Methods, apparatuses, devices, and storage media for wiper control

Abstract

The application discloses a method, device and equipment for controlling a windscreen wiper and a storage medium, and belongs to the technical field of automobiles. The method specifically comprises the following steps: acquiring image information, point cloud information and spectrum information of a windscreen of a vehicle; performing particulate matter identification processing on the windscreen by using a preset identification strategy based on the image information, the point cloud information and the spectrum information of the windscreen, so as to obtain first characteristic parameters of particulate matter; performing conversion processing on the first characteristic parameters of the particulate matter, so as to construct particulate matter map information in the coordinate system of the windscreen; determining a windscreen wiper control strategy by using a preset decision algorithm based on the particulate matter map information; and controlling the windscreen wiper to perform a wiping operation on the windscreen based on the windscreen wiper control strategy.

Description

Technical Field

[0001] This application relates to the field of automotive technology, specifically to vehicle cleaning technology, vehicle control technology, and other technical fields, and particularly to a method, device, equipment, and storage medium for windshield wiper control. Background Technology

[0002] During daily driving and parking, various particles inevitably accumulate on the surface of the windshield. When the driver activates the wipers to clean it, some particles may be caught by the wiper blades and slide across the glass, causing scratches on the windshield and wear on the wiper blades. Severe glass scratches may cause glare under certain lighting conditions or scatter oncoming headlights at night, interfering with the driver's vision and posing a safety hazard.

[0003] Currently, most particulate matter removal solutions attempt to remove particles before wiping. However, they cannot fundamentally prevent particles from entering the contact interface between the wiper blade and the glass. If particles are not completely removed, or if they are caught under the rubber strip during wiping, they can still scratch the glass surface. Summary of the Invention

[0004] This application provides a method, apparatus, device, and storage medium for controlling windshield wipers, which can solve the problem of damage to the windshield and wiper blades during windshield wiper cleaning. The technical solution is as follows: In a first aspect, a method for controlling a windshield wiper is provided, the method comprising: Acquire image information, point cloud information, and spectral information of the vehicle's windshield; Based on the image information, point cloud information, and spectral information of the windshield, a preset recognition strategy is used to perform particulate matter recognition processing on the windshield to obtain the first characteristic parameters of the particulate matter. The first characteristic parameters of the particulate matter are transformed to construct particulate matter map information in the windshield coordinate system; Based on the particulate matter map information, a preset decision algorithm is used to determine the wiper control strategy. Based on the aforementioned wiper control strategy, the wipers are controlled to perform a wiping operation on the windshield.

[0005] In one possible implementation, the first characteristic parameters of the particulate matter include a first image recognition result of the particulate matter, a first height of the particulate matter, a first hardness of the particulate matter, and a first adhesion strength of the particulate matter. Based on the image information, point cloud information, and spectral information of the windshield, a preset recognition strategy is used to perform particulate matter recognition processing on the windshield to obtain the first characteristic parameters of the particulate matter, including: The image information of the windshield is processed for particulate matter recognition to obtain a first image recognition result of particulate matter. Based on the point cloud information of the windshield and the first image recognition result of the particulate matter, the first height of the particulate matter is obtained using a height recognition algorithm; Based on the spectral information of the windshield and the first image recognition result of the particulate matter, the first hardness of the particulate matter is obtained using a hardness estimation algorithm; Based on the first image recognition result of the particulate matter, the first adhesion strength of the particulate matter is obtained using an adhesion strength analysis algorithm.

[0006] In one possible implementation, the transformation processing of the first feature parameters of the particulate matter to construct particulate matter map information in the windshield coordinate system includes: Based on the first image recognition result of the particulate matter, the first feature parameters of the particulate matter are subjected to coordinate system transformation to obtain the second feature parameters of the particulate matter in the windshield coordinate system. The particulate matter map information is constructed based on the second feature parameters of the particulate matter in the windshield coordinate system.

[0007] In one possible implementation, determining the wiper control strategy based on the particulate matter map information using a preset decision algorithm includes: The second feature parameters of the particles in the particulate map information are obtained. The second feature parameters of the particles include the second image recognition result of the particles, the second height of the particles, the second hardness of the particles, and the second adhesion strength of the particles. If the second image recognition result of the particulate matter and the second hardness of the particulate matter meet the preset avoidance conditions, the wiper control strategy is determined to be a wiper avoidance strategy based on the preset oscillation speed, the second image recognition result of the particulate matter and the second height of the particulate matter. If the second image recognition result of the particulate matter and the second hardness of the particulate matter meet the preset decompression conditions, the wiper control strategy is determined to be a wiper decompression strategy. If the second adhesion strength of the particulate matter meets the preset pre-removal conditions, the wiper control strategy is determined to be a pre-removal strategy.

[0008] In one possible implementation, controlling the windshield wipers to perform the wiping operation based on the wiper control strategy includes: When the wiper control strategy is determined to be a wiper avoidance strategy, based on the preset swing speed, the second image recognition result of the particulate matter and the second height of the particulate matter, a preset lifting algorithm is used to obtain the lifting height, lifting time and lifting position, so as to control the wiper to perform a wiping operation on the windshield based on the lifting height, lifting time and lifting position. When the wiper control strategy is determined to be a wiper decompression strategy, the wiper is controlled to perform a wiping operation on the windshield based on a preset pressure value. If the wiper control strategy is determined to be a pre-cleaning strategy, the windshield is pre-cleaned in order to control the wipers to perform a wiping operation on the pre-cleaned windshield.

[0009] Secondly, a windshield wiper control device is provided, the device comprising: The acquisition unit is used to acquire image information, point cloud information, and spectral information of the vehicle's windshield; The identification unit is used to perform particulate matter identification processing on the windshield based on the image information, point cloud information and spectral information of the windshield, using a preset identification strategy, so as to obtain the first characteristic parameters of the particulate matter. The construction unit is used to transform the first feature parameters of the particulate matter to construct particulate matter map information in the windshield coordinate system. The determining unit is used to determine the wiper control strategy based on the particulate matter map information and using a preset decision algorithm. The control unit is used to control the windshield wipers to perform wiping operations on the windshield based on the wiper control strategy.

[0010] Thirdly, a computer-readable storage medium is provided, wherein at least one instruction is stored therein, the at least one instruction being loaded and executed by a processor to implement the aspects and any possible implementations described above.

[0011] Fourthly, an electronic device is provided, comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the methods described above and any possible implementations.

[0012] Fifthly, a vehicle is provided that includes the electronic equipment described in the aforementioned aspects.

[0013] The beneficial effects of the technical solution provided in this application include at least the following: As can be seen from the above technical solution, the embodiments of this application can acquire image information, point cloud information, and spectral information of the windshield of a vehicle. Based on this information, a preset recognition strategy can be used to perform particulate matter identification processing on the windshield to obtain the first feature parameters of the particulate matter. These first feature parameters are then converted to construct a particulate matter map in the windshield coordinate system. Based on this map, a preset decision algorithm is used to determine a wiper control strategy. Based on this strategy, the wipers are controlled to perform wiping operations on the windshield. Because the particulate matter on the windshield can be identified first, and the corresponding wiper control strategy can be determined based on the particulate matter feature information, the sliding friction between the particulate matter and the glass is reduced, lowering the risk of damage to the glass and wiper blades, thereby ensuring the service life of the windshield and wipers.

[0014] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a schematic flowchart of a windshield wiper control method provided in one embodiment of this application; Figure 2 This is a structural block diagram of a wiper control device provided in another embodiment of this application; Figure 3 This is a block diagram of an electronic device used to implement the wiper control method of the embodiments of this application. Detailed Implementation

[0017] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of this application, including various details to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0018] Obviously, the described embodiments are only some, not all, of the embodiments in this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.

[0019] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0020] Please refer to Figure 1 This document illustrates a flowchart of a windshield wiper control method according to an embodiment of this application. This windshield wiper control method can be applied to a windshield wiper control system and may specifically include: Step 101: Obtain image information, point cloud information, and spectral information of the vehicle's windshield.

[0021] Step 102: Based on the image information, point cloud information and spectral information of the windshield, use a preset recognition strategy to perform particulate matter recognition processing on the windshield to obtain the first feature parameters of the particulate matter.

[0022] Step 103: Convert the first characteristic parameters of the particulate matter to construct particulate matter map information in the windshield coordinate system.

[0023] Step 104: Based on the particulate matter map information, determine the wiper control strategy using a preset decision algorithm.

[0024] Step 105: Based on the aforementioned wiper control strategy, control the wipers to perform a wiping operation on the windshield.

[0025] It should be noted that the image information of the windshield can be acquired through a camera. The point cloud information of the windshield can be acquired through a LiDAR scanner. The spectral information of the windshield can be acquired through a multispectral light source integrated into the camera. The spectral information can include light reflectivity.

[0026] It should be noted that the number of particles in the particulate matter map information can be one or more.

[0027] It should be noted that the windshield wiper control system may include a camera, lidar, control unit, piezoelectric micro-motion mechanism, wiper motor driver, wiper actuator, and piezoelectric high-voltage driver, etc.

[0028] The camera, mounted behind the rearview mirror, uses a 5-megapixel CMOS sensor with a 30fps frame rate and wide dynamic range to adapt to different lighting conditions such as backlighting and nighttime. The lens covers the entire windshield, capturing two-dimensional images of it. Multispectral light sources, including infrared LEDs (850nm, 940nm) and ultraviolet LEDs (365nm), are integrated into the camera module for material identification. A lidar unit, mounted on the front roof, uses a 905nm wavelength with 16 scan lines and a point cloud density of at least 100 points per square centimeter, accurately measuring the three-dimensional size and height of particles with an accuracy of ±0.1mm. The control unit can employ a multi-core heterogeneous processor, including ARM Cortex-A72 and Cortex-M4 cores. The ARM Cortex-A72 core is used for image processing and AI inference, while the Cortex-M4 core is used for real-time control. It includes 4GB of LPDDR4 memory and 32GB of eMMC storage. A piezoelectric micro-motion mechanism can be integrated at the connection between the wiper arm and the wiper blade. This mechanism may include a piezoelectric stack, a flexible hinge amplification mechanism, a displacement sensor, and the wiper blade. The piezoelectric stack can be composed of multiple layers of piezoelectric ceramic sheets, with dimensions of 5mm × 5mm × 10mm. The flexible hinge amplification mechanism uses an integrated flexible hinge to amplify the 15μm displacement of the piezoelectric stack to 600μm (0.6mm), allowing the wiper blade to be locally lifted to avoid most particles. The displacement sensor can be a miniature inductive displacement sensor with a resolution of 0.5μm, monitoring the wiper blade lift height in real time to form a closed-loop control. The wiper blade can be a traditional rubber wiper blade with an interface on its back for connection to the piezoelectric micro-motion mechanism. The wiper motor driver can be PWM controlled, allowing precise adjustment of the wiper oscillation speed and position. The piezoelectric high-voltage driver can be a 256-channel high-voltage amplifier, with each channel outputting 0-200V high voltage and a rise time of less than 50μs. It is used to independently control multiple drive points of the piezoelectric micro-motion mechanism, achieving localized lifting of the wiper blade. This control can be segmented along the length of the wiper blade. The wiper actuator can include a wiper arm and a wiper blade. The wiper arm contains a piezoelectric micro-motion mechanism for driving the wiper blade to perform micro-lifting perpendicular to the wiping direction.

[0029] In this way, by acquiring image information, point cloud information, and spectral information of the vehicle's windshield, and then using a preset recognition strategy based on the image information, point cloud information, and spectral information of the windshield, particulate matter identification processing can be performed on the windshield to obtain the first feature parameters of the particulate matter. The first feature parameters of the particulate matter are then transformed to construct particulate matter map information in the windshield coordinate system. Based on the particulate matter map information, a preset decision algorithm is used to determine the wiper control strategy. Based on the wiper control strategy, the wipers are controlled to wipe the windshield. Since the particulate matter on the windshield can be identified first, and the corresponding wiper control strategy can be determined based on the particulate matter feature information, the sliding friction between the particulate matter and the glass is reduced, lowering the risk of particulate matter scratching the glass and damaging the wiper blades, thereby ensuring the service life of the windshield and wipers.

[0030] Optionally, in one possible implementation of this embodiment, in step 102, the first characteristic parameters of the particulate matter include the first image recognition result of the particulate matter, the first height of the particulate matter, the first hardness of the particulate matter, and the first adhesion strength of the particulate matter. In step 102, firstly, particulate matter recognition processing can be performed on the image information of the windshield to obtain the first image recognition result of the particulate matter. Secondly, based on the point cloud information of the windshield and the first image recognition result of the particulate matter, a height recognition algorithm can be used to obtain the first height of the particulate matter. Thirdly, based on the spectral information of the windshield and the first image recognition result of the particulate matter, a hardness estimation algorithm can be used to obtain the first hardness of the particulate matter. Finally, based on the first image recognition result of the particulate matter, an adhesion strength analysis algorithm can be used to obtain the first adhesion strength of the particulate matter.

[0031] In one specific implementation of this method, an image semantic segmentation model can be used to perform particulate matter recognition processing on the image information of the windshield to obtain a segmentation mask and a category of particulate matter. Then, based on the segmentation mask and the category of particulate matter, the first image recognition result of the particulate matter can be obtained.

[0032] In this implementation, the image semantic segmentation model can be based on the lightweight instance segmentation network YOLACT, and the backbone network can be MobileNetV3. This allows for segmentation accuracy while maintaining a single-frame inference time of less than 30ms, thus meeting real-time requirements.

[0033] Here, the image semantic segmentation model can be pre-trained using sample windshield images. These sample windshield images can include gravel particles, biological particles, and industrial particles. Gravel particles can include quartz sand, river sand, and construction dust. Biological particles can include pollen, shellac, and bird droppings. Industrial particles can include carbon powder, metal shavings, and rubber powder. The scenes in the sample windshield images include sunny days, cloudy days, rainy days, nighttime, backlighting, and strong sidelighting. Pixel-level instance segmentation and annotation are performed on each image, treating each particle as an independent instance and annotating its contour. For an input 1280×720 image, the image semantic segmentation model output can include an instance segmentation mask, i.e., the contour of each particle, the material category probability distribution of each instance, and the confidence score of each instance.

[0034] In this implementation, the first image recognition result of the particulate matter may include the first size of the particulate matter, the first diameter of the particulate matter, and the first position of the particulate matter.

[0035] Here, the first diameter of the particle can be the equivalent diameter of the image region of the particle. The first diameter of the particle can be calculated based on its first size.

[0036] In another specific implementation of this method, the point cloud information of the windshield and the first position of the particulate matter are matched to obtain the height information in the point cloud information corresponding to the particulate matter. Based on the height information in the point cloud information corresponding to the particulate matter and the preset glass base height, the first height of the particulate matter is calculated.

[0037] In one specific implementation, when the first position of the particle does not match the point cloud information of the windshield, the first height of the particle can be calculated based on the product of the first diameter of the particle and a preset coefficient.

[0038] Preferably, the preset coefficient can be 0.3.

[0039] In this implementation, the first image recognition result of the particulate matter may also include the first category of the particulate matter. The spectral information of the windshield may include light reflectance.

[0040] In another specific implementation of this method, the spectral information of the particles can be determined based on the spectral information of the windshield and the first position of the particles. Then, based on the spectral information of the particles and the first category of the particles, the first hardness of the particles can be obtained using a preset hardness table.

[0041] Here, the first hardness of particulate matter can include a hardness rating.

[0042] For example, a preset hardness table can be shown in Table 1: Table 1:

[0043] One specific implementation method involves using a hardness estimation model based on the spectral information of the windshield, the first size of the particulate matter, and the first position of the particulate matter to output the hardness level of the particulate matter, and using the hardness level of the particulate matter as the first hardness of the particulate matter.

[0044] Here, the hardness estimation model can be a model based on a random forest classifier, and the spectral information of the windshield can include the multi-band reflectance of particulate matter, such as the reflectance of the 850nm, 940nm, and 365nm bands.

[0045] In this implementation, the first image recognition result of particulate matter can be the first image recognition result of particulate matter corresponding to multiple frames of images.

[0046] In another specific implementation of this method, the first position of the particles in three adjacent frames can be obtained based on the first image recognition result of the particles. If the displacement difference between the first positions of the particles in three adjacent frames is less than a preset first distance threshold, the first adhesion strength of the particles is determined to be a high adhesion strength value. If the displacement difference between the first positions of the particles in three adjacent frames is greater than a preset second distance threshold, the first adhesion strength of the particles is determined to be a low adhesion strength value.

[0047] In this implementation, preferably, the first preset distance threshold can be 0 or a small distance value. The second preset distance threshold can be 5 centimeters or a large distance value.

[0048] In this implementation, the first adhesion strength can be a strength level value from 1 to 5. 1 can represent a low adhesion strength value, and 5 can represent a high adhesion strength value.

[0049] It is understandable that a high initial adhesion strength value for particulate matter indicates that the particulate matter is firmly attached and difficult to remove. Conversely, a low initial adhesion strength value indicates that the particulate matter is loose and relatively easy to remove.

[0050] In this way, by using the image information, point cloud information, and spectral information of the windshield respectively, and employing the corresponding algorithms, we can obtain more accurate and effective first image recognition results of particles, first height of particles, first hardness of particles, and first adhesion strength of particles, so that we can subsequently determine a more accurate strategy for controlling the windshield wipers.

[0051] Optionally, in one possible implementation of this embodiment, in step 103, firstly, based on the first image recognition result of the particulate matter, a coordinate system transformation process can be performed on the first feature parameters of the particulate matter to obtain the second feature parameters of the particulate matter in the windshield coordinate system. Secondly, based on the second feature parameters of the particulate matter in the windshield coordinate system, the particulate matter map information can be constructed.

[0052] In this implementation, the first image recognition result of the particulate matter may include the first position of the particulate matter. This first position of the particulate matter may be its position coordinates in the image coordinate system.

[0053] In a specific implementation of this method, based on a preset calibration matrix, the first position of the particulate matter is transformed to the windshield coordinate system to obtain the second position of the particulate matter in the windshield coordinate system. Based on the second position of the particulate matter, the second image recognition result, the second height, the second hardness, and the second adhesion strength of the particulate matter in the windshield coordinate system are obtained to determine the second feature parameters of the particulate matter. Based on the second feature parameters of the particulate matter, the particulate matter map information is constructed.

[0054] In another specific implementation of this method, the particulate map information is constructed based on a preset grid and the second feature parameters of the particles.

[0055] In this implementation, preferably, the grid precision can be 1mm × 1mm.

[0056] In this way, the feature parameters of the particles can be transformed into the windshield coordinate system based on the first image recognition result of the particles, so as to obtain the particle feature parameters for constructing the windshield, which can improve the reliability of the particle map information.

[0057] It should be noted that the specific implementation process provided in this embodiment can be combined with various specific implementation processes provided in the aforementioned implementation methods to implement the wiper control method of this embodiment. Detailed descriptions can be found in the relevant content of the aforementioned implementation methods, and will not be repeated here.

[0058] Optionally, in one possible implementation of this embodiment, in step 104, firstly, the second feature parameters of the particles in the particulate matter map information can be obtained. These second feature parameters include the second image recognition result of the particles, the second height of the particles, the second hardness of the particles, and the second adhesion strength of the particles. Secondly, if the second image recognition result and the second hardness of the particles satisfy a preset avoidance condition, the wiper control strategy can be determined as a wiper avoidance strategy based on a preset oscillation speed, the second image recognition result of the particles, and the second height of the particles. Thirdly, if the second image recognition result and the second hardness of the particles satisfy a preset decompression condition, the wiper control strategy can be determined as a wiper decompression strategy. Finally, if the second adhesion strength of the particles satisfies a preset pre-clearing condition, the wiper control strategy can be determined as a pre-clearing strategy.

[0059] In this implementation, the second image recognition result of the particulate matter may include the second diameter of the particulate matter.

[0060] In this implementation, the preset avoidance conditions may include the second diameter of the particle being greater than or equal to a preset diameter threshold, and the second hardness being greater than or equal to a preset hardness threshold.

[0061] Preferably, the preset diameter threshold can be 0.5 mm. The preset hardness threshold can be 3.

[0062] In one specific implementation of this method, when the second diameter of the particle is greater than or equal to a preset diameter threshold and the second hardness is greater than or equal to a preset hardness threshold, the wiper control strategy is determined to be a wiper avoidance strategy based on the preset oscillation speed, the second image recognition result of the particle, and the second height of the particle.

[0063] In one specific implementation, when the wiper control strategy is determined to be a wiper avoidance strategy, a preset lifting algorithm is used to obtain the lifting height, lifting time, and lifting position based on the preset swing speed, the second image recognition result of the particles, and the second height of the particles. Based on the lifting height, lifting time, and lifting position, the wiper is controlled to perform a wiping operation on the windshield.

[0064] In this implementation, for example, the wiper avoidance strategy can be shown in the following code: FUNCTION plan_lift_trajectory(lift_height, approach_speed): / / lift_height: Target lift height / / approach_speed: The speed at which the scraper approaches the particle / / Lift-up time: set to 50ms to ensure it is imperceptible to the human eye. lift_time = 50 ms / / Calculate the lifting start position based on the approach speed start_position = particle_position - approach_speed * lift_time / 2 / / Generate trajectory trajectory = generate_s_curve(0, lift_height, lift_time) RETURN {start_position, trajectory} END FUNCTION Here, the speed at which the scraper approaches the particles can be a preset oscillation speed.

[0065] In this implementation, the second image recognition result of the particulate matter may also include the second location of the particulate matter.

[0066] Preferably, firstly, the lifting time can be calculated based on a preset oscillation speed, the starting position of the wiper, and the second position of the particulate matter. Secondly, the lifting height can be calculated based on the second height of the particulate matter and a preset height offset. Thirdly, the lifting position can be obtained based on the second position of the particulate matter.

[0067] Here, preferably, the preset height offset can be 0.1mm.

[0068] It is understood that control commands can be generated based on the lifting height, lifting time, and lifting position, and based on these control commands, the windshield wipers can be controlled to perform a wiping operation on the windshield.

[0069] In this implementation, the preset decompression conditions may include a second diameter smaller than a preset diameter threshold and a second hardness greater than or equal to a preset hardness threshold.

[0070] Preferably, the preset diameter threshold can be 0.5 mm. The preset hardness threshold can be 3.

[0071] In another specific implementation of this method, when the second diameter is less than a preset diameter threshold and the second hardness is greater than or equal to a preset hardness threshold, the wiper control strategy is determined to be a wiper decompression strategy.

[0072] In one specific implementation, if the wiper control strategy is determined to be a wiper decompression strategy, the wiper is controlled to perform a wiping operation on the windshield based on a preset pressure value.

[0073] Here, the preset pressure value can be determined based on a preset pressure reduction percentage. The preset pressure value can be determined according to the actual conditions of the windshield and wiper products.

[0074] In this implementation, the pre-removal condition may include a second adhesion strength less than or equal to a preset adhesion strength threshold.

[0075] Here, preferably, the preset adhesion strength threshold can be 2.

[0076] In another specific implementation of this method, the wiper control strategy can be determined as a pre-cleaning strategy if the second adhesion strength is less than or equal to a preset adhesion strength threshold.

[0077] One specific implementation method involves pre-cleaning the windshield when the wiper control strategy is determined to be a pre-cleaning strategy, so as to control the wipers to perform a wiping operation on the pre-cleaned windshield.

[0078] In this implementation, the pre-cleaning process may include air blowing or micro-spraying.

[0079] Another specific implementation process is as follows: when the wiper control strategy is determined to be a pre-cleaning strategy, the time it takes for the wiper blade to reach the particles is calculated based on the position of the particles and the current speed of the wiper. Then, based on the arrival time and a preset time offset, the pre-cleaning start time is determined. Based on the pre-cleaning start time and the preset cleaning duration, the cleaning device is controlled to pre-clean the particles, and then the wiper is controlled to wipe.

[0080] Here, preferably, the preset time offset can be 0.2s. The preset clearing duration can be 0.3s.

[0081] For example, when it is determined that pre-removal is needed, the arrival time t_arrive is calculated based on the position of the particles and the current speed of the wipers. At t_arrive-0.2s, a micro-blowing device is activated and lasts for 0.3s to blow loosely attached particles away from the glass surface, and then the wipers are controlled to wipe.

[0082] Understandably, a pre-removal strategy could be to remove particles with low adhesion strength by spraying washing liquid or activating a micro-blowing device before the scraper arrives.

[0083] In this implementation, for example, during the process of determining the wiper control strategy based on the particulate matter map information and using a preset decision algorithm, the preset decision algorithm can be represented by the following code: FUNCTION decide_avoidance_strategy(particle): / / particle: {diameter, height, hardness, stickiness} / / Default strategy: No avoidance, normal pressure strategy = {action: "none", pressure_reduction: 0, lift_height:0} / / Hard and large particles → Forced avoidance IF particle.hardness>= 3 AND particle.diameter>= 0.5 mm THEN strategy.action = "lift" strategy.lift_height = particle.height + 0.1 mm / / Add safety clearance / / Hard particles but small size → Reduce pressure ELSE IF particle.hardness>= 3 AND particle.diameter<0.5 mm THEN strategy.action = "reduce_pressure" strategy.pressure_reduction = 30% / / Reduce downpressure by 30% / / Soft particles → No treatment ELSE strategy.action = "none" END IF / / Weak adhesion → Try pre-cleaning even if the size is small IF particle.stickiness<= 2 AND strategy.action == "none" THEN / / Trigger pre-cleaning (blowing or micro-spraying) trigger_pre_clean(particle.position) END IF RETURN strategy END FUNCTION In another specific implementation of this method, the second image recognition result of the particulate matter may also include the second size of the particulate matter. If the second size of any particulate matter in the particulate matter map information is greater than a preset size threshold, the wiper activation is paused, and a cleaning prompt message is displayed, allowing the driver to determine whether to restart the wipers based on the cleaning prompt message.

[0084] For example, if a large number of hard particles are detected before the wipers start, the system can display "Hard particles detected, we recommend spraying water to soften them first" on the HUD and issue a voice prompt. Startup is only allowed after user confirmation or the system detects a reduction in particles.

[0085] Understandably, after a brushing cycle ends, the particulate map can be updated. The particles that have been cleared can be removed from the map, and newly appearing particles can be added to the map to provide a basis for planning the next brushing cycle or the reverse cycle.

[0086] In this implementation, for example, in a highway driving scenario, a family car may have a quartz sand particle (Mohs hardness 7) with a diameter of approximately 1.2 mm and a height of approximately 0.4 mm attached to the lower right corner of the windshield. The driver presses the wiper switch. Based on the solution of this embodiment, the vehicle first collects image information, point cloud information, and spectral information of the windshield. Second, the image semantic segmentation model identifies the particle in the lower right corner of the windshield image and segments its outline. Through image recognition results and LiDAR point cloud information, it can be determined that the particle-covered area has a height abrupt change, and the measured height is 0.42 mm. Multispectral analysis shows that the spectral information of the particle-covered area has high infrared reflectivity. Based on a preset hardness table, the hardness level of the particle can be determined to be 4, and the material can be quartz sand. Analysis of the image recognition results of consecutive frames shows that the particle position is fixed, the adhesion strength is 4, and it is a strong type. Finally, based on the particle feature parameters, a particle map in the windshield coordinate system can be constructed. Based on the particulate matter map, the second characteristic parameters of the particulate matter can be obtained: the position coordinates are mapped as (X=650mm, Y=350mm), the diameter D is 1.2mm, the height H is 0.42mm, the hardness is 4, and the adhesion strength is 4. Furthermore, at this point, the diameter ≥ 0.5mm and the hardness ≥ 3, satisfying the preset avoidance conditions. Based on the second characteristic parameters, the lifting height Δh = height + 0.1 = 0.52mm can be calculated. According to the current wiper position and the preset oscillation speed of 0.5m / s, the estimated arrival time t = 1.3s is calculated, i.e., the lifting time is 1.3s. The lifting position can be the coordinate information of the lower right corner area, and a lifting control command can be generated: {t = 1.3s, Δh = 0.52mm, position = lower right corner area}. Then, wiping and dynamic avoidance are executed. After the wipers start, a lifting command is triggered at t = 1.3s, sending a lifting command to the piezoelectric micro-motion mechanism in the corresponding lower right corner area. A piezoelectric high-voltage actuator outputs 120V, generating a displacement of approximately 10μm through the piezoelectric stack. This displacement is amplified to approximately 0.5mm via a flexible hinge, causing the wiper blade to lift locally by 0.52mm. The wiper blade smoothly "jumps over" the quartz sand particles without contacting them. A displacement sensor provides real-time feedback on the lifting height, with a control error of ±0.02mm. After passing the particles, the voltage is removed, and the wiper blade returns to its original position. Furthermore, after one wiper cycle, particle detection on the windshield can be re-collected. If quartz sand particles are found to remain in place (not removed), the particle map remains unchanged. When the wiper swings in the opposite direction, the same avoidance action is performed again, ensuring that the particles are not wiped on the return stroke. If the particle position changes, the particle map can be updated. Thus, throughout the entire wiping process, the wiper blade never comes into contact with quartz sand particles, completely avoiding the risk of particles dragging and scratching the glass surface. The driver is unaware of the impact, and the cleaning effect remains unaffected.

[0087] For example, when a vehicle is driving on city roads, a large number of tiny dust particles may be scattered on the windshield. These particles are generally less than 0.1 mm in diameter and have a hardness rating of 2. When the driver activates the windshield wipers, the vehicle first uses image, point cloud, and spectral information collected from the windshield to detect and identify the particles. A large number of tiny particles are detected, all less than 0.1 mm in diameter and with low hardness ratings. The characteristic parameters of the particles meet the preset pressure reduction conditions, allowing the control strategy to be determined as a wiper pressure reduction strategy. This strategy targets small, low-hardness particles that do not require avoidance, and the large number of particles reduces the overall downward pressure of the wipers by 15%, thus reducing friction. When the wipers are activated, a piezoelectric micro-motion mechanism applies a bias voltage, causing the wiper blade to slightly lift, further reducing the contact pressure by 15%. As the wiper blade slides on the glass, the reduced pressure significantly weakens the abrasive effect of the tiny particles. In this way, while maintaining cleaning effectiveness, micro-scratches caused by microparticles are reduced by more than 80%, extending the lifespan of both the glass and the wiper blade.

[0088] For example, a vehicle has just driven past a construction site, leaving a large amount of sand and gravel of varying sizes on the windshield. The driver activates the wipers. First, the vehicle uses image, point cloud, and spectral information collected from the windshield to detect more than 50 hard particles larger than 0.5mm in diameter, densely distributed on the glass. Second, it can issue a warning. Determining the current situation as "extremely high risk," the system automatically suspends the wipers. The HUD displays "Large number of hard particles detected; it is recommended to spray water to soften them," and a voice prompt is given. The driver can follow the prompt and activate the washer spray to wet the particles. After 30 seconds, the system rescans and finds that some particles have been softened or washed away, reducing the risk level and allowing the wipers to resume. This prevents users from activating the wipers without understanding the situation, which could result in the glass being severely scratched by a large amount of sand and gravel.

[0089] Thus, by employing the solution in this embodiment, the position of particles can be sensed in real time, and the wiper blade can actively skip over harder particles, minimizing the sliding friction between particles and the glass and reducing the risk of glass scratches by more than 95%. Furthermore, by reducing the abrasion of the glass by particles and the wear on the wiper blade, the lifespan of the glass can be extended by 2-3 times, and the lifespan of the wiper blade can be extended by more than 3 times, reducing user maintenance costs. Long-term use can also prevent the formation of fine scratches on the glass surface, maintaining the glass's light transmittance and the condition of a new car, avoiding glare at night, thereby improving driving safety.

[0090] Furthermore, by adopting the solution in this embodiment, particles with diameters as small as 0.1 mm can be identified by integrating high-resolution visual recognition and LiDAR three-dimensional measurement, and the height measurement accuracy reaches ±0.1 mm. The hardness of the particles can be inferred through multispectral analysis, providing a reliable basis for differentiated avoidance strategies.

[0091] Furthermore, by adopting the scheme in this embodiment, a micro-motion system based on a piezoelectric stack and a flexible hinge amplification mechanism can achieve a continuously adjustable lifting height of 0-0.5mm, a response time of <50ms, a lifting accuracy of ±0.02mm, and closed-loop control by a displacement sensor to ensure accurate and reliable operation, thus achieving dynamic obstacle avoidance with micron-level precision.

[0092] Furthermore, by adopting the solution in this embodiment, a differentiated control strategy can be used to dynamically adjust the wiper control strategy based on characteristic parameters such as particle size, hardness, and adhesion strength. This enables the avoidance of hard particles, the reduction of pressure on small particles, and the pre-removal of weak adhesion, thus achieving a refined graded protection strategy.

[0093] Furthermore, by adopting the solution in this embodiment, the wipers can be automatically paused in extremely high-risk scenarios to prompt the user to take pre-treatment measures, thus avoiding serious damage to the windshield.

[0094] It should be noted that the specific implementation process provided in this embodiment can be combined with various specific implementation processes provided in the aforementioned implementation methods to implement the wiper control method of this embodiment. Detailed descriptions can be found in the relevant content of the aforementioned implementation methods, and will not be repeated here.

[0095] Figure 2 A structural block diagram of a wiper control device according to an embodiment of this application is shown, as follows: Figure 2 As shown. The wiper control device 200 of this embodiment can be applied to a windshield wiper control system and may include an acquisition unit 201, an identification unit 202, a construction unit 203, a determination unit 204, and a control unit 205. The acquisition unit 201 is used to acquire image information, point cloud information, and spectral information of the vehicle's windshield; the identification unit 202 is used to perform particulate matter identification processing on the windshield based on the image information, point cloud information, and spectral information, using a preset identification strategy to obtain first feature parameters of the particulate matter; the construction unit 203 is used to perform conversion processing on the first feature parameters of the particulate matter to construct particulate matter map information in the windshield coordinate system; the determination unit 204 is used to determine a wiper control strategy based on the particulate matter map information, using a preset decision algorithm; and the control unit 205 is used to control the wipers to perform wiping operations on the windshield based on the wiper control strategy.

[0096] Optionally, in one possible implementation of this embodiment, the first characteristic parameters of the particulate matter include the first image recognition result of the particulate matter, the first height of the particulate matter, the first hardness of the particulate matter, and the first adhesion strength of the particulate matter. The recognition unit 202 is used to perform particulate matter recognition processing on the image information of the windshield to obtain the first image recognition result of the particulate matter; based on the point cloud information of the windshield and the first image recognition result of the particulate matter, the first height of the particulate matter is obtained using a height recognition algorithm; based on the spectral information of the windshield and the first image recognition result of the particulate matter, the first hardness of the particulate matter is obtained using a hardness estimation algorithm; and based on the first image recognition result of the particulate matter, the first adhesion strength of the particulate matter is obtained using an adhesion strength analysis algorithm.

[0097] Optionally, in one possible implementation of this embodiment, the construction unit 203 is used to perform coordinate system transformation processing on the first feature parameters of the particulate matter based on the first image recognition result of the particulate matter to obtain the second feature parameters of the particulate matter in the windshield coordinate system; and to construct the particulate matter map information based on the second feature parameters of the particulate matter in the windshield coordinate system.

[0098] Optionally, in one possible implementation of this embodiment, the determining unit 204 is configured to acquire second feature parameters of the particles in the particulate matter map information. The second feature parameters of the particles include the second image recognition result of the particles, the second height of the particles, the second hardness of the particles, and the second adhesion strength of the particles. If the second image recognition result and the second hardness of the particles satisfy a preset avoidance condition, the wiper control strategy is determined to be a wiper avoidance strategy based on a preset oscillation speed, the second image recognition result of the particles, and the second height of the particles. If the second image recognition result and the second hardness of the particles satisfy a preset decompression condition, the wiper control strategy is determined to be a wiper decompression strategy. If the second adhesion strength of the particles satisfies a preset pre-removal condition, the wiper control strategy is determined to be a pre-removal strategy.

[0099] Optionally, in one possible implementation of this embodiment, the control unit 205 is configured to, when determining that the wiper control strategy is a wiper avoidance strategy, obtain a lift height, lift time, and lift position based on a preset oscillation speed, a second image recognition result of the particulate matter, and a second height of the particulate matter using a preset lift algorithm, so as to control the wiper to perform a wiping operation on the windshield based on the lift height, lift time, and lift position; when determining that the wiper control strategy is a wiper decompression strategy, control the wiper to perform a wiping operation on the windshield based on a preset pressure value; and when determining that the wiper control strategy is a pre-cleaning strategy, perform a pre-cleaning treatment on the windshield so as to control the wiper to perform a wiping operation on the pre-cleaned windshield.

[0100] In this embodiment, the acquisition unit acquires image information, point cloud information, and spectral information of the vehicle's windshield. The recognition unit, based on the image, point cloud, and spectral information of the windshield, uses a preset recognition strategy to perform particulate matter identification processing on the windshield to obtain the first feature parameters of the particulate matter. The construction unit transforms the first feature parameters of the particulate matter to construct particulate matter map information in the windshield coordinate system. The determination unit, based on the particulate matter map information, uses a preset decision algorithm to determine the wiper control strategy. The control unit, based on the wiper control strategy, controls the wipers to perform wiping operations on the windshield. Because the particulate matter on the windshield can be identified first, and the corresponding wiper control strategy can be determined based on the particulate matter feature information, the sliding friction between the particulate matter and the glass is reduced, lowering the risk of damage to the glass and wiper blades, thereby ensuring the service life of the windshield and wipers.

[0101] The technical solution of this application involves the collection, storage, use, processing, transmission, provision, and disclosure of user personal information, such as user image and attribute data, which comply with relevant laws and regulations and do not violate public order and good morals.

[0102] According to embodiments of this application, this application also provides an electronic device, a readable storage medium, and a computer program product.

[0103] According to embodiments of this application, a vehicle including the provided electronic equipment is further provided. The vehicle may include fuel-powered vehicles and new energy vehicles. For example, the vehicle may be a passenger car, a commercial vehicle, a logistics vehicle, a large vehicle, etc.

[0104] Figure 3A schematic block diagram of an example electronic device 300 that can be used to implement embodiments of this application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the application described and / or claimed herein.

[0105] like Figure 3 As shown, the electronic device 300 includes a computing unit 301, which can perform various appropriate actions and processes based on a computer program stored in a read-only memory (ROM) 302 or a computer program loaded from a storage unit 308 into a random access memory (RAM) 303. The RAM 303 may also store various programs and data required for the operation of the electronic device 300. The computing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0106] Multiple components in electronic device 300 are connected to I / O interface 305, including: input unit 306, such as keyboard, mouse, etc.; output unit 307, such as various types of displays, speakers, etc.; storage unit 308, such as disk, optical disk, etc.; and communication unit 309, such as network card, modem, wireless transceiver, etc. Communication unit 309 allows electronic device 300 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0107] The computing unit 301 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 301 performs the various methods and processes described above, such as the wiper control method. For example, in some embodiments, the wiper control method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 300 via ROM 302 and / or communication unit 309. When the computer program is loaded into RAM 303 and executed by the computing unit 301, one or more steps of the wiper control method described above may be performed. Alternatively, in other embodiments, the computing unit 301 may be configured to perform the wiper control method by any other suitable means (e.g., by means of firmware).

[0108] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0109] The program code used to implement the methods of this application may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0110] In the context of this application, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0111] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0112] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0113] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0114] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this application can be achieved, and this is not limited herein.

[0115] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for controlling windshield wipers, characterized in that, The method includes: Acquire image information, point cloud information, and spectral information of the vehicle's windshield; Based on the image information, point cloud information, and spectral information of the windshield, a preset recognition strategy is used to perform particulate matter recognition processing on the windshield to obtain the first characteristic parameters of the particulate matter. The first characteristic parameters of the particulate matter are transformed to construct particulate matter map information in the windshield coordinate system; Based on the particulate matter map information, a preset decision algorithm is used to determine the wiper control strategy. Based on the aforementioned wiper control strategy, the wipers are controlled to perform a wiping operation on the windshield.

2. The method according to claim 1, characterized in that, The first characteristic parameters of the particulate matter include the first image recognition result of the particulate matter, the first height of the particulate matter, the first hardness of the particulate matter, and the first adhesion strength of the particulate matter. Based on the image information, point cloud information, and spectral information of the windshield, a preset recognition strategy is used to perform particulate matter recognition processing on the windshield to obtain the first characteristic parameters of the particulate matter, including: The image information of the windshield is processed for particulate matter recognition to obtain a first image recognition result of particulate matter. Based on the point cloud information of the windshield and the first image recognition result of the particulate matter, the first height of the particulate matter is obtained using a height recognition algorithm; Based on the spectral information of the windshield and the first image recognition result of the particulate matter, the first hardness of the particulate matter is obtained using a hardness estimation algorithm; Based on the first image recognition result of the particulate matter, the first adhesion strength of the particulate matter is obtained using an adhesion strength analysis algorithm.

3. The method according to claim 2, characterized in that, The step of transforming the first feature parameters of the particulate matter to construct particulate matter map information in the windshield coordinate system includes: Based on the first image recognition result of the particulate matter, the first feature parameters of the particulate matter are subjected to coordinate system transformation to obtain the second feature parameters of the particulate matter in the windshield coordinate system. The particulate matter map information is constructed based on the second feature parameters of the particulate matter in the windshield coordinate system.

4. The method according to claim 1, characterized in that, The step of determining the wiper control strategy based on the particulate matter map information and using a preset decision algorithm includes: The second feature parameters of the particles in the particulate map information are obtained. The second feature parameters of the particles include the second image recognition result of the particles, the second height of the particles, the second hardness of the particles, and the second adhesion strength of the particles. If the second image recognition result of the particulate matter and the second hardness of the particulate matter meet the preset avoidance conditions, the wiper control strategy is determined to be a wiper avoidance strategy based on the preset oscillation speed, the second image recognition result of the particulate matter and the second height of the particulate matter. If the second image recognition result of the particulate matter and the second hardness of the particulate matter meet the preset decompression conditions, the wiper control strategy is determined to be a wiper decompression strategy. If the second adhesion strength of the particulate matter meets the preset pre-removal conditions, the wiper control strategy is determined to be a pre-removal strategy.

5. The method according to claim 4, characterized in that, The step of controlling the windshield wipers to perform wiping operations based on the aforementioned wiper control strategy includes: When the wiper control strategy is determined to be a wiper avoidance strategy, based on the preset swing speed, the second image recognition result of the particulate matter and the second height of the particulate matter, a preset lifting algorithm is used to obtain the lifting height, lifting time and lifting position, so as to control the wiper to perform a wiping operation on the windshield based on the lifting height, lifting time and lifting position. When the wiper control strategy is determined to be a wiper decompression strategy, the wiper is controlled to perform a wiping operation on the windshield based on a preset pressure value. If the wiper control strategy is determined to be a pre-cleaning strategy, the windshield is pre-cleaned in order to control the wipers to perform a wiping operation on the pre-cleaned windshield.

6. A wiper control device, characterized in that, The device includes: The acquisition unit is used to acquire image information, point cloud information, and spectral information of the vehicle's windshield; The identification unit is used to perform particulate matter identification processing on the windshield based on the image information, point cloud information and spectral information of the windshield, using a preset identification strategy, so as to obtain the first characteristic parameters of the particulate matter. The construction unit is used to transform the first feature parameters of the particulate matter to construct particulate matter map information in the windshield coordinate system. The determining unit is used to determine the wiper control strategy based on the particulate matter map information and using a preset decision algorithm. The control unit is used to control the windshield wipers to perform wiping operations on the windshield based on the wiper control strategy.

7. An electronic device, characterized in that, include: At least one processor; as well as A memory that is communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1-5.

8. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-5.

9. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1-5.

10. A vehicle, characterized in that, Including the electronic device according to claim 7.

Images