S1210, as well as the descriptions in steps S1207 and 1212.

[0273] S230: Issue control commands. The control commands are used to instruct the wiper blades to execute the wiping mode corresponding to the target scenario.

[0274] The process of issuing control commands and the brushing mode can be referred to in the description of step S130 above, and will not be repeated here.

[0275] This application provides a windshield wiper control method that, by acquiring and utilizing data detected by a sensing sensor, determines whether the vehicle's current environment is rainy, the corresponding rainfall level if it is raining, and whether the environment is one with foreign objects attached or no rain if it is not raining. Because the detection data from the sensing sensor is used during the detection process, it provides rich and accurate criteria for determining the target scene, thus improving the accuracy of the determined target scene and allowing for a more precise wiping mode to be adapted to the target scene.

[0276] Compared to existing technologies, this application, through data detected by sensing sensors, can solve problems such as difficulty in shaving and accidental shaving. This significantly improves the driving experience in rainy conditions and reduces safety issues caused by rain.

[0277] This application embodiment also provides a vehicle, which includes a processor and a memory coupled together. The memory stores a computer program, which includes computer instructions. The processor is used to run the computer program or instructions, causing the vehicle to perform the aforementioned actions. Figure 7 , Figures 9 to 16 The steps in the method described in the illustrated embodiment.

[0278] This application also provides a computer-readable storage medium storing a program that, when run on a computer, causes the computer to perform actions such as... Figure 7 , Figures 9 to 16 The steps in the method described in the illustrated embodiment.

[0279] This application also provides a computer program product, which includes a program that, when run on a computer, causes the computer to perform the aforementioned actions. Figure 7 , Figures 9 to 16 The steps in the method described in the illustrated embodiment.

[0280] This application embodiment also provides a circuit system, the circuit system including a processing circuit, the processing circuit being configured to perform such... Figure 7 , Figures 9 to 16 The steps in the method described in the illustrated embodiment.

[0281] The planning data acquisition device provided in this application embodiment can specifically be a chip. The chip includes a processing unit, which may be, for example, a processor. Optionally, the chip also includes a communication unit, which may be, for example, an input / output interface, pins, or circuits. The processing unit can execute computer execution instructions stored in the storage unit to cause the chip to perform the above-mentioned tasks. Figures 1 to 12 The method described in the illustrated embodiment. Optionally, the storage unit is a storage unit within the chip, such as a register, cache, etc. The storage unit can also be a storage unit located outside the chip within the wireless access device, such as a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, random access memory (RAM), etc.

[0282] The processor mentioned above can be a general-purpose central processing unit, a microprocessor, an ASIC, or one or more integrated circuits used to control the execution of a program in the first aspect of the method.

[0283] It should also be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. In addition, in the device embodiment drawings provided in this application, the connection relationship between modules indicates that they have a communication connection, which can be implemented as one or more communication buses or signal lines.

[0284] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware, and of course, it can also be implemented by special hardware including application-specific integrated circuits, special-purpose CLUs, special-purpose memory, special-purpose components, etc. Generally, any function performed by a computer program can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be diverse, such as analog circuits, digital circuits, or special-purpose circuits. However, for this application, software program implementation is more often the preferred implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium, such as a computer floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk, or optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0285] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product.

[0286] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0287] The above description is merely a specific embodiment of this application. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the protection scope of this application. The protection scope of this application should be determined by the protection scope of the claims.

Claims

1. A windshield wiper control method, characterized in that, The method includes: Acquire data detected by a rain gauge and a sensing sensor, wherein the sensing sensor includes at least one of a radar and a vision sensor; Based on the data detected by the rain sensor and the sensing sensor, a target scene is determined, wherein the target scene is at least one of the following: heavy rain scene, light rain scene, foreign object attachment scene, and no rain scene. A control command is issued, which instructs the wiper blades to perform the wiping operation according to the wiping mode corresponding to the target scenario.

2. The method as described in claim 1, characterized in that, Based on the data detected by the rain gauge and the sensing sensor, the target scene is determined, including: Based on the data detected by the rain sensor, determine whether it is greater than a first preset threshold. If so, based on the data detected by the sensing sensor, it is determined whether the first preset condition is met. Meeting the first preset condition is used to indicate heavy rainfall. If the first preset condition is met, then the target scenario is determined to be a heavy rainfall scenario.

3. The method as described in claim 2, characterized in that, After determining whether the first preset condition is met based on the data detected by the sensing sensor, the method further includes: If not, then based on the data detected by the sensing sensor, it is determined whether the second preset condition is met. Meeting the second preset condition is used to indicate the attachment of foreign objects. If the second preset condition is met, then the target scene is determined to be the foreign object attachment scene; If the second preset condition is not met, then the target scene is determined to be the rainless scene.

4. The method as described in claim 2 or 3, characterized in that, The heavy rainfall scenario includes at least heavy rain scenario and moderate rain scenario; After determining that the target scenario is a heavy rainfall scenario, the method further includes: determining whether the data detected by the rainfall sensor is greater than a second preset threshold, wherein the second preset threshold is greater than the first preset threshold; If so, then the target scenario is determined to be the heavy rain scenario; If not, then the target scenario is determined to be the moderate rain scenario.

5. The method according to any one of claims 2 to 4, characterized in that, After determining whether the data detected by the rain gauge is greater than a first preset threshold, the method further includes: If not, then based on the data detected by the sensing sensor, it is determined whether the third preset condition is met. Meeting the third preset condition is used to indicate that the rainfall is low. If the third preset condition is met, then the target scenario is determined to be a light rain scenario.

6. The method as described in claim 5, characterized in that, The light rainfall scenario includes at least light rain scenario and drizzle scenario; After determining that the target scenario is a light rain scenario, the method further includes: determining whether the data detected by the rain sensor is greater than a third preset threshold, wherein the third preset threshold is less than the first preset threshold; If so, then the target scene is determined to be the light rain scene; If not, then the target scene is determined to be the drizzle scene.

7. The method according to any one of claims 1 to 6, characterized in that, Acquire data detected by the rain gauge, including: Acquire the rainfall intensity signal collected by the rain sensor; The method further includes: determining the changing trend and relative change value of the rainfall intensity signal based on the rainfall intensity signal.

8. The method according to any one of claims 1 to 7, characterized in that, When the sensing sensor includes radar, specifically lidar and / or millimeter-wave radar, acquiring the data detected by the sensing sensor includes: Acquire the point cloud data collected by the radar; The method further includes: determining the overall density of suspended particles based on the point cloud data.

9. The method as described in claim 8, characterized in that, Based on the point cloud data, the overall density of the suspended particles is determined, including: The point cloud data is processed to determine the spurious values ​​and the difference in laser intensity between adjacent frames; The overall density of the suspended particles is determined based on the stray value and the difference in laser intensity between adjacent frames.

10. The method as described in claim 9, characterized in that, The point cloud data is processed to determine spurious values ​​and laser intensity differences between adjacent frames, including: Cluster the point cloud data to determine the spurious values; The point cloud data is processed using a dynamic target tracking algorithm to determine the laser intensity difference between adjacent frames.

11. The method according to any one of claims 8 to 10, characterized in that, The first preset condition includes: the overall density of the suspended particles shows an upward trend and is greater than a preset slope; The second preset condition includes: the overall density of the suspended particles is greater than a preset density threshold; The third preset condition includes: the overall density of the suspended particles shows an upward trend and is less than the preset slope.

12. The method according to any one of claims 1 to 11, characterized in that, When the sensing sensor includes a vision sensor, acquiring the data detected by the sensing sensor includes: acquiring the image collected by the vision sensor; The method further includes: determining image features of the image, the image features including image gradients.

13. The method as described in claim 12, characterized in that, The first preset condition includes: the image gradient is less than a first gradient threshold; The second preset condition includes: the image gradients corresponding to multiple regions in the image are different; The third preset condition includes: the image gradient is less than the second gradient threshold, and the second gradient threshold is greater than the first gradient threshold.

14. The method as described in claim 12 or 13, characterized in that, The image features also include image variance and / or spatial consistency.

15. A windshield wiper system, characterized in that, The wiper system includes a rain sensor, a wiper controller, a wiper motor, and wiper blades; the wiper controller is connected to the rain sensor, the wiper motor, and a sensing sensor, and the wiper motor is connected to the wiper blades; the sensing sensor includes at least one of radar and a vision sensor. The wiper controller is used to perform the wiper control method as described in any one of claims 1 to 14; The wiper motor is used to respond to the control command and control the wiper blades to perform wiping operations according to the wiping mode corresponding to the target scene.

16. A vehicle, characterized in that, The vehicle includes a central controller, sensing sensors, and a wiper system, wherein the wiper system includes a rain sensor, a wiper controller, a wiper motor, and wiper blades; the sensing sensors include at least one of radar and a vision sensor. The central controller is connected to the sensing sensor, the rain sensor and the wiper controller respectively, and the wiper motor is connected to the wiper blade; The central controller is used to execute the wiper control method as described in any one of claims 1 to 14; The central controller is also used to send control commands to the wiper motor through the wiper controller; The wiper motor is used to respond to the control command and control the wiper blades to perform wiping operations according to the wiping mode corresponding to the target scene.

17. The vehicle as described in claim 16, characterized in that, The radar is a lidar and / or millimeter-wave radar, and the vision sensor is a forward-facing vision sensor.

18. A vehicle, characterized in that, It includes a processor and a memory, the processor being coupled to the memory, the memory storing a computer program, the computer program including computer instructions; The processor is configured to run computer programs or instructions that cause the vehicle to perform the method as described in any one of claims 1 to 14.

19. A readable storage medium, characterized in that, The readable storage medium includes instructions that, when executed by at least one processor of the device, cause the device to perform the method as described in any one of claims 1 to 14.

20. A computer program product, characterized in that, The computer program product includes instructions that, when executed by at least one processor of the device, cause the device to perform the method as described in any one of claims 1 to 14.

21. A chip, characterized in that, The chip includes a processor for performing the method of any one of claims 1 to 14.

Images