Control method for window cleaning machine and related products

Abstract

The application relates to a window cleaning machine control method and related products, which are applied to the technical field of cleaning equipment, and the method comprises the following steps: acquiring environment characteristic parameters collected by an environment sensing module; determining a target obstacle type of an obstacle in a target area and a target confidence degree corresponding to the target obstacle type based on the environment characteristic parameters, wherein the target area comprises a measurement area of the environment sensing module; determining a target passing strategy of a window cleaning machine based on the target confidence degree and the target obstacle type; and controlling the window cleaning machine to move according to the target passing strategy. The method can solve the problem that, in the prior art, the sensing obstacle is collided by a machine, the machine body is damaged, and the service life of the window cleaning machine is reduced.

Description

Technical Field

[0001] This application relates to the field of cleaning equipment technology, and in particular to a control method for a window cleaning machine and related products. Background Technology

[0002] In the field of high-altitude glass cleaning, window cleaning machines need to move autonomously and complete a comprehensive cleaning in complex external window environments. Therefore, they have high requirements for accurate perception and intelligent obstacle avoidance capabilities of glass boundaries, window frames and various window surface obstacles.

[0003] In related technologies, window cleaning robots often employ mechanical collision-based edge-finding structures when performing boundary recognition and obstacle detection. This type of solution generally relies on the physical contact and impact between the machine body and the window frame or obstacle to indirectly determine the boundary position and the presence of the obstacle, which is a passive blind navigation method.

[0004] By using mechanical collisions to detect obstacles, the machine body is easily damaged due to repeated collisions, resulting in a reduced lifespan for the window cleaning machine. Summary of the Invention

[0005] This application provides a control method and related products for a window cleaning machine, which solves the problem in the prior art where the perception of mechanical collisions is impeded, which can easily lead to damage to the machine body and reduce the service life of the window cleaning machine.

[0006] According to a first aspect of the embodiments of this application, a control method for a window cleaning machine is provided, comprising: Acquire environmental feature parameters collected by the environmental perception module; Based on the environmental feature parameters, the target obstacle type in the target area is determined, as well as the target confidence level corresponding to the target obstacle type. The target area includes the measurement area of ​​the environmental perception module. Determine the target passage strategy for the window cleaning machine based on the target confidence level and the target obstacle type; Control the window cleaning machine to travel according to the target traffic strategy.

[0007] Optionally, determining the target obstacle type and the target confidence level corresponding to the target obstacle type based on environmental feature parameters in the target area includes: The probability of the obstacle belonging to each preset obstacle type is determined based on the environmental feature parameters; The preset obstacle type with the highest probability is determined as the target obstacle type, and the probability corresponding to the target obstacle type is determined as the target confidence level.

[0008] Optionally, determining the target obstacle type and the target confidence level corresponding to the target obstacle type based on environmental feature parameters in the target area includes: Based on the acquired environmental feature parameters, the initial obstacle type and its corresponding initial confidence level of obstacles in the target area are determined by obtaining a preset number of consecutive times. If the initial obstacle types obtained in the consecutive preset number of times are the same, the initial obstacle type is determined to be the target obstacle type, and the target confidence level is determined based on each initial confidence level; If the initial obstacle types obtained in the consecutive preset number of times are different, the target obstacle type is determined by election of each initial obstacle type, and the target confidence level is determined based on the initial confidence level corresponding to the candidate obstacle type. The candidate obstacle type is the same as the initial obstacle type as the target obstacle type.

[0009] Optionally, determining the target access strategy for the window cleaning machine based on the target confidence level and the target obstacle type includes: Determine the target confidence level to which the target confidence level belongs from multiple preset confidence levels; The target access strategy is determined based on the target confidence level and the target obstacle type.

[0010] Optionally, the preset confidence level includes a first confidence level, a second confidence level, and a third confidence level, ranked from high to low, wherein the higher the preset confidence level, the higher the corresponding confidence level. Determining the target passage strategy based on the target confidence level and the target obstacle type includes: When the target confidence level is the first confidence level, the passage strategy corresponding to the target obstacle type is determined as the target passage strategy; When the target confidence level is the second confidence level, the target obstacle type and its corresponding target confidence level of the obstacles in the target area are re-determined, and the target passage strategy is determined according to the re-determined target obstacle type and target confidence level; If the target confidence level is the third confidence level, the target passage policy is determined to be a stop passage policy.

[0011] Optionally, after determining the target obstacle type and the target confidence level corresponding to the target obstacle type in the target area based on the environmental feature parameters, the method further includes: Whether the retest conditions are met is determined at least based on the target confidence level and the target obstacle type. If satisfied, the window cleaning machine is adjusted according to the preset adjustment strategy, and the environmental perception module is controlled to re-collect environmental feature parameters according to the adjusted state of the window cleaning machine. Based on the re-collected environmental feature parameters, the target obstacle type and its corresponding target confidence level are re-determined.

[0012] Optionally, the environmental characteristic parameters include distance values, and the retest conditions include at least one of the following: The target obstacle type is a specified obstacle type and the corresponding target confidence level is greater than a first specified threshold; The types of target obstacles determined by the number of consecutive preset attempts are different; The target confidence level is less than a second specified threshold and the distance value is less than a preset distance threshold; The distance value changes by more than a preset change threshold within a specified time period.

[0013] According to a second aspect of the embodiments of this application, a window cleaning machine is provided, including: an environmental sensing module and a controller, wherein the environmental sensing module is used to collect environmental characteristic parameters; and the controller is used to implement the control method of the window cleaning machine as described in the first aspect.

[0014] According to a third aspect of the embodiments of this application, a control device for a window cleaning machine is provided, comprising: The acquisition unit is used to acquire environmental feature parameters collected by the environmental perception module. The first determining unit is used to determine the target obstacle type of the obstacle in the target area and the target confidence level corresponding to the target obstacle type based on the environmental feature parameters, wherein the target area includes the measurement area of ​​the environmental perception module; The second determining unit is used to determine the target passage strategy of the window cleaning machine based on the target confidence level and the target obstacle type; The control unit is used to control the window cleaning machine to move in accordance with the target traffic strategy.

[0015] According to a fourth aspect of the embodiments of this application, an electronic device is provided, including a memory and a processor; The memory is connected to the processor and is used to store programs; The processor is used to implement the window cleaning machine control method as described in the first aspect by running the program in the memory.

[0016] According to a fifth aspect of the present application, a storage medium is provided, on which a computer program is stored, and when the computer program is run by a processor, it implements the control method of the window cleaning machine as described in the first aspect.

[0017] According to a sixth aspect of the embodiments of this application, a computer program product is provided, including computer program instructions, which, when executed by a processor, cause the processor to perform the control method for a window cleaning machine as described in the first aspect.

[0018] Compared with the prior art, the technical solution provided in this application has the following advantages: The method provided in this application acquires environmental feature parameters collected by an environmental perception module; determines the target obstacle type and the target confidence level corresponding to the target obstacle type based on the environmental feature parameters, wherein the target area includes the measurement area of ​​the environmental perception module; determines the target passage strategy of the window cleaning machine based on the target confidence level and the target obstacle type; and controls the window cleaning machine to move according to the target passage strategy. In this way, the environmental feature parameters in front of the window cleaning machine collected by the environmental perception module can be used to determine the obstacle type, and then the target passage strategy of the window cleaning machine can be determined using the determined target obstacle type and target confidence level. This allows the window cleaning machine to autonomously decide its movement mode based on the perceived information, thereby avoiding the defects of disordered paths, easy jamming, and impact damage to windows caused by mechanical collision edge finding, effectively improving the intelligence and safety of cleaning operations. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0020] Figure 1 A flowchart of a control method for a window cleaning machine is provided for one embodiment of this application.

[0021] Figure 2 This is a structural diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0022] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0023] Exemplary Implementation Environment The control method for a window cleaning machine according to embodiments of this application can be executed by electronic devices such as terminal devices or servers. The terminal device can be a window cleaning machine or a controller on the window cleaning machine, and the server can be an independent physical server, a server cluster consisting of multiple physical servers, or a cloud server capable of cloud computing. This method can be implemented by a processor calling computer-readable program instructions stored in memory. This application uses the example of a controller executing the control method for a window cleaning machine for explanation and illustration, but does not limit the scope of the application.

[0024] The window cleaning machine provided in this application includes a machine body, an environmental sensing module, and a controller mounted on the machine. The environmental sensing module may include a non-contact distance sensor for real-time detection of the distance between the window cleaning machine and window boundaries or obstacles, obtaining distance information between the machine and the obstacle; it may also include a camera to capture environmental images in front of the machine. A control unit, communicatively connected to the environmental sensing module, is used to execute the control method for the window cleaning machine provided in this application.

[0025] This non-contact ranging sensor can, but is not limited to, use the Direct Time-of-Flight (dTOF) ranging principle. It incorporates a SPAD (Single-Photon Avalanche Diode) and a unique dTOF acquisition and processing technology, enabling it to perform 120 precise ranging measurements per second. During each measurement, the radar emits an infrared laser, which is reflected back to the single-photon receiving unit upon encountering an object. The time difference between the laser emission and reception time is obtained; this time difference represents the time of light's flight. Combined with the speed of light, the distance can be calculated.

[0026] The Time-of-Flight (TOF) sensor can be connected to the window cleaning machine controller, communicating via an Inter-Integrated Circuit (I2C) bus. The TOF sensor feeds back distance information to the controller, which then uses this information to control the machine's movement accordingly.

[0027] The TOF sensor includes two operating modes: short-range mode and long-range mode. The short-range mode can be used for edge detection in window cleaning machines. The long-range mode can be used for navigation mapping and path planning in window cleaning machines.

[0028] Understandably, multiple Time-of-Flight (TOF) sensors can be installed at different heights on the window cleaning machine. Through the detection of each TOF sensor, obstacles (window frames, handles, protrusions, etc.) in front of the cleaning machine can be identified. After the obstacle is identified, the control unit uses the built-in Slime Mould Algorithm (SLMA) algorithm to plan a path (bow-shaped or spiral) to bypass the obstacle and clean the window. This enables the window cleaning machine to avoid jamming, collisions, and missing cleaning areas, thereby improving cleaning efficiency.

[0029] A negative pressure sensor can also be installed on the window cleaning machine. This sensor collects the pressure between the machine body and the window to determine the adhesion between the machine body and the glass. If the negative pressure sensor detects insufficient suction, it automatically compensates for the negative pressure. If the negative pressure falls below a threshold, the window cleaning machine can be stopped. A safety rope can also be installed on the window cleaning machine to prevent it from falling.

[0030] The window cleaning machine can also be equipped with a backup battery, so that in the event of a power outage from the main battery, the backup battery can take over directly, ensuring that the window cleaning machine will not fall due to a power outage.

[0031] The window cleaning machine can also be equipped with a dirt sensor to detect the degree of dirt on the glass surface and adjust the cleaning intensity accordingly to ensure cleaning effectiveness.

[0032] Exemplary methods Please see Figure 1 In one exemplary embodiment, a control method for a window cleaning machine is provided, comprising: Step 101: Obtain environmental feature parameters collected by the environmental perception module.

[0033] In some embodiments, the environmental perception module may include, but is not limited to, a Time-of-Flight (TOF) sensor and a camera. The TOF sensor measures the distance to the environment in front of the window cleaning machine to obtain distance data. The camera acquires two-dimensional images of the target area to obtain visual information such as texture, color, and edges. The distance data output by the controller's TOF sensor and the image data output by the camera are fused to generate environmental feature parameters.

[0034] Environmental feature parameters can be a set of parameters that characterize the spatial location, surface properties, and changing trends of points within the target area being measured, and are not limited to single-point distance values. For example, they can be 3D point cloud data composed of multiple distance values ​​and corresponding image pixels (each point contains 3D coordinates and color / texture information), or they can be fused feature vectors obtained after coordinate transformation. By employing a TOF sensor in collaboration with a camera, high-precision distance information can be obtained, along with rich visual semantics, providing complementary, high spatiotemporal resolution raw information for subsequent obstacle type recognition.

[0035] The environmental feature parameters may include, but are not limited to, distance values ​​measured by a TOF sensor, image data acquired by a camera, and distance-image association information obtained after coordinate registration. For example, the association information could be projecting distance data onto an image plane, labeling the depth value of each pixel to form a depth map; or it could be extracting the contour features of obstacles in the image and matching them with the distance data. Furthermore, the environmental feature parameters may also include the distribution of distance values ​​with the measurement angle, the rate of change of distance values ​​during continuous measurement, echo signal intensity, image texture gradient, color histogram, and other information.

[0036] Step 102: Determine the target obstacle type and the target confidence level corresponding to the target obstacle type in the target area based on the environmental feature parameters. The target area includes the measurement area of ​​the environmental perception module.

[0037] In some embodiments, the target area typically refers to the glass surface area within a certain angle and distance in front of or around the window cleaning machine's direction of travel. An obstacle generally refers to any object that may affect the normal movement of the window cleaning machine, such as handles, latches, window trim, window frames, raised stains, glass edges, etc. The target obstacle type is the type most likely to be assigned to by the current obstacle, determined from a preset set of obstacle types. The target confidence level characterizes the reliability of this determination result.

[0038] One method for determining the type of target obstacle is to use a pre-established obstacle recognition model. Environmental feature parameters are input into the model, which outputs the probability that the obstacle belongs to various preset obstacle types. The type corresponding to the highest probability is then taken as the target obstacle type, and this probability is used as the target confidence level. For example, a classifier can be obtained by performing machine learning on a large number of known obstacle environmental feature parameter samples; or a template matching algorithm can be used to compare real-time collected distance points with typical 3D contours of window handles to obtain the similarity as a probability.

[0039] Alternatively, a rule engine can be used to determine the obstacle type based on whether environmental feature parameters meet the geometric feature conditions of a certain obstacle type, and assign a confidence level related to the degree of feature matching. For example, image features captured by a camera can be compared with preset obstacle images, and the obstacle type corresponding to the closest obstacle image can be determined as the target obstacle type, and the similarity between the captured image and the obstacle image can be determined as the target confidence level.

[0040] It should be noted that the identification of the aforementioned obstacle types provides a crucial decision-making basis for determining appropriate passage strategies. If it is impossible to accurately distinguish whether an obstacle is a raised stain or a hard latch, it is difficult to select an appropriate avoidance or covering action, easily leading to jamming or incomplete cleaning. Therefore, by identifying the target obstacle type and its confidence level, perceptual information is directly transformed into structured classification conclusions, allowing subsequent decisions to be based on clear semantic information, avoiding path confusion and window damage problems caused by blind collisions in related technologies.

[0041] In an optional embodiment, to further optimize the accuracy and interpretability of obstacle recognition, the above-mentioned determination of the target obstacle type and the target confidence level corresponding to the target obstacle type based on environmental feature parameters includes: determining the probability that the obstacle belongs to each preset obstacle type based on the environmental feature parameters; determining the preset obstacle type with the highest probability as the target obstacle type; and determining the probability corresponding to the target obstacle type as the target confidence level.

[0042] In some embodiments, environmental feature parameters can be input into the classification and inference stage of the obstacle recognition model, and the output is a probability vector of the obstacle belonging to multiple preset obstacle types such as glass boundary, handle, latch, window trim, and raised stain. The category corresponding to the highest probability value in the probability vector is taken as the target obstacle type, and the highest probability value is output as the target confidence level.

[0043] For example, if the environmental feature parameters measured in a certain frame are processed by the obstacle recognition model, and the probability of belonging to a lock is 0.85, the probability of belonging to a handle is 0.10, and the probability of belonging to a window frame is 0.05, then the target obstacle type is determined to be a lock, and the target confidence level is 0.85.

[0044] The probabilities can be calculated using functions such as the softmax function, ensuring that the sum of all probabilities equals 1. Using confidence level as a quantitative indicator of decision reliability facilitates subsequent threshold setting for tiered control.

[0045] In an optional embodiment, to address the problem of misjudgment caused by momentary interference or noise in a single measurement, the target obstacle type and the target confidence level corresponding to the target obstacle type in the target area are determined based on environmental feature parameters. This includes: obtaining initial obstacle types and their corresponding initial confidence levels of obstacles in the target area determined based on the acquired environmental feature parameters for a consecutive preset number of times; if the initial obstacle types obtained for the consecutive preset number of times are the same, determining the initial obstacle type as the target obstacle type, and determining the target confidence level based on each initial confidence level; if the initial obstacle types obtained for the consecutive preset number of times are different, electing the target obstacle type from each initial obstacle type, and determining the target confidence level based on the initial confidence level corresponding to the candidate obstacle type, wherein the candidate obstacle type is the same as the target obstacle type.

[0046] In some embodiments, an election mechanism based on multiple consecutive measurements can be employed. Specifically, the initial obstacle type and its corresponding initial confidence level of obstacles in the target area, determined based on the acquired environmental feature parameters, can be obtained for a predetermined number of consecutive times (e.g., 3 or 5 times, or an odd number of times).

[0047] For example, five consecutive measurement frames are taken, and an initial obstacle type and an initial confidence level are independently determined for each frame. If the initial obstacle types obtained in the five consecutive measurements are exactly the same, then that initial obstacle type is directly determined as the final target obstacle type. Simultaneously, the final target confidence level can be calculated based on these five initial confidence levels by averaging, minimizing, or weighted averaging. If different initial obstacle types appear in the five consecutive measurements, an election is held for each initial obstacle type, for example, selecting the type with the highest frequency as the target obstacle type. For this target obstacle type, the initial confidence levels of its class are taken, and the target confidence level is determined by averaging. For example, if the five consecutive initial obstacle types are handle, handle, latch, handle, and handle, after election, the target obstacle type is determined to be handle, and the corresponding candidate obstacle type is handle. The target confidence level can be calculated based on the confidence levels of these four handle measurements.

[0048] By introducing a time-series multiple measurement consistency check and voting mechanism, the type jump caused by occasional measurement errors is effectively suppressed, making the obstacle recognition results more stable and reliable. It can be applied to scenarios with abnormal fluctuations in ranging signals caused by glass reflection, dirt coverage, etc.

[0049] In one optional embodiment, determining the target access strategy for the window cleaning machine based on the target confidence level and the target obstacle type includes: determining the target confidence level to which the target confidence level belongs from a plurality of preset confidence levels; and determining the target access strategy based on the target confidence level and the target obstacle type.

[0050] In some embodiments, the preset confidence level is a division of the confidence level range, such as high, medium, and low levels, or more levels. When the target confidence level falls within a certain level range, that level is considered the target confidence level. Different levels correspond to different decision-making tendencies; for example, with high confidence, the identification result is trusted, and the standard passage strategy for that type of obstacle is followed; with low confidence, a conservative approach is taken.

[0051] This allows the window cleaning machine to respond differently to the reliability of the identification results, rather than treating all confidence levels the same, thus achieving a better balance between safety and operational efficiency.

[0052] Furthermore, the preset reliability levels include a first confidence level, a second confidence level, and a third confidence level, ranked from highest to lowest, with higher preset reliability levels corresponding to higher confidence levels.

[0053] Determining the target passage strategy based on the target confidence level and the target obstacle type includes: When the target confidence level is the first confidence level, the passage strategy corresponding to the target obstacle type is determined as the target passage strategy; when the target confidence level is the second confidence level, the target obstacle type and its corresponding target confidence level of the obstacles in the target area are re-determined, and the target passage strategy is determined according to the re-determined target obstacle type and target confidence level; when the target confidence level is the third confidence level, the target passage strategy is determined as a stop passage strategy.

[0054] In some embodiments, when the target confidence level is the first confidence level, the preset passage strategy corresponding to the target obstacle type is determined as the target passage strategy. For example, for handle types, the strategy corresponding to the first confidence level is to detour around it with a safe distance of 2cm. When the target confidence level is the second confidence level, it indicates that the current recognition result has a certain degree of uncertainty, thus triggering a process to redetermine the target obstacle type and its target confidence level in the target area. For example, the environmental perception module is required to re-collect data at a higher frequency or after adjusting its posture, and then the target passage strategy is determined according to the redetermined result. When the target confidence level is the third confidence level, the recognition reliability is considered too low, and the target passage strategy can be directly determined as a stop passage strategy, controlling the window cleaning machine to stop in place, waiting for further instructions or user intervention.

[0055] The thresholds for the first, second, and third confidence levels can be set as follows: confidence level ≥ 0.8 for the first confidence level, 0.5 ≤ confidence level < 0.8 for the second confidence level, and confidence level < 0.5 for the third confidence level. It is understood that the specific thresholds can be adjusted based on the actual sensor performance characteristics and risk assessment of the application scenario. By determining the target passage strategy through a tiered approach, cleaning and obstacle avoidance are efficiently executed when identification is reliable, proactive verification is performed when doubts exist, and immediate cessation is implemented when unreliable identification occurs, fully balancing operational continuity with personal and equipment safety.

[0056] Step 103: Determine the target passage strategy for the window cleaning machine based on the target confidence level and the target obstacle type.

[0057] In some embodiments, the target passage strategy refers to the movement response that the window cleaning robot should take in response to the current obstacle, such as detouring, slowing down, cleaning along the edge, or stopping.

[0058] Taking a window latch as an example with high confidence level as the target obstacle, the passage strategy can be determined as to walk around the latch at a safe distance to ensure cleaning coverage and avoid collisions. If the target obstacle is a raised stain with high confidence level, the passage strategy can be determined as to reduce the walking speed and try to wipe back and forth to enhance the cleaning effect. For cases with low confidence level, a more conservative strategy can be adopted.

[0059] The decision-making mechanism that uses both target confidence and target obstacle type to determine the target passage strategy enables the window cleaning robot to flexibly adjust its movement mode based on real-time perception results, replacing the simple one-touch stop method in mechanical collision edge finding.

[0060] In an optional embodiment, to improve the proactive defense capability against potential misjudgments, after determining the target obstacle type of the obstacle in the target area based on the environmental feature parameters, and the target confidence level corresponding to the target obstacle type, the method further includes: At least based on the target confidence level and the target obstacle type, it is determined whether the retest conditions are met; if they are met, the window cleaning machine is adjusted according to the preset adjustment strategy, the environmental perception module is controlled to re-collect environmental feature parameters according to the adjusted state of the window cleaning machine, and the target obstacle type and its corresponding target confidence level are re-determined based on the re-collected environmental feature parameters.

[0061] In some embodiments, after initial identification, a retest condition check is performed. If a retest is required, adjustments and retests are performed; otherwise, the process proceeds directly to the step of determining the passage strategy. By configuring a retest mechanism, the reliability and accuracy of the determined target obstacle type and its target confidence can be improved.

[0062] Preset adjustment strategies can include: retracting the window cleaning machine a specified distance (e.g., 3-5 cm), rotating it in place by a certain angle (e.g., any angle below 30 degrees), or adjusting the pitch angle of the environmental perception module (e.g., any angle below 10 degrees). By changing the relative position or posture of the window cleaning machine and the obstacle, physically completely different measurement samples can be obtained, thereby verifying the initial identification results. If the results are consistent after retesting, the credibility can be enhanced; if they are inconsistent, further selection or a more conservative strategy can be adopted.

[0063] Furthermore, when environmental characteristic parameters include distance values, the retest conditions may include at least one of the following: First, the target obstacle type is a specified obstacle type and its corresponding target confidence level is greater than a first specified threshold. The specified obstacle type can be an obstacle type with an aspect ratio greater than the specified threshold (e.g., slender), an obstacle type with a thickness less than a preset thickness (e.g., sheet-like), or an obstacle type that has a significant impact on security, such as window latches or window grilles. Even if the confidence level is high, it can be further confirmed through retesting to improve security.

[0064] Second, the target obstacle type is different after a series of preset attempts. If the target obstacle type is different after multiple attempts, it indicates that the recognition result is unstable, and therefore a retest is required.

[0065] Third, the target confidence level is less than the second specified threshold and the distance value is less than the preset distance threshold. This indicates that while the identification is uncertain, the window cleaning machine is already very close to the object and requires careful handling. Therefore, a retest can be performed to improve safety.

[0066] Fourth, if the change in the distance value within a specified time period exceeds a preset change threshold, it indicates a sudden change in the distance value, which may be due to sensor malfunction or sudden changes in ambient light. Therefore, a retest can be performed to improve safety.

[0067] The aforementioned retesting conditions capture potential uncertainties and risks from multiple dimensions, ensuring that the retesting mechanism is triggered when necessary. This approach guarantees safety while avoiding the negative impact of frequent, repeated measurements on cleaning efficiency. It is understood that these retesting conditions can be used individually or in any combination to suit different product levels and user needs.

[0068] Step 104: Control the window cleaning machine to travel according to the target passage strategy.

[0069] In some embodiments, controlling the movement of the window cleaning machine according to a determined target passage strategy can avoid defects such as disordered paths, easy jamming, and window damage caused by mechanical collision edge searching, effectively improving the intelligence and safety of cleaning operations.

[0070] When the target passage strategy includes cleaning along the edge of an obstacle, it can combine the distance information continuously fed back by the environmental perception module to achieve closed-loop edge control, so that the window cleaning machine maintains a preset distance from the obstacle.

[0071] The control method for the window cleaning machine provided in this application enables the window cleaning machine to identify and respond to obstacles without collision, and to make appropriate passage actions to obstacles that appear continuously on the glass surface during the continuous execution of the method, thereby achieving a high coverage cleaning rate.

[0072] Exemplary device Accordingly, this application also provides a control device for a window cleaning machine, including: The acquisition unit is used to acquire environmental feature parameters collected by the environmental perception module. The first determining unit is used to determine the target obstacle type of the obstacle in the target area and the target confidence level corresponding to the target obstacle type based on the environmental feature parameters, wherein the target area includes the measurement area of ​​the environmental perception module; The second determining unit is used to determine the target passage strategy of the window cleaning machine based on the target confidence level and the target obstacle type; The control unit is used to control the window cleaning machine to move in accordance with the target traffic strategy.

[0073] The control device for the window cleaning machine provided in this embodiment belongs to the same concept as the control method for the window cleaning machine provided in the above embodiments of this application. It can execute the method provided in any of the above embodiments of this application and has the corresponding functional modules and beneficial effects of the method. Technical details not described in detail in this embodiment can be found in the specific processing content of the control method for the window cleaning machine provided in the above embodiments of this application, and will not be repeated here.

[0074] The functions of each unit in the control device of the above window cleaning machine can be implemented by the same or different processors, and this application embodiment does not limit this.

[0075] It should be understood that each unit in the above device can be implemented by a processor calling software. For example, the device includes a processor connected to a memory containing instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of each unit in the device. The processor can be a general-purpose processor, such as a CPU or microprocessor, and the memory can be internal or external to the device. Alternatively, the units in the device can be implemented as hardware circuits. By designing the hardware circuits, some or all of the unit functions can be implemented. The hardware circuits can be understood as one or more processors. For example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all of the above units are implemented by designing the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a PLD, such as an FPGA, which can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files to implement the functions of some or all of the above units. All units in the above device can be implemented entirely by a processor calling software, entirely by hardware circuits, or partially by a processor calling software with the remaining parts implemented by hardware circuits.

[0076] In this application embodiment, a processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction reading and execution capabilities, such as a CPU, microprocessor, GPU, or 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 as an ASIC or PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the processor loading instructions to implement the functions of some or all of the above units. Furthermore, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as an NPU, TPU, or DPU.

[0077] As can be seen, each unit in the above device can be one or more processors (or processing circuits) configured to implement the above methods, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0078] Furthermore, the units in the above devices can be integrated in whole or in part, or they can be implemented independently. In one implementation, these units are integrated together and implemented in the form of a System-on-Chip (SoC). The SoC may include at least one processor for implementing any of the above methods or implementing the functions of the units in the device. The at least one processor may be of different types, such as CPU and FPGA, CPU and artificial intelligence processor, CPU and GPU, etc.

[0079] Exemplary electronic devices Another embodiment of this application also provides an electronic device, see [link to relevant documentation] Figure 2 As shown, the device includes: Memory 200 and processor 210; The memory 200 is connected to the processor 210 and is used to store programs; The processor 210 is used to implement the window cleaning machine control method disclosed in any of the above embodiments by running the program stored in the memory 200.

[0080] Specifically, the control equipment of the aforementioned window cleaning machine may also include: a bus, a communication interface 220, an input device 230, and an output device 240.

[0081] The processor 210, memory 200, communication interface 220, input device 230, and output device 240 are interconnected via a bus. Among them: A bus can include a pathway for transmitting information between various components of a computer system.

[0082] Processor 210 can be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program of the present invention. It can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0083] Processor 210 may include a main processor, as well as a baseband chip, modem, etc.

[0084] The memory 200 stores a program that executes the technical solution of this invention, and may also store an operating system and other key business functions. Specifically, the program may include program code, which includes computer operation instructions. More specifically, the memory 200 may include read-only memory (ROM), other types of static storage devices capable of storing static information and instructions, random access memory (RAM), other types of dynamic storage devices capable of storing information and instructions, disk storage, flash memory, etc.

[0085] Input device 230 may include a device for receiving user input data and information, such as a keyboard, mouse, camera, scanner, light pen, voice input device, touch screen, pedometer, or gravity sensor.

[0086] Output device 240 may include devices that allow information to be output to a user, such as a display screen, printer, speaker, etc.

[0087] The communication interface 220 may include a device that uses any transceiver to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.

[0088] The processor 210 executes the program stored in the memory 200 and calls other devices, which can be used to implement the various steps of any of the window cleaning machine control methods provided in the above embodiments of this application.

[0089] Exemplary computer program products and storage media In addition to the methods and devices described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in the control methods of window cleaning machines according to various embodiments of this application as described in any of the above embodiments of this specification.

[0090] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0091] Furthermore, embodiments of this application may also be storage media storing a computer program, which is executed by a processor through steps in the control method of the window cleaning machine according to various embodiments of this application described in any of the above embodiments of this specification. Specifically, the following steps can be implemented: Acquire environmental feature parameters collected by the environmental perception module; Based on the environmental feature parameters, the target obstacle type in the target area is determined, as well as the target confidence level corresponding to the target obstacle type. The target area includes the measurement area of ​​the environmental perception module. Determine the target passage strategy for the window cleaning machine based on the target confidence level and the target obstacle type; Control the window cleaning machine to travel according to the target traffic strategy.

[0092] For the foregoing method embodiments, in order to simplify the description, they are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0093] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For apparatus embodiments, since they are basically similar to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0094] The steps in the methods of the various embodiments of this application can be adjusted, merged, or deleted in order according to actual needs, and the technical features described in each embodiment can be replaced or combined.

[0095] The modules and sub-modules in the apparatus and terminal in the various embodiments of this application can be merged, divided, and deleted according to actual needs.

[0096] It should be understood that the disclosed terminals, devices, and methods can be implemented in other ways, given the several embodiments provided in this application. For example, the terminal embodiments described above are merely illustrative. For instance, the division of modules or sub-modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple sub-modules or modules may be combined or integrated into another module, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or modules, and may be electrical, mechanical, or other forms.

[0097] The modules or submodules described as separate components may or may not be physically separate. The components that constitute a module or submodule may or may not be physical modules or submodules; that is, they may be located in one place or distributed across multiple network modules or submodules. Some or all of the modules or submodules can be selected to achieve the purpose of this embodiment's solution, depending on actual needs.

[0098] Furthermore, the functional modules or sub-modules in the various embodiments of this application can be integrated into one processing module, or each module or sub-module can exist physically separately, or two or more modules or sub-modules can be integrated into one module. The integrated modules or sub-modules described above can be implemented in hardware or in the form of software functional modules or sub-modules.

[0099] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0100] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software unit executed by a processor, or a combination of both. The software unit can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0101] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0102] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A control method for a window cleaning machine, characterized in that, include: Acquire environmental feature parameters collected by the environmental perception module; Based on the environmental feature parameters, the target obstacle type in the target area is determined, as well as the target confidence level corresponding to the target obstacle type. The target area includes the measurement area of ​​the environmental perception module. Determine the target passage strategy for the window cleaning machine based on the target confidence level and the target obstacle type; Control the window cleaning machine to travel according to the target traffic strategy.

2. The method of claim 1, wherein, Determining the target obstacle type and the corresponding target confidence level in the target area based on environmental feature parameters includes: The probability of the obstacle belonging to each preset obstacle type is determined based on the environmental feature parameters; The preset obstacle type with the highest probability is determined as the target obstacle type, and the probability corresponding to the target obstacle type is determined as the target confidence level.

3. The method of claim 1, wherein, Determining the target obstacle type and the corresponding target confidence level in the target area based on environmental feature parameters includes: Based on the acquired environmental feature parameters, the initial obstacle type and its corresponding initial confidence level of obstacles in the target area are determined by obtaining a preset number of consecutive times. If the initial obstacle types obtained in the consecutive preset number of times are the same, the initial obstacle type is determined to be the target obstacle type, and the target confidence level is determined based on each initial confidence level; If the initial obstacle types obtained in the consecutive preset number of times are different, the target obstacle type is determined by election of each initial obstacle type, and the target confidence level is determined based on the initial confidence level corresponding to the candidate obstacle type. The candidate obstacle type is the same as the initial obstacle type as the target obstacle type.

4. The method of claim 1, wherein, Determine the target access strategy for the window cleaning machine based on the target confidence level and the target obstacle type, including: Determine the target confidence level to which the target confidence level belongs from multiple preset confidence levels; The target access strategy is determined based on the target confidence level and the target obstacle type.

5. The method of claim 4, wherein, The preset confidence levels include a first confidence level, a second confidence level, and a third confidence level, ranked from high to low, wherein the higher the preset confidence level, the higher the corresponding confidence level. Determining the target passage strategy based on the target confidence level and the target obstacle type includes: When the target confidence level is the first confidence level, the passage strategy corresponding to the target obstacle type is determined as the target passage strategy; When the target confidence level is the second confidence level, the target obstacle type and its corresponding target confidence level of the obstacles in the target area are re-determined, and the target passage strategy is determined according to the re-determined target obstacle type and target confidence level; If the target confidence level is the third confidence level, the target passage policy is determined to be a stop passage policy.

6. The method of claim 1, wherein, After determining the target obstacle type and the target confidence level corresponding to the target obstacle type in the target area based on the environmental feature parameters, the method further includes: Whether the retest conditions are met is determined at least based on the target confidence level and the target obstacle type. If satisfied, the window cleaning machine is adjusted according to the preset adjustment strategy, and the environmental perception module is controlled to re-collect environmental feature parameters according to the adjusted state of the window cleaning machine. Based on the re-collected environmental feature parameters, the target obstacle type and its corresponding target confidence level are re-determined.

7. The method of claim 6, wherein, The environmental characteristic parameters include distance values, and the retest conditions include at least one of the following: The target obstacle type is a specified obstacle type and the corresponding target confidence level is greater than a first specified threshold; The types of target obstacles determined by the number of consecutive preset attempts are different; The target confidence level is less than a second specified threshold and the distance value is less than a preset distance threshold; The distance value changes by more than a preset change threshold within a specified time period.

8. A window cleaning machine, characterized in that include: An environment sensing module and a controller, wherein the environment sensing module is used to collect environmental characteristic parameters; The controller is used to implement the control method of the window cleaning machine as described in any one of claims 1 to 7.

9. An electronic device, comprising: Including memory and processor; The memory is connected to the processor and is used to store programs; The processor is used to implement the control method of the window cleaning machine as described in any one of claims 1 to 7 by running the program in the memory.

10. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the control method for the window cleaning machine as described in any one of claims 1 to 7.

11. A computer program product, characterised in that, include: Computer program instructions, when executed by a processor, cause the processor to perform the control method for a window cleaning machine as described in any one of claims 1 to 7.

Images