Cleaning robot control method and apparatus, cleaning robot, and storage medium

Abstract

This application relates to a cleaning robot control method, device, cleaning robot, and storage medium. The method includes: when the cleaning robot faces a rectangular microspace, firstly acquiring a preset observation point corresponding to the rectangular microspace to be cleaned and the minimum cleanable area supported by the cleaning robot; controlling the cleaning robot to move to the preset observation point; calculating the actual visible unobstructed cleanable area based on the laser vision fusion point cloud sequence acquired by the cleaning robot at the preset observation point facing the rectangular microspace to be cleaned; comparing the unobstructed cleanable area with the minimum cleanable area to delineate a target cleanable area that is greater than or equal to the minimum cleanable area; generating a cleaning path within the target cleanable area based on the cleaning robot's structural parameters; and controlling the cleaning robot to perform the cleaning task according to the cleaning path. Since the target cleanable area is greater than or equal to the minimum cleanable area, the minimum kinematic constraints of the cleaning robot within the rectangular microspace are satisfied.

Description

Technical Field

[0001] This application relates to the field of cleaning robot technology, and in particular to a cleaning robot control method, device, cleaning robot, and storage medium. Background Technology

[0002] With the development of intelligent robots, robots are being used to replace manual labor in more and more scenarios. For example, cleaning robots are being used to replace manual cleaning and are mostly applied in scenarios such as exhibition halls, shopping malls, airports, underground parking garages, high-bay warehouses, and cold chain logistics parks. However, current cleaning robots are generally based on the algorithm architecture of "open halls". In scenarios such as underground parking garages, high-bay warehouses, and cold chain logistics parks, the cleaning coverage rate is low. Moreover, due to the narrow space, abnormal behaviors such as getting stuck or stopping are prone to occur, resulting in low cleaning efficiency of cleaning robots. Summary of the Invention

[0003] This application provides a cleaning robot control method, device, cleaning robot, and storage medium to solve the problem of low cleaning efficiency of existing cleaning robots in rectangular micro-spaces.

[0004] In a first aspect, this application provides a method for controlling a cleaning robot, the method comprising: Obtain the preset observation point corresponding to the rectangular micro-space to be cleaned and the minimum cleanable area supported by the cleaning robot, and control the cleaning robot to move to the preset observation point; The preset observation point is adjusted according to the coverage of the rectangular micro-space to be cleaned by the image collected by the cleaning robot at the preset observation point to obtain the target observation point, wherein the target observation point is used to enable the cleaning robot to observe the whole picture of the rectangular micro-space to be cleaned. Based on the laser vision fusion point cloud sequence collected by the cleaning robot at the target observation point, the unobstructed and cleanable area corresponding to the rectangular microspace to be cleaned is determined. Based on the comparison between the unobstructed cleanable area and the minimum cleanable area, the target cleanable area corresponding to the rectangular micro-space to be cleaned is determined, wherein the target cleanable area is greater than or equal to the minimum cleanable area. The cleaning path is generated within the target area to be cleaned based on the structural parameters of the cleaning robot, and the cleaning robot is controlled to perform the cleaning task according to the cleaning path.

[0005] Secondly, this application provides a cleaning robot control device, the device comprising: The acquisition module is used to acquire the preset observation point corresponding to the rectangular micro-space to be cleaned and the minimum cleanable area supported by the cleaning robot, and control the cleaning robot to move to the preset observation point. An adjustment module is used to adjust the preset observation point according to the coverage of the rectangular micro-space to be cleaned by the image collected by the cleaning robot at the preset observation point, so as to obtain a target observation point, wherein the target observation point is used to enable the cleaning robot to observe the whole picture of the rectangular micro-space to be cleaned; The area recognition module is used to determine the unobstructed cleanable area corresponding to the rectangular microspace to be cleaned based on the laser vision fusion point cloud sequence collected by the cleaning robot at the target observation point; The area determination module is used to determine the target area to be cleaned corresponding to the rectangular micro-space to be cleaned based on the comparison result between the barrier-free cleanable area and the minimum cleanable area, wherein the target area to be cleaned is greater than or equal to the minimum cleanable area. The execution module is used to generate a cleaning path in the target area to be cleaned based on the structural parameters of the cleaning robot, and to control the cleaning robot to perform the cleaning task according to the cleaning path.

[0006] Thirdly, this application provides a cleaning robot, characterized in that the cleaning robot includes the cleaning robot control device as described above.

[0007] Fourthly, this application also provides a computer storage medium storing computer-executable instructions for executing the above-described cleaning robot control method.

[0008] Compared with the prior art, the technical solution provided in this application has the following advantages: The method provided in this application, when the cleaning robot faces a rectangular microspace, first acquires the preset observation point corresponding to the rectangular microspace to be cleaned and the minimum cleanable area supported by the cleaning robot. The minimum cleanable area indicates the minimum area that the cleaning robot can clean. The preset observation point is the location where the cleaning robot can observe the rectangular microspace to be cleaned at close range. After controlling the cleaning robot to move to the preset observation point, the method calculates the value of the laser vision fusion point cloud sequence acquired by the cleaning robot at the preset observation point facing the rectangular microspace to be cleaned. The visible, unobstructed cleanable area is compared with the minimum cleanable area to define a target area to be cleaned that is greater than or equal to the minimum cleanable area. A cleaning path is then generated within this target area based on the robot's structural parameters. The robot is controlled to perform the cleaning task according to this path. Because the target area to be cleaned is greater than or equal to the minimum cleanable area, the minimum kinematic constraints of the robot within the rectangular micro-space are satisfied. This avoids the robot failing to turn around or abandoning the task due to the narrow space, thus improving the cleaning efficiency and coverage of the robot within the rectangular micro-space. Attached Figure Description

[0009] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0010] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0012] Figure 1 An application environment diagram for a cleaning robot control method provided in this application embodiment; Figure 2 A flowchart illustrating a cleaning robot control method provided in an embodiment of this application; Figure 3 A flowchart illustrating a cleaning robot control method provided in an embodiment of this application; Figure 4 This is a schematic diagram illustrating the effect of expanding the barrier-free, cleanable area provided in the embodiments of this application; Figure 5 This application provides a schematic diagram of the cleaning path effect within a target area to be cleaned, as illustrated in an embodiment of the present application. Figure 6 A structural block diagram of a cleaning robot control device provided in an embodiment of this application; Figure 7 This is a schematic diagram of the internal structure of a cleaning robot provided in an embodiment of this application. Detailed Implementation

[0013] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, 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, 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.

[0014] The following disclosure provides numerous different embodiments or examples for implementing various structures of the invention. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the scope of the invention. Furthermore, reference numerals and / or letters may be repeated in different examples. Such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed.

[0015] Figure 1 This is an application environment diagram of a cleaning robot control method in one embodiment. (Refer to...) Figure 1 The cleaning robot control method is applied to a cleaning robot 100, which includes a cleaning robot control device 110. The cleaning robot control device 110 is used to collect data and perform calculations based on the collected data, thereby generating control commands to control various functional components of the cleaning robot 100. The functional components include a movement component, a cleaning component, a voice component, a communication component, etc.

[0016] In one embodiment, Figure 2 This is a flowchart illustrating a cleaning robot control method in one embodiment, with reference to... Figure 2 A method for controlling a cleaning robot is provided. This embodiment mainly illustrates the application of this method to a cleaning robot control device 110, and the cleaning robot control method specifically includes the following steps: Step S210: Obtain the preset observation point corresponding to the rectangular micro-space to be cleaned and the minimum cleanable area supported by the cleaning robot 100, and control the cleaning robot 100 to move to the preset observation point.

[0017] Specifically, the rectangular micro-space to be cleaned is typically a localized space in an underground parking garage, a high-bay rack warehouse, or a cold chain logistics park. Examples include an independent parking space in an underground garage, an aisle between any two parallel high-bay racks in a high-bay rack warehouse, or an aisle between any two parallel cold chain racks in a cold chain logistics park. The two-dimensional rectangular area corresponding to the micro-space to be cleaned is either an aisle area or a parking space area. The length of the aisle area is equal to the length of the rack distribution, while the width is equal to the distance between two parallel high-bay racks. The length and width of the parking space area corresponding to an independent parking space are determined by the ground parking space frame. In this embodiment, an independent parking space is used as an example to illustrate the rectangular micro-space to be cleaned.

[0018] The preset observation point is located outside the rectangular area corresponding to the rectangular microspace to be cleaned, and is located on the perpendicular bisector of the side of the rectangular area, at a preset distance from the midpoint of the side of the rectangular area. This side can be the long side or the short side of the rectangular area, so that the cleaning robot 100 can observe the whole picture of the rectangular microspace to be cleaned from the preset observation point.

[0019] The minimum cleanable area supported by the cleaning robot 100 is used to indicate the minimum area in which the cleaning robot 100 can turn and make a U-turn based on its own size and minimum kinematic constraints to achieve cleaning. The area of ​​the minimum cleanable area is denoted as the minimum cleanable area. The minimum cleanable area is usually a regular shape, such as a 1m×1m square or a 1m×2m rectangle.

[0020] The cleaning robot control device 110 sends a movement command corresponding to a preset observation point to the moving component of the cleaning robot 100 to control the cleaning robot 100 to move to the preset observation point.

[0021] Step S220: Adjust the preset observation point according to the coverage of the rectangular microspace to be cleaned by the image collected by the cleaning robot 100 at the preset observation point to obtain the target observation point, wherein the target observation point is used to enable the cleaning robot 100 to observe the whole picture of the rectangular microspace to be cleaned.

[0022] Specifically, after the cleaning robot 100 moves to the preset observation point, it collects images of the rectangular micro-space to be cleaned via a camera or other image acquisition device. The collected images contain the visible view of the rectangular micro-space to be cleaned from the cleaning robot 100. Based on the collected images, the visibility rate of the cleaning robot 100 over the rectangular micro-space to be cleaned from the preset observation point is determined, which is the coverage rate of the collected images over the rectangular micro-space to be cleaned. This is used to determine whether the preset observation point is the optimal observation point and whether it can completely observe the entire micro-space to be cleaned. If the coverage rate of the collected images over the micro-space to be cleaned is low, the position of the preset observation point is adjusted to obtain the target observation point, so that the cleaning robot 100 can observe the entire micro-space to be cleaned from the target observation point, so that the cleaning robot 100 can accurately identify obstacles in the micro-space to be cleaned.

[0023] The process of adjusting the preset observation point includes controlling the cleaning robot 100 to gradually move to the target observation point as the preset observation point is adjusted.

[0024] Step S230: Based on the laser vision fusion point cloud sequence collected by the cleaning robot 100 at the target observation point, determine the unobstructed cleanable area corresponding to the rectangular microspace to be cleaned.

[0025] Specifically, the cleaning robot 100 uses a LiDAR to collect a 3D geometric point cloud at the target observation point. This point cloud is then spatiotemporally aligned and fused with 2D image information acquired by a visual camera to form a laser visual fusion point cloud. The laser visual fusion point cloud sequence contains multiple frames of time-continuous laser visual fusion point cloud data. Based on this sequence, the robot accurately identifies the distribution of obstacles within the rectangular micro-space to be cleaned, thereby identifying the unobstructed cleanable area within that micro-space, excluding the obstacles.

[0026] Step S240: Based on the comparison result between the unobstructed cleanable area and the minimum cleanable area, determine the target cleanable area corresponding to the rectangular micro-space to be cleaned, wherein the target cleanable area is greater than or equal to the minimum cleanable area.

[0027] Specifically, the unobstructed cleanable area is compared with the minimum cleanable area, and a new target cleanable area that is greater than or equal to the minimum cleanable area is redefined. Even if the unobstructed cleanable area does not meet the minimum cleanable area requirement of the cleaning robot 100, a new target cleanable area that meets the minimum cleanable area requirement can be redefined based on the unobstructed cleanable area to satisfy the minimum kinematic constraints of the cleaning robot 100.

[0028] Step S250: Generate a cleaning path in the target area to be cleaned according to the structural parameters of the cleaning robot 100, and control the cleaning robot 100 to perform the cleaning task according to the cleaning path.

[0029] Specifically, a cleaning path is generated within the target area to be cleaned by combining the structural parameters of the cleaning robot 100. The cleaning robot 100 is then controlled to perform the cleaning task according to the cleaning path. Since the target area to be cleaned is greater than or equal to the minimum cleanable area, the minimum kinematic constraints of the cleaning robot 100 in the rectangular micro-space are satisfied. This avoids the cleaning robot 100 failing to turn around or abandoning the task due to the space being too narrow, thereby improving the cleaning efficiency and cleaning coverage of the cleaning robot 100 in the rectangular micro-space.

[0030] In one embodiment, refer to Figure 3 The step of obtaining the preset observation point corresponding to the rectangular micro-space to be cleaned and the minimum cleanable area supported by the cleaning robot 100, and controlling the cleaning robot 100 to move to the preset observation point, includes: Obtain a reflectivity grid map corresponding to the rectangular microspace to be cleaned, wherein the reflectivity grid map includes a rectangular area corresponding to the rectangular microspace to be cleaned, and the rectangular area includes two long sides, an outer short side and an inner short side, and the outer short side is used to indicate the entrance of the rectangular area; Based on the reflectivity grid map and the structural parameters of the cleaning robot 100, a preset observation point corresponding to the rectangular area is determined, wherein the preset observation point is located outside the rectangular area and is at a preset distance from the midpoint of the outer short side of the rectangular area; The minimum cleanable area corresponding to the rectangular area is determined based on the structural parameters of the cleaning robot 100, wherein the structural parameters include the body size, positioning method, minimum turning radius and preset safety margin of the cleaning robot 100.

[0031] Specifically, the reflectance raster map corresponding to the rectangular microspace to be cleaned can be a raster map corresponding to this local space, that is, it only contains the surface reflectance of the rectangular microspace to be cleaned; or it can be a global raster map corresponding to the storage space containing the rectangular microspace to be cleaned, that is, it contains the surface reflectance of all rectangular microspaces to be cleaned within the storage space. A reflectance raster map is a probabilistic / deterministic environmental representation map that divides the environment into raster cells and stores the surface reflectance value for each raster cell. Its core purpose is to characterize the optical reflectance properties of ground features.

[0032] Based on reflectivity grid maps, the rectangular area corresponding to the rectangular micro-space to be cleaned can be accurately determined. Taking the rectangular area as a parking space area as an example, based on the limiter marks in the reflectivity grid map, the parking space orientation of the parking space area can also be identified, that is, the entrance orientation of the rectangular area. Thus, the outer short side and the inner short side can be distinguished among the two short sides of the rectangular area. That is, the first short side through which the entrance orientation passes is the outer short side (used to indicate the entrance of the rectangular area), while the second short side through which the entrance orientation passes is the inner short side.

[0033] Based on the determined parking space area, the midpoint of the short side of the parking space entrance is taken, and the point is moved outward by a preset distance along the exit direction (i.e., away from the inner short side) to obtain the coordinates of the preset observation point. The preset observation point is located on the perpendicular bisector of the short side of the parking space entrance, at a preset distance from the short side of the parking space entrance. The preset distance is calculated by multiplying the body length of the cleaning robot 100 by a preset coefficient and adding a distance coefficient. Both the preset coefficient and the distance coefficient are customized according to actual application requirements. In this embodiment, the body length is denoted as L (meters), the preset coefficient is denoted as A1=1.2, and the distance coefficient is denoted as A2=0.3, so the preset distance is 1.2×L+0.3 (meters).

[0034] The structural parameters of the cleaning robot 100 include the robot's body dimensions (including length, width, and height), positioning method, minimum turning radius, and preset safety margin. Using the artificial intelligence model corresponding to the minimum kinematic constraints, the minimum cleanable area corresponding to the cleaning robot 100 is calculated based on the body dimensions, positioning method, minimum turning radius, and preset safety margin. The boundary of the minimum cleanable area includes the area length and area width. Based on the area length and area width, the minimum cleanable area corresponding to the minimum cleanable area can be calculated. This method outputs a minimum cleanable area with centimeter-level accuracy, precisely adapting to the motion characteristics of different cleaning robot models. It avoids overestimating the cleanable range, preventing the robot from entering areas that cannot be cleaned, causing it to get stuck, collide with limiters, or malfunction in warehouse shelves. It also avoids overcompressing the cleanable range, leaving blind spots in the rectangular micro-space to be cleaned. Simultaneously, relying on the accurate representation of environmental optical characteristics using a reflectivity grid map, combined with the calculation results of the artificial intelligence model corresponding to the minimum kinematic constraints, it can provide accurate area boundary constraints for subsequent cleaning path planning. This improves the computational efficiency of cleaning path planning and also increases cleaning coverage, effectively ensuring the cleaning effect and operational safety of the rectangular micro-space to be cleaned in warehouse scenarios.

[0035] In one embodiment, refer to Figure 3 The step of adjusting the preset observation point based on the coverage of the image acquired by the cleaning robot 100 at the preset observation point for the rectangular micro-space to be cleaned, to obtain the target observation point, includes: Acquire images of the cleaning robot 100 at a preset observation point, facing the rectangular micro-space to be cleaned; When the coverage of the acquired image for the rectangular microspace to be cleaned is greater than or equal to a preset coverage rate, the preset observation point is taken as the target observation point; When the coverage of the acquired image for the rectangular microspace to be cleaned is less than a preset coverage rate, the preset observation point is translated along a preset direction and a preset step size, and the step of acquiring the image of the cleaning robot 100 at the preset observation point is re-executed, wherein the preset direction is parallel to the outer short side of the rectangular area corresponding to the rectangular microspace to be cleaned.

[0036] Specifically, the cleaning robot 100 acquires images of the rectangular micro-space to be cleaned from a preset observation point. The acquired images are then analyzed and processed. Specifically, the coverage rate of the acquired images can be determined based on the similarity between the acquired images and the standard images corresponding to the rectangular micro-space to be cleaned at the preset observation point. The lower the coverage rate, the more likely the cleaning robot 100 cannot properly observe the rectangular micro-space to be cleaned from the preset observation point. This may be due to temporary obstacles causing the adjustment failure, meaning that the actual orientation of the cleaning robot 100 is not towards the rectangular micro-space to be cleaned, or it may be due to temporary obstacles between the rectangular micro-space to be cleaned and the cleaning robot 100, causing the cleaning robot 100 to only see a partial view of the rectangular micro-space to be cleaned and not be able to observe the entire rectangular micro-space.

[0037] Therefore, when the coverage of the acquired image over the rectangular micro-space to be cleaned is greater than or equal to the preset coverage, it means that the cleaning robot 100 can observe the entire rectangular micro-space at the preset observation point. The preset observation point is then used as the target observation point. The preset coverage can be 100%. To provide a margin of error for the preset observation point, the preset coverage can also be set to 80%, 85%, 90%, 95%, etc. The higher the preset coverage, the higher the positioning accuracy of the target observation point. In other words, the cleaning robot 100 only needs to observe most of the rectangular micro-space to be cleaned at the preset observation point.

[0038] When the coverage of the acquired image for the rectangular micro-space to be cleaned is less than the preset coverage, it indicates that the cleaning robot 100 cannot observe the entire rectangular micro-space from the preset observation point. Therefore, the preset observation point needs to be adjusted so that the cleaning robot 100 can move to a location where the entire rectangular micro-space can be observed. Specifically, the preset observation point is moved laterally according to a preset direction and a preset step size. The preset direction is parallel to the short side of the rectangular area, meaning the cleaning robot 100 moves laterally relative to the short side of the rectangular area according to a preset step size. The preset step size can be customized based on the size of the rectangular area. For rectangular areas with larger dimensions, the preset step size is set to be larger; conversely, for rectangular areas with smaller dimensions, the preset step size is set to be smaller. In this embodiment, the preset step size is set to 0.2 meters. After the cleaning robot 100 moves 0.2 meters along the preset direction, it re-captures an image of the rectangular micro-space to be cleaned. Then, the coverage rate of the captured image for the rectangular micro-space to be cleaned is recalculated until the coverage rate of the captured image for the rectangular micro-space to be cleaned is greater than or equal to the preset coverage rate. Then, the cleaning robot 100 stops moving, and the location after the cleaning robot 100 moves is taken as the target observation point.

[0039] The target observation point can also be stored locally in the cleaning robot 100 to update the preset observation point corresponding to the rectangular micro-space to be cleaned. This allows the cleaning robot 100 to move directly to the corrected target observation point before cleaning the rectangular micro-space next time, thereby shortening the target observation point correction process and improving the cleaning efficiency of the cleaning robot 100.

[0040] In one embodiment, refer to Figure 3 The step of determining the unobstructed cleanable area corresponding to the rectangular micro-space to be cleaned based on the laser vision fusion point cloud sequence collected by the cleaning robot 100 at the target observation point includes: Acquire the laser vision fusion point cloud sequence obtained by the cleaning robot 100 at the target observation point facing the rectangular microspace to be cleaned; The distribution positions of obstacles in the rectangular microspace to be cleaned are determined based on the laser vision fusion point cloud sequence. Based on the location of the obstacles, the rectangular area corresponding to the rectangular microspace to be cleaned is longitudinally and / or laterally cut to obtain the unobstructed cleanable area corresponding to the rectangular microspace to be cleaned.

[0041] Specifically, the cleaning robot 100 collects a laser vision fusion point cloud sequence from the target observation point toward the rectangular microspace to be cleaned. This sequence includes multiple consecutive frames of laser vision fusion point cloud. Obstacle recognition is performed on the Meizhen laser vision fusion point cloud. If the same obstacle appears in multiple consecutive frames (e.g., 5 frames), the obstacle is identified as a valid obstacle. The distribution position of the valid obstacle in the rectangular microspace to be cleaned is then determined, thereby determining the obstacle distribution position.

[0042] Based on the location of obstacles, the rectangular area corresponding to the micro-space to be cleaned is divided longitudinally and / or laterally. Specifically, the lateral and longitudinal occupancy rates of the obstacles within the rectangular area are determined. If the lateral occupancy rate is greater than the longitudinal occupancy rate, the rectangular area is divided longitudinally; if the longitudinal occupancy rate is greater than the lateral occupancy rate, the rectangular area is divided laterally. This process removes the obstacle-occupied area from the rectangular area, preserving as much unobstructed area as possible. Alternatively, both longitudinal and lateral divisions can be performed simultaneously to minimize the area of ​​obstacle-included regions, ensuring the maximum remaining area. The area remaining after obstacle removal is designated as the unobstructed cleanable zone.

[0043] This cutting method increases the proportion of unobstructed cleanable area, allowing the cleaning robot 100 to bypass areas containing obstacles and reducing ineffective cleaning blind spots. At the same time, the continuous frame obstacle verification mechanism based on laser vision fusion point cloud can reduce the probability of noise in single frame acquisition and temporary moving objects being misjudged as obstacles, avoiding frequent adjustments to the cleaning path by the cleaning robot 100 due to misjudgment. This effectively improves the efficiency of cleaning path planning and actual cleaning coverage, and can shorten the overall cleaning completion time in narrow and complex indoor cleaning scenarios.

[0044] In one embodiment, refer to Figure 3 The step of determining the target area to be cleaned corresponding to the rectangular micro-space to be cleaned based on the comparison result between the unobstructed cleanable area and the minimum cleanable area includes: When the unobstructed cleanable area is greater than or equal to the minimum cleanable area, the unobstructed cleanable area is determined as the target area to be cleaned; When the unobstructed cleanable area is smaller than the minimum cleanable area, the unobstructed cleanable area is expanded to obtain an extended area. If the extended area is greater than or equal to the minimum cleanable area, the extended area is determined as the target area to be cleaned.

[0045] Specifically, the unobstructed cleanable area is compared with the minimum cleanable area. This comparison involves comparing the dimensions of both the long and short sides of the unobstructed cleanable area. If both the long and short sides of the unobstructed cleanable area are greater than or equal to those of the minimum cleanable area, then the unobstructed cleanable area is considered to be greater than or equal to the minimum cleanable area. This indicates that the unobstructed cleanable area meets the minimum kinematic constraints of the cleaning robot 100, and can then be designated as the target area to be cleaned. Alternatively, the system can determine if the dimensions of the unobstructed cleanable area completely cover the dimensions of the minimum cleanable area. If the unobstructed cleanable area completely covers the minimum cleanable area, then it is considered to be greater than or equal to the minimum cleanable area.

[0046] Area comparison is not simply a direct comparison of the areas of the two areas. This is because there may be cases where the area of ​​the unobstructed cleanable area is greater than or equal to the area of ​​the minimum cleanable area, but the shorter side of the unobstructed cleanable area is smaller than the shorter side of the minimum cleanable area. In other words, there may be cases where the unobstructed cleanable area is long and narrow, but its narrowness is less than the minimum turning radius of the cleaning robot 100, causing the cleaning robot 100 to be unable to turn or turn around normally in this area. Therefore, it is necessary to compare the area size of the unobstructed cleanable area with the area size of the minimum cleanable area to ensure the accuracy of the judgment on whether the unobstructed cleanable area meets the minimum kinematic constraints of the cleaning robot 100.

[0047] If the shorter side of the unobstructed cleanable area is smaller than the shorter side of the minimum cleanable area, or if the unobstructed cleanable area cannot completely cover the minimum cleanable area, then the unobstructed cleanable area is considered to be smaller than the minimum cleanable area. In this case, the unobstructed cleanable area needs to be expanded. If the expanded area can completely cover the minimum cleanable area, then the expanded area is taken as the target area to be cleaned. The expanded area includes the unobstructed cleanable area and the expanded area. By expanding the unobstructed cleanable area, the target area to be cleaned is ensured to meet the minimum kinematic constraints of the cleaning robot 100, so that the cleaning task can be completed even in narrow spaces.

[0048] If the expanded area still cannot completely cover the smallest cleanable area, that is, if the expanded area is still smaller than the smallest cleanable area, then the cleaning is abandoned and the cleaning task corresponding to the rectangular micro-space to be cleaned is refused.

[0049] In one embodiment, refer to Figure 3 When the unobstructed cleanable area is smaller than the minimum cleanable area, expanding the unobstructed cleanable area to obtain an extended area includes: When the unobstructed cleanable area is smaller than the minimum cleanable area, the obstacle accumulation state on the outer side of the long side of the rectangular area corresponding to the rectangular microspace to be cleaned is determined according to the laser vision fusion point cloud sequence. When at least one long side of the rectangular area is free of obstacles, the long side with free obstacles is defined as the free long side, and the free cleanable area is expanded outward by a specified distance to the outside of the free long side to obtain the extended area.

[0050] Specifically, when the unobstructed cleanable area cannot completely cover the minimum cleanable area, the obstacle accumulation state outside the two long sides of the rectangular area is determined based on the laser vision fusion point cloud sequence, that is, whether there are obstacles outside the two long sides of the rectangular area. If there are no obstacles outside at least one long side of the rectangular area, then that long side is determined as the obstacle-free long side, and the area is extended outward by a specified distance towards the outside of the obstacle-free long side. The specified distance can be customized according to different application scenarios. In this embodiment, the specified distance is set to 0.05 meters, that is, the obstacle-free long side is translated 0.05 meters away from the rectangular area, that is, the short side of the unobstructed cleanable area is extended by 0.05 meters. The translated obstacle-free long side, the unmoved long side, and the extended short side constitute the extended area.

[0051] Reference Figure 4 The rectangular region is the region corresponding to (d1+d2)×L. Figure 4 The obstacle is indicated by a midpoint. The unobstructed, cleanable area after longitudinally dividing the rectangular area according to the obstacle's location is the region corresponding to d2×L. The expanded area after extending the unobstructed, cleanable area is the region corresponding to (d3+d2)×L. This is because the right side of the rectangular area (i.e.,...) Figure 4 There is a black wall obstacle in the lower right of the rectangular area. Therefore, the left long side of the rectangular area is taken as the unobstructed long side, that is, to the left (i.e., Figure 4 The upper left side of the rectangular area is translated to the unobstructed long side, and the short side of the unobstructed cleanable area is extended to the left to obtain the expanded area.

[0052] In one embodiment, refer to Figure 3 The cleaning path is generated within the target area to be cleaned based on the structural parameters of the cleaning robot 100, including: Based on the body size, maximum turning radius, and cleaning radius of the cleaning robot 100, multiple bow-shaped sweeping lines are generated at equal intervals along the long side of the target area to be cleaned. Construct an arc connecting line between any two adjacent arc-shaped sweep lines based on an elliptic function, wherein the elliptic function includes a major axis parameter and a minor axis parameter, the major axis parameter being the product of the major axis coefficient and a preset spacing, and the minor axis parameter being the product of the minor axis coefficient and the major axis parameter; Predict the body collision state of the cleaning robot 100 at various coordinate points on the arc connecting line; When the robot 100 is in a collision state at at least one coordinate point on the arc connecting line, the minor axis parameter is shortened according to a preset variable, and the step of constructing the arc connecting line between any two adjacent bow-shaped sweeping lines according to the elliptic function is re-executed. When the robot 100 is in a non-collision state at each coordinate point on the arc connecting line, it forms a cleaning path in the target area to be cleaned based on the multiple bow-shaped sweeping lines and the arc connecting lines between each adjacent bow-shaped sweeping line.

[0053] Specifically, the body size also includes the outer radius of the frame of the cleaning robot 100. The outer radius of the frame, the maximum turning radius, the cleaning radius, and the area size of the target area to be cleaned are input into the bow-shaped sweeping line calculation model, and multiple equally spaced parallel bow-shaped sweeping lines are output. The bow-shaped sweeping lines are parallel to the long side of the target area to be cleaned.

[0054] Then, an arc connecting two adjacent arc-shaped sweep lines is constructed using an elliptic function. The elliptic function is y² / a² + x² / b² = 1, where a is the major axis parameter and b is the minor axis parameter. The major axis parameter is the product of the major axis coefficient and the preset spacing, i.e., a = a1 × d, where a1 is the major axis coefficient and d is the preset spacing. The minor axis parameter is the product of the minor axis coefficient and the major axis parameter, i.e., b = b1 × a. In this embodiment, the major axis coefficient is set to 0.5 and the minor axis coefficient is set to 0.3, i.e., a = 0.5 × d and b = 0.3 × a.

[0055] For each coordinate point on the arc connecting line, a vehicle frame simulated collision detection is performed sequentially. This predicts the body collision state of the sweeping robot 100 at each coordinate point on the arc connecting line. If the body collision state of the sweeping robot 100 at at least one coordinate point on the arc connecting line is "collision has occurred," the minor axis parameter is reduced according to a preset variable. The preset variable is any value; in this embodiment, the preset variable Δb is set to 0.05 meters, meaning the updated minor axis parameter is b' = b - Δb. The arc connecting line is then reconstructed using the updated minor axis parameter, and the vehicle frame simulated collision detection is performed again until all points on the arc connecting line pass the vehicle condition simulated collision detection. The cleaning path is then formed based on the bow-shaped sweeping line and the arc connecting line, referring to... Figure 5 The cleaning path in the middle, Figure 5 The rectangle in the upper right corner that does not contain the cleaning path refers to the parking space limiter, which is used to identify the orientation of the parking space entrance.

[0056] This path generation method is adaptable to cleaning robots 100 of different sizes and cleaning areas of different dimensions. Relying on the iterative adjustment of collision detection simulation of the vehicle frame, it ensures that the final generated cleaning path will not have the risk of colliding with obstacles or area boundaries, while maximizing the coverage integrity of the arc-shaped cleaning path. It avoids leaving cleaning dead corners by unnecessarily reducing the path coverage area to avoid collisions. At the same time, through the gradual adjustment and optimization of the short axis parameters, the turning arc of the arc connecting line is adapted to the actual turning ability of the cleaning robot 100. This solves the problems of robot jamming and wear and tear on parts when turning in place that are easy to occur in traditional fixed parameter path generation. It can effectively improve the autonomous path planning efficiency and actual cleaning coverage of the cleaning robot 100 and reduce the probability of failure during robot operation.

[0057] Figure 2 and Figure 3 This is a flowchart illustrating a cleaning robot control method in one embodiment. It should be understood that, although... Figure 2 and Figure 3 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 2 and Figure 3 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0058] In one embodiment, such as Figure 6 As shown, a cleaning robot control device 110 is provided, including: The acquisition module 310 is used to acquire the preset observation point corresponding to the rectangular micro-space to be cleaned and the minimum cleanable area supported by the cleaning robot 100, and control the cleaning robot 100 to move to the preset observation point. The adjustment module 320 is used to adjust the preset observation point according to the coverage of the image collected by the cleaning robot 100 at the preset observation point for the rectangular micro-space to be cleaned, so as to obtain the target observation point, wherein the target observation point is used to enable the cleaning robot 100 to observe the whole picture of the rectangular micro-space to be cleaned. The area recognition module 330 is used to determine the unobstructed cleanable area corresponding to the rectangular microspace to be cleaned based on the laser vision fusion point cloud sequence collected by the cleaning robot 100 at the target observation point. The area determination module 340 is used to determine the target area to be cleaned corresponding to the rectangular micro-space to be cleaned based on the comparison result between the barrier-free cleanable area and the minimum cleanable area, wherein the target area to be cleaned is greater than or equal to the minimum cleanable area. The execution module 350 is used to generate a cleaning path in the target area to be cleaned according to the structural parameters of the cleaning robot 100, and control the cleaning robot 100 to perform the cleaning task according to the cleaning path.

[0059] In one embodiment, the acquisition module 310 is further configured to: Obtain a reflectivity grid map corresponding to the rectangular microspace to be cleaned, wherein the reflectivity grid map includes a rectangular area corresponding to the rectangular microspace to be cleaned, and the rectangular area includes two long sides, an outer short side and an inner short side, and the outer short side is used to indicate the entrance of the rectangular area; Based on the reflectivity grid map and the structural parameters of the cleaning robot 100, a preset observation point corresponding to the rectangular area is determined, wherein the preset observation point is located outside the rectangular area and is at a preset distance from the midpoint of the outer short side of the rectangular area; The minimum cleanable area corresponding to the rectangular area is determined based on the structural parameters of the cleaning robot 100, wherein the structural parameters include the body size, positioning method, minimum turning radius and preset safety margin of the cleaning robot 100.

[0060] In one embodiment, the adjustment module 320 is further configured to: Acquire images of the cleaning robot 100 at a preset observation point, facing the rectangular micro-space to be cleaned; When the coverage of the acquired image for the rectangular microspace to be cleaned is greater than or equal to a preset coverage rate, the preset observation point is taken as the target observation point. When the coverage of the acquired image for the rectangular microspace to be cleaned is less than a preset coverage rate, the preset observation point is translated along a preset direction and a preset step size, and the step of acquiring the image of the cleaning robot 100 at the preset observation point is re-executed, wherein the preset direction is parallel to the outer short side of the rectangular area corresponding to the rectangular microspace to be cleaned.

[0061] In one embodiment, the region identification module 330 is further configured to: Acquire the laser vision fusion point cloud sequence obtained by the cleaning robot 100 at the target observation point facing the rectangular microspace to be cleaned; The distribution positions of obstacles in the rectangular microspace to be cleaned are determined based on the laser vision fusion point cloud sequence. Based on the location of the obstacles, the rectangular area corresponding to the rectangular microspace to be cleaned is longitudinally and / or laterally cut to obtain the unobstructed cleanable area corresponding to the rectangular microspace to be cleaned.

[0062] In one embodiment, the region determination module 340 is further configured to: When the unobstructed cleanable area is greater than or equal to the minimum cleanable area, the unobstructed cleanable area is determined as the target area to be cleaned; When the unobstructed cleanable area is smaller than the minimum cleanable area, the unobstructed cleanable area is expanded to obtain an extended area. If the extended area is greater than or equal to the minimum cleanable area, the extended area is determined as the target area to be cleaned.

[0063] In one embodiment, the region determination module 340 is further configured to: When the unobstructed cleanable area is smaller than the minimum cleanable area, the obstacle accumulation state on the outer side of the long side of the rectangular area corresponding to the rectangular microspace to be cleaned is determined according to the laser vision fusion point cloud sequence. When at least one long side of the rectangular area is free of obstacles, the long side with free obstacles is defined as the free long side, and the free cleanable area is expanded outward by a specified distance to the outside of the free long side to obtain the extended area.

[0064] In one embodiment, the execution module 350 is further configured to: Based on the body size, maximum turning radius, and cleaning radius of the cleaning robot 100, multiple bow-shaped sweeping lines are generated at equal intervals along the long side of the target area to be cleaned. Construct an arc connecting line between any two adjacent arc-shaped sweep lines based on an elliptic function, wherein the elliptic function includes a major axis parameter and a minor axis parameter, the major axis parameter being the product of the major axis coefficient and a preset spacing, and the minor axis parameter being the product of the minor axis coefficient and the major axis parameter; Predict the body collision state of the cleaning robot 100 at various coordinate points on the arc connecting line; When the robot 100 is in a collision state at at least one coordinate point on the arc connecting line, the minor axis parameter is shortened according to a preset variable, and the step of constructing the arc connecting line between any two adjacent bow-shaped sweeping lines according to the elliptic function is re-executed. When the robot 100 is in a non-collision state at each coordinate point on the arc connecting line, it forms a cleaning path in the target area to be cleaned based on the multiple bow-shaped sweeping lines and the arc connecting lines between each adjacent bow-shaped sweeping line.

[0065] It should be noted that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the content disclosed in the above embodiments. It should also be noted that the above modules, as part of a device, can operate in environments such as... Figure 1 The hardware environment shown can be implemented either through software or through hardware.

[0066] like Figure 7 As shown, this application embodiment provides a cleaning robot 100, including a processor 711, a communication interface 712, a memory 713, and a communication bus 714. The processor 711, the communication interface 712, and the memory 713 communicate with each other through the communication bus 714. The memory 713 is used to store computer programs. When the processor 711 executes the program stored in the memory 713, it implements the cleaning robot control method provided in any of the aforementioned method embodiments.

[0067] The memory and processor in the aforementioned electronic devices communicate with each other via a communication bus and a communication interface. The communication bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc.

[0068] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0069] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0070] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the cleaning robot 100 to which the present application is applied. The specific cleaning robot 100 may include more or fewer parts than shown in the figure, or combine certain parts, or have different part arrangements.

[0071] According to another aspect of the embodiments of this application, a computer program product or computer program is also provided, which includes computer instructions stored in a computer-readable storage medium. The processor of the cleaning robot 100 reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the cleaning robot 100 to perform the steps of any of the above embodiments.

[0072] In one embodiment, the cleaning robot control device 110 provided in this application can be implemented as a computer program, and the computer program can be implemented in such a way as... Figure 7 The cleaning robot 100 shown is running. The memory of the cleaning robot 100 can store various program modules that make up the cleaning robot control device 110, for example, Figure 6 The diagram shows an acquisition module 310, an adjustment module 320, an area recognition module 330, an area determination module 340, and an execution module 350. The computer program comprised of these modules causes the processor to execute the cleaning robot control methods of the various embodiments of this application described in this specification.

[0073] Figure 7 The cleaning robot 100 shown can, as Figure 6The acquisition module 310 in the cleaning robot control device 110 shown acquires a preset observation point corresponding to the rectangular micro-space to be cleaned and the minimum cleanable area supported by the cleaning robot 100, and controls the cleaning robot 100 to move to the preset observation point. The cleaning robot 100 can adjust the preset observation point according to the coverage of the image acquired by the cleaning robot 100 at the preset observation point, obtained by the adjustment module 320, to obtain a target observation point. The target observation point is used for the cleaning robot 100 to observe the entire rectangular micro-space to be cleaned. The cleaning robot 100 can determine the unobstructed cleanable area corresponding to the rectangular micro-space to be cleaned based on the laser vision fusion point cloud sequence acquired by the cleaning robot 100 at the target observation point, through the area recognition module 330. The cleaning robot 100 can determine the target area to be cleaned corresponding to the rectangular micro-space to be cleaned based on the comparison result between the unobstructed cleanable area and the minimum cleanable area through the area determination module 340, wherein the target area to be cleaned is greater than or equal to the minimum cleanable area. The cleaning robot 100 can generate a cleaning path within the target area to be cleaned based on the structural parameters of the cleaning robot 100 through the execution module 350, and control the cleaning robot 100 to perform the cleaning task according to the cleaning path.

[0074] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the cleaning robot control method provided in any of the foregoing method embodiments.

[0075] Optionally, in embodiments of this application, the computer-readable medium is configured to store program code for the processor to perform the following steps: Obtain the preset observation point corresponding to the rectangular micro-space to be cleaned and the minimum cleanable area supported by the cleaning robot 100, and control the cleaning robot 100 to move to the preset observation point; The cleaning robot 100 adjusts the preset observation point based on the coverage of the rectangular micro-space to be cleaned by the image collected at the preset observation point to obtain the target observation point, wherein the target observation point is used to enable the cleaning robot 100 to observe the whole picture of the rectangular micro-space to be cleaned. Based on the laser vision fusion point cloud sequence collected by the cleaning robot 100 at the target observation point, the unobstructed cleanable area corresponding to the rectangular microspace to be cleaned is determined. Based on the comparison between the unobstructed cleanable area and the minimum cleanable area, the target cleanable area corresponding to the rectangular micro-space to be cleaned is determined, wherein the target cleanable area is greater than or equal to the minimum cleanable area. The cleaning path in the target area to be cleaned is generated according to the structural parameters of the cleaning robot 100, and the cleaning robot 100 is controlled to perform the cleaning task according to the cleaning path.

[0076] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments, and will not be repeated here.

[0077] It is understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit can be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described herein, or combinations thereof.

[0078] For software implementation, the techniques described herein can be implemented by units that perform the functions described herein. The software code can be stored in memory and executed by a processor. The memory can be implemented in the processor or external to the processor.

[0079] Those skilled in the art will 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, or a combination of computer software and electronic hardware. 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.

[0080] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0081] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0082] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0083] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0084] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a USB flash drive, external hard drive, ROM, RAM, magnetic disk, or optical disk, or other media capable of storing program code, including several instructions to cause a cleaning robot (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments.

[0085] It should be understood that the terminology used herein is for the purpose of describing particular exemplary embodiments only and is not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “described” as used herein may also mean including the plural forms. The terms “comprising,” “including,” “containing,” and “having” are inclusive and therefore indicate the presence of the stated features, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, elements, components, and / or combinations thereof. The method steps, processes, and operations described herein are not construed as requiring them to be performed in a particular order described or illustrated unless the order of performance is explicitly indicated. It should also be understood that alternatives or substitutions may be used.

[0086] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. 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 the invention. Therefore, the present invention 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 claimed herein.

Claims

1. A control method for a cleaning robot, characterized in that, The method includes: Obtain the preset observation point corresponding to the rectangular micro-space to be cleaned and the minimum cleanable area supported by the cleaning robot, and control the cleaning robot to move to the preset observation point; The preset observation point is adjusted according to the coverage of the rectangular micro-space to be cleaned by the image collected by the cleaning robot at the preset observation point to obtain the target observation point, wherein the target observation point is used to enable the cleaning robot to observe the whole picture of the rectangular micro-space to be cleaned. Based on the laser vision fusion point cloud sequence collected by the cleaning robot at the target observation point, the unobstructed and cleanable area corresponding to the rectangular microspace to be cleaned is determined. Based on the comparison between the unobstructed cleanable area and the minimum cleanable area, the target cleanable area corresponding to the rectangular micro-space to be cleaned is determined, wherein the target cleanable area is greater than or equal to the minimum cleanable area. The cleaning path is generated within the target area to be cleaned based on the structural parameters of the cleaning robot, and the cleaning robot is controlled to perform the cleaning task according to the cleaning path.

2. The method according to claim 1, characterized in that, The step of acquiring the preset observation point corresponding to the rectangular micro-space to be cleaned and the minimum cleanable area supported by the cleaning robot, and controlling the cleaning robot to move to the preset observation point, includes: Obtain a reflectivity grid map corresponding to the rectangular microspace to be cleaned, wherein the reflectivity grid map includes a rectangular area corresponding to the rectangular microspace to be cleaned, and the rectangular area includes two long sides, an outer short side and an inner short side, and the outer short side is used to indicate the entrance of the rectangular area; Based on the reflectivity grid map and the structural parameters of the cleaning robot, a preset observation point corresponding to the rectangular area is determined, wherein the preset observation point is located outside the rectangular area and is at a preset distance from the midpoint of the outer short side of the rectangular area; The minimum cleanable area corresponding to the rectangular region is determined based on the structural parameters of the cleaning robot, wherein the structural parameters include the robot's body size, positioning method, minimum turning radius, and preset safety margin.

3. The method according to claim 1, characterized in that, The step of adjusting the preset observation point based on the coverage of the rectangular micro-space to be cleaned by the image collected by the cleaning robot at the preset observation point to obtain the target observation point includes: The cleaning robot acquires an image of itself from a preset observation point, facing the rectangular micro-space to be cleaned. When the coverage of the acquired image for the rectangular microspace to be cleaned is greater than or equal to a preset coverage rate, the preset observation point is taken as the target observation point. When the coverage of the acquired image for the rectangular microspace to be cleaned is less than a preset coverage rate, the preset observation point is translated along a preset direction and a preset step size, and the step of acquiring the image of the cleaning robot at the preset observation point is re-executed, wherein the preset direction is parallel to the outer short side of the rectangular area corresponding to the rectangular microspace to be cleaned.

4. The method according to claim 1, characterized in that, The step of determining the unobstructed, cleanable area corresponding to the rectangular micro-space to be cleaned based on the laser vision fusion point cloud sequence collected by the cleaning robot at the target observation point includes: The cleaning robot acquires a laser vision fusion point cloud sequence from the target observation point, facing the rectangular microspace to be cleaned. The distribution positions of obstacles in the rectangular microspace to be cleaned are determined based on the laser vision fusion point cloud sequence. Based on the location of the obstacles, the rectangular area corresponding to the rectangular microspace to be cleaned is longitudinally and / or laterally cut to obtain the unobstructed cleanable area corresponding to the rectangular microspace to be cleaned.

5. The method according to claim 4, characterized in that, The step of determining the target area to be cleaned corresponding to the rectangular micro-space to be cleaned based on the comparison result between the unobstructed cleanable area and the minimum cleanable area includes: When the unobstructed cleanable area is greater than or equal to the minimum cleanable area, the unobstructed cleanable area is determined as the target area to be cleaned; When the unobstructed cleanable area is smaller than the minimum cleanable area, the unobstructed cleanable area is expanded to obtain an extended area. If the extended area is greater than or equal to the minimum cleanable area, the extended area is determined as the target area to be cleaned.

6. The method according to claim 5, characterized in that, When the unobstructed cleanable area is smaller than the minimum cleanable area, the unobstructed cleanable area is expanded to obtain an extended area, including: When the unobstructed cleanable area is smaller than the minimum cleanable area, the obstacle accumulation state on the outer side of the long side of the rectangular area corresponding to the rectangular microspace to be cleaned is determined according to the laser vision fusion point cloud sequence. When at least one long side of the rectangular area is free of obstacles, the long side with free obstacles is defined as the free long side, and the free cleanable area is expanded outward by a specified distance to the outside of the free long side to obtain the extended area.

7. The method according to claim 1, characterized in that, Generate a cleaning path within the target area to be cleaned based on the structural parameters of the cleaning robot, including: Based on the robot's body size, maximum turning radius, and cleaning radius, multiple arc-shaped sweeping lines are generated at equal intervals along the long side of the target area to be cleaned. Construct an arc connecting line between any two adjacent arc-shaped sweep lines based on an elliptic function, wherein the elliptic function includes a major axis parameter and a minor axis parameter, the major axis parameter being the product of the major axis coefficient and a preset spacing, and the minor axis parameter being the product of the minor axis coefficient and the major axis parameter; Predict the collision state of the cleaning robot at each coordinate point on the arc connecting line; When the robot body collision state at at least one coordinate point on the arc connecting line is a collision, the minor axis parameter is shortened according to a preset variable, and the step of constructing the arc connecting line between any two adjacent bow-shaped sweeping lines according to the elliptic function is re-executed. When the robot body collision state at each coordinate point on the arc connecting line is non-collision, the cleaning path in the target cleaning area is formed according to the multiple bow-shaped sweeping lines and the arc connecting lines between each adjacent bow-shaped sweeping line.

8. A control device for a cleaning robot, characterized in that, The device includes: The acquisition module is used to acquire the preset observation point corresponding to the rectangular micro-space to be cleaned and the minimum cleanable area supported by the cleaning robot, and control the cleaning robot to move to the preset observation point. An adjustment module is used to adjust the preset observation point according to the coverage of the rectangular micro-space to be cleaned by the image collected by the cleaning robot at the preset observation point, so as to obtain a target observation point, wherein the target observation point is used to enable the cleaning robot to observe the whole picture of the rectangular micro-space to be cleaned; The area recognition module is used to determine the unobstructed cleanable area corresponding to the rectangular microspace to be cleaned based on the laser vision fusion point cloud sequence collected by the cleaning robot at the target observation point; The area determination module is used to determine the target area to be cleaned corresponding to the rectangular micro-space to be cleaned based on the comparison result between the barrier-free cleanable area and the minimum cleanable area, wherein the target area to be cleaned is greater than or equal to the minimum cleanable area. The execution module is used to generate a cleaning path in the target area to be cleaned based on the structural parameters of the cleaning robot, and to control the cleaning robot to perform the cleaning task according to the cleaning path.

9. A cleaning robot, characterized in that, The cleaning robot includes the cleaning robot control device as described in claim 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 7.

Images