Dynamic path planning method and system of self-moving cleaning robot and sweeper

Abstract

The invention discloses a dynamic path planning method and system for a self-moving cleaning robot and a sweeper, and relates to the technical field of smart home. The dynamic path planning method comprises the following steps: generating an initial planning path; identifying a removable target obstacle on the initial planned path, and removing the target obstacle through a removal component on the self-moving cleaning robot; determining a compensation cleaning area and a compensation cleaning path according to the position and the size of the target obstacle; and carrying out topological fusion on the compensation cleaning path and the initial planning path to generate an updated planning path. According to the invention, an integrated solution of obstacle removal, missing sweeping compensation and sweeping path optimization is realized by constructing a response compensation mechanism of'grabbing-area marking-compensation sweeping '.

Description

Technical Field

[0001] The present application relates to the field of smart home technology, and specifically to a dynamic path planning method and system for a self-propelled cleaning robot and a sweeper. Background Art

[0002] Current robotic vacuums have achieved basic obstacle avoidance capabilities in environmental perception and path planning, but significant flaws exist in their collaborative operations after grasping objects. For example, existing technologies often use independent control modules: the robotic gripping system and the cleaning path planning system have no data interaction, resulting in a logical disconnect between action execution. Specifically, the following issues exist:

[0003] Missed-sweep problem: The completion of the grasping action only triggers obstacle avoidance re-planning, and cannot identify and clean the missed-sweep area, which will cause dust or debris to remain in the grasping area; path redundancy problem: The robot arm movement and cleaning path are generated by independent algorithms, lacking coordinated scheduling, and frequent starts and stops resulting in high path redundancy rate and time-consuming cleaning tasks; secondary pollution problem: The existing system has not established a dynamic map marking mechanism for polluted areas, and residual pollutants after the grasped object is removed may be spread again.

[0004] Therefore, a solution is needed to at least partially solve the above problems. Summary of the Invention

[0005] The purpose of the embodiments of the present application is to provide a dynamic path planning method, system and sweeper for a self-moving cleaning robot, to construct a response compensation mechanism of "grasping-area marking-compensation cleaning", and to achieve an integrated solution for obstacle removal, missed sweep compensation and cleaning path optimization.

[0006] In order to achieve the above-mentioned objectives, the first aspect of the present application provides a dynamic path planning method for a self-moving cleaning robot, which includes: generating an initial planned path; identifying removable target obstacles on the initial planned path, and removing the target obstacles through the removal components on the self-moving cleaning robot; determining a compensation cleaning area and a compensation cleaning path based on the position and size of the target obstacle; and topologically fusing the compensation cleaning path with the initial planned path to generate an updated planned path.

[0007] On the other hand, the present application provides a dynamic path planning system for a self-moving cleaning robot, wherein the self-moving cleaning robot includes a removal component, and the dynamic path planning system includes: a first path planning device for generating an initial planned path; an identification device for identifying removable target obstacles on the initial planned path during the cleaning process, and obtaining the position and size information of the target obstacle; a removal component control device for controlling the removal component to remove the target obstacle; a compensation area determination device for determining a compensation cleaning area according to the position and size of the target obstacle; a compensation path determination device for determining a compensation cleaning path located in the compensation cleaning area; and a second path planning device for topologically fusing the compensation cleaning path with the initial planned path to generate an updated planned path.

[0008] On the other hand, the present application provides a sweeping machine, which includes a removal component and a dynamic path planning system for a self-moving cleaning robot as described above.

[0009] Through the above technical solution, the present invention constructs a response compensation mechanism of "grasping-area marking-compensation cleaning" to realize closed-loop processing of missed scanning areas, which can reduce the area of ​​missed scanning areas, thereby realizing an integrated solution for obstacle removal, missed scanning compensation and cleaning path optimization.

[0010] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following detailed description, they are used to explain the embodiments of the present application but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0012] Figure 1 A schematic diagram of a flow chart of a dynamic path planning method for a self-moving cleaning robot according to an embodiment of the present application is shown;

[0013] Figures 2a-2c A schematic diagram of a compensation cleaning area of ​​a self-propelled cleaning robot according to an embodiment of the present application is shown;

[0014] Figure 3 A schematic diagram of the associated area construction of the self-moving cleaning robot according to an embodiment of the present application is shown;

[0015] Figure 4 A schematic diagram of the cleaning process of the self-propelled cleaning robot according to an embodiment of the present application is shown;

[0016] Figure 5A structural schematic diagram of a dynamic path planning system for a self-moving cleaning robot according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0017] To make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0018] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative position relationship, movement status, etc. between the various components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indications will also change accordingly.

[0019] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the fact that they can be implemented by ordinary technicians in this field. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0020] First, an embodiment of the present application provides a dynamic path planning method for a self-moving cleaning robot, such as a sweeping robot. Figure 1 As shown in the flowchart of FIG. 1 , the dynamic path planning method 100 may include steps S110 to S160:

[0021] Step S110: Generate an initial planning path and start cleaning. Figure 2a As shown, the initial planned path may include: a first arcuate path planned based on the improved ox plowing method.

[0022] Step S120 , identifying target obstacles on the initial planned path during the cleaning process, and obtaining the position and size information of the target obstacles.

[0023] In an embodiment of the present application, the self-moving cleaning robot can be equipped with a depth camera to collect three-dimensional information of the environment in real time, so as to identify and collect removable obstacles (such as shoes, toys, paper balls, and other preset categories) in the three-dimensional environment in real time, and identify the target obstacles according to the properties of the obstacles (size, material) according to the preset algorithm, and obtain the position and size information of the target obstacles.

[0024] In the embodiment of the present application, step S120 may include an energy consumption balancing strategy, specifically including the following steps S121-S123:

[0025] Step S121 , identifying obstacles on the initial planned path and estimating the weight of each obstacle.

[0026] Among them, the built-in visual recognition model can be used to identify removable obstacles on the initial planned path. For example, screenshots of graspable objects (i.e., removable obstacles, such as shoes, toys, paper balls, and other preset categories) can be pre-entered into the AI ​​visual recognition model for training and learning to obtain a visual recognition model with recognition accuracy that meets the requirements for identifying removable obstacles. This method can then calculate the relative grasping posture of the self-propelled cleaning robot corresponding to different types of removable obstacles, facilitating subsequent grasping and removal.

[0027] Step S122 : determining a set weight threshold that is positively correlated with the remaining power of the self-propelled cleaning robot.

[0028] Step S123: When the weight of an obstacle is less than a set weight threshold, the obstacle is determined as a target obstacle. For example, when the remaining power is less than 30%, the set weight threshold can be reduced from 400g to 300g.

[0029] Step S130: removing the target obstacle by using the removing component on the self-moving cleaning robot.

[0030] The removal component can be a robotic arm, which can leverage its active grasping capabilities to grab and remove the target obstacle. The autonomous cleaning robot can control the robotic arm's movements through a robotic arm control module. This module controls the robotic arm to invoke a pre-trained grasping strategy based on the object type to remove the target obstacle. For example, the robot can move the object to a temporary safe area and retract the robotic arm, or temporarily maintain the current grasping state if there is no safe area nearby.

[0031] In addition, after the global cleaning is completed, a topological map of the locations of grabbable items detected during the cleaning process can be created. The object sorting logic is then planned and executed, placing grabbable items in pre-set areas to achieve obstacle classification.

[0032] The self-propelled cleaning robot may also include a side brush. During the process of removing the target obstacle, the dynamic path planning method 100 of the present application may also include a motion coordination optimization mechanism, namely, maintaining the side brush's continuous rotation during the grasping action to prevent debris from spreading. This indicates that by developing a parallel coordination algorithm for the robot arm's motion and the cleaning path, motion time can be reduced.

[0033] Step S140: Determine a compensation cleaning area based on the location and size information of the target obstacle.

[0034] That is, after the robot arm grasping action is triggered, the dynamic path planning method 100 of the present application can also automatically generate a "marking area", such as Figure 2b As shown, it serves as the range for subsequent compensation cleaning. The size of the marked area can be configured according to actual conditions, and this application does not limit this.

[0035] In the embodiment of the present application, step S140 may include the following steps S141-S143:

[0036] Step S141: Determine the bounding rectangle of the target obstacle's projection on the ground based on the target obstacle's location and size information, where the sides of the bounding rectangle are parallel or perpendicular to the line of the initial planned path. Specifically, the bounding rectangle can be obtained in the following manner:

[0037] 1) First, define the point set of the target obstacle's projection figure on the ground as:

[0038] S={(x,y)∈R 2 |F(x,y)≤0}

[0039] Among them, F(x,y)=0 is the boundary of the figure, and F(x,y)<0 is the internal area.

[0040] 2) Draw x=min (x,y)∈S x y=min (x,y)∈S y

[0041] 3) The figure enclosed by the four lines is the desired circumscribed rectangle.

[0042] Step S142 : Enlarge the length and width of the circumscribed rectangle according to the expansion multiple, and determine an expanded rectangle that is collinear with the diagonal line of the circumscribed rectangle.

[0043] Step S143: Determine the expanded rectangle as the compensation cleaning area, wherein the expansion multiple can be 1-2.5, such as 1, 1.5, 2, or 2.5.

[0044] In addition, the dynamic path planning method may also include: when the remaining power of the self-moving cleaning robot is less than the set power, reducing the expansion multiple, thereby achieving an energy consumption balance strategy. For example, when the remaining power is <30%, the expansion multiple is reduced, thereby automatically reducing the compensation cleaning radius. For example, if the compensation cleaning area is a square, if the expansion multiple is reduced from 2 to 1, the radius of the inscribed circle of the compensation cleaning area is reduced from 30cm to 15cm. This dynamic area change mechanism can achieve an intelligent response to low power mode and extend the machine's battery life.

[0045] Step S150: determining a compensation cleaning path in the compensation cleaning area.

[0046] The compensation cleaning path may include: a second arcuate path based on the improved ox-plowing method or a spiral extension path centered on the removal point of the target obstacle. That is, a spiral extension path is generated with the grasping point as the center, such as Figure 2c As shown, the radius of the inscribed circle in the area where the spiral expansion path is located is R = the diameter of the grasped object × 1.5.

[0047] Step S160 , topologically fuse the compensated sweeping path with the initial planned path to generate an updated planned path.

[0048] In summary, the compensation cleaning mechanism of the present application realizes closed-loop processing of missed scanning areas by constructing a response mechanism of "grabbing-area marking-compensation cleaning", which can reduce the area of ​​missed scanning areas.

[0049] In the embodiment of the present application, step S160 may include the following steps S161-S163:

[0050] Step S161: Stop executing the initial planned path and determine the current position of the self-propelled cleaning robot. That is, freeze the current cleaning path and wait for the subsequent execution of a new planned path.

[0051] Step S162: determining a first shortest splicing point with the current position in the compensation cleaning path, and determining a second shortest splicing point with the compensation cleaning area in the initial planning path.

[0052] Step S163 : inserting a first compensation path segment between the current position and the first shortest splicing point, and inserting a second compensation path segment between the end point of the compensation cleaning path and the second shortest splicing point.

[0053] The above steps S162-S163 can realize the compensation path insertion. By calculating the shortest splicing point between the compensation path and the original path, the compensation path segment is inserted according to the above method and the transition is smoothed, so that the compensation cleaning path and the initial planning path are topologically merged to generate an updated planning path.

[0054] In another embodiment of the present application, step S160 may also include a path splicing algorithm to reduce redundant paths. Specifically, the following steps S164-S166 are included:

[0055] Step S164: When there are multiple target obstacles, determine whether there is a correlation between any two compensation cleaning areas based on the distance between the center points of any two compensation cleaning areas with continuous movement trajectories.

[0056] Step S165: When the distance between the center points of any two compensation cleaning areas with continuous moving trajectories is less than the set distance, it is determined that there is a correlation between the two compensation cleaning areas, and the two compensation cleaning areas are combined to generate a merged compensation cleaning area in a chain compensation manner.

[0057] That is, a regional correlation test is required to trigger the chained compensation cleaning logic. If the distance between the center points of any two compensation cleaning areas with continuous movement trajectories is less than a set distance (30-80cm, for example, 50cm), the two compensation cleaning areas are determined to be associated.

[0058] Among them, such as Figure 3 As shown, step S165 can be implemented by the following steps:

[0059] 1) Determine the two points with the greatest distance between the two compensation sweeping areas.

[0060] 2) Determine a rectangular area with a connecting line of two points as a diagonal line, wherein sides of the rectangular area are parallel or perpendicular to the line of the initial planned path.

[0061] 3) The rectangular area is determined as the merged compensation cleaning area.

[0062] Through the above steps, the two red compensation cleaning areas are merged into a blue compensation cleaning area.

[0063] In addition, determining whether there is a correlation between any two compensation cleaning areas having continuous movement trajectories according to the distance between the center points of the two compensation cleaning areas in step S165 may further include:

[0064] 1) Determine the pollution index for each compensation cleaning area based on the dynamic pollution prediction model. The pollution index is dynamically determined based on the real-time monitored pollution value and the historical cleaning times.

[0065] Among them, the above-mentioned dynamic pollution prediction model can output the pollution index based on the pollution value stored in each grid on the input map according to the built-in algorithm, and then find out whether there is a correlation between any two compensation cleaning areas based on the pollution index. Specifically, a high-resolution grid map (resolution accuracy such as 1cm) can be used to divide the map into multiple grids, and each grid can store the following state parameters: pollution value, obstacle height, historical cleaning times, grab operation marks and other information. Among them, the input of pollution values ​​can be through real-time pollution detection, that is, through the three high-frequency laser dust sensors installed on the bottom of the fuselage, real-time monitoring of changes in ground particulate matter concentration. At the same time, historical data can also be loaded, that is, reading the pollution heat map of the past n cleaning records of the area.

[0066] Dynamic weights can then be assigned to different area types, allowing the pollution index of the marked compensation area to be calculated and updated based on the dynamic pollution prediction model. For example, the pollution index of the compensation area is W = 1.2 × (pollution value / 100) + 0.3 × (historical cleaning times); while the pollution index of the regular area is W = 0.8 × (pollution value / 100).

[0067] 2) If the distance between the center points of any two compensating cleaning areas with continuous movement trajectories is less than a set distance and the difference in pollution index between the two compensating cleaning areas is less than a set threshold, it is determined that there is a correlation between the two compensating cleaning areas.

[0068] For example, when two compensation cleaning areas meet the following specific conditions: the distance is less than 50 cm, the pollution index difference is less than 30, and there is a continuous movement trajectory, it can be considered that there is a correlation between the two compensation cleaning areas.

[0069] In addition, based on the pollution prediction model, the pollution index of the marked compensation area can be calculated and updated, and high-risk areas (such as those around pet food bowls) can be marked in advance. At the same time, it supports user-defined compensation strategies (such as increasing the compensation radius of the children's toy area).

[0070] Step S166: generating a compensation cleaning path according to the merged compensation cleaning area, and topologically merging it with the initial planned path to generate an updated planned path.

[0071] The compensation cleaning path may include: an arcuate path or a spiral extension path centered on the removal point of the target obstacle. Figure 3 As shown, a new spiral extension path is generated in the blue area with the center point of the merged compensation sweeping area (blue area) as the center.

[0072] In addition, the workflow of the escape logic of the present invention can be found in Figure 4 , which may include:

[0073] 1) Start normal cleaning and detect whether there are any grabbable items on the cleaning path;

[0074] 2) Move the item to a safe area through the robotic arm control unit;

[0075] 3) Mark the center position and size of the compensation cleaning area according to the object size measurement module;

[0076] 4) Calculate the compensation cleaning path based on the area size and topologically integrate it with the original cleaning path;

[0077] 5) Perform compensatory cleaning and update the pollution index on the map in real time;

[0078] 6) Perform correlation detection on the compensation cleaning area and trigger chain compensation cleaning at the appropriate time;

[0079] 7) After the global cleaning is completed, a topological map of the locations of grabbable items detected during the cleaning process is created;

[0080] 8) Plan and execute item sorting logic to place grabbable items in pre-set areas.

[0081] Through the above technical solution, the beneficial effects of the present invention may include:

[0082] 1) Quantitative improvement of missed scanning rate: A response compensation mechanism of "grabbing - area marking - compensation cleaning" is established. The compensation mechanism reduces the area of ​​missed scanning, and the chain compensation can cover continuous contaminated belts.

[0083] 2) Efficiency optimization: Regional correlation detection triggers a chain-compensated cleaning algorithm for path splicing to reduce redundant paths. At the same time, the coordinated control of the robot arm motion and the cleaning path is developed to reduce the time consumption of the grasping action.

[0084] 3) Intelligent extension: Based on the pollution prediction model, the pollution index of the marked compensation area is calculated and updated, high-risk areas are marked in advance, and user-defined compensation strategies are supported.

[0085] On the other hand, the present application also provides a dynamic path planning system 200 for a self-moving cleaning robot, such as a sweeping robot, including a removal component. Figure 5 As shown in the structural diagram of FIG, the dynamic path planning system 200 may include:

[0086] The first path planning device 210 is used to generate an initial planned path.

[0087] The identification device 220 is used to identify removable target obstacles on the initial planned path during the cleaning process and obtain the position and size information of the target obstacles.

[0088] a removal component control device 230, configured to control the removal component to remove the target obstacle;

[0089] The compensation area determining device 240 is used to determine the compensation cleaning area according to the position and size of the target obstacle.

[0090] The compensation path determining device 250 is used to determine the compensation cleaning path located in the compensation cleaning area.

[0091] The second path planning device 260 is used to topologically fuse the compensation sweeping path with the initial planned path to generate an updated planned path.

[0092] Specifically, the dynamic path planning system 200 of the self-moving cleaning robot of the present invention may further include the following modules:

[0093] 1. Real-time raster map update engine

[0094] A high-resolution grid map (e.g., 1 cm) can be used, with each grid storing the following status parameters: {contamination value | obstacle height | historical cleaning times | grasping operation flag}. Once the robotic arm grasps, a "compensatory cleaning zone" (configurable in size) can be automatically generated.

[0095] The built-in dynamic pollution prediction model is used to output the pollution index. Its input includes:

[0096] 1) Real-time pollution detection: Three high-frequency laser dust sensors installed on the bottom of the fuselage monitor the changes in ground particulate matter concentration in real time

[0097] 2) Historical data loading: read the pollution heat map of the area's past n cleaning records

[0098] 3) Dynamic weight setting for different regions:

[0099] Compensation area weight W = 1.2 × (pollution index / 100) + 0.3 × (historical cleaning times)

[0100] Conventional area weight W = 0.8 × (pollution index / 100)

[0101] 2. Associated area calculation module

[0102] Regional correlation is established when two areas meet specific conditions: 1) the distance is less than 50 cm and the pollution index difference is less than 30; 2) there is a continuous movement trajectory.

[0103] 3. Dynamic generation algorithm of cleaning path

[0104] 1) Basic path generation: planning an arched path based on the improved ox-plowing method

[0105] 2) Compensation path insertion: When a grab operation is detected, execute:

[0106] ①Freeze the current cleaning path

[0107] ② Generate a spiral expansion path with the grasping point as the center (radius R = grasping object diameter × 1.5)

[0108] ③Calculate the shortest splicing point between the compensation path and the original path

[0109] ④Insert compensation path segments and smooth transition

[0110] 4. Robotic arm-cleaning collaborative controller

[0111] 1) Motion coordination optimization: Maintaining continuous rotation of the side brush during the grasping action (to prevent the spread of debris);

[0112] 2) Energy consumption balance strategy: When the remaining power is less than 30%, the compensation cleaning radius is automatically reduced (for example, from 30cm to 15cm), and the grab weight threshold is reduced from 400g to 300g.

[0113] In summary, the present invention aims to propose a dynamic path planning system for a self-propelled cleaning robot with integrated robotic arm grasping function, which has the following beneficial effects:

[0114] 1) Quantitative improvement of missed scanning rate: Build a response mechanism of "grabbing - area marking - compensation cleaning". The compensation mechanism reduces the area of ​​missed scanning, and chain compensation can cover continuous contaminated belts.

[0115] 2) Efficiency optimization: Regional correlation detection triggers a chain-compensated cleaning algorithm for path splicing to reduce redundant paths. At the same time, the coordinated control of the robot arm motion and the cleaning path is developed to reduce the time consumption of the grasping action.

[0116] 3) Intelligent extension: Based on the pollution prediction model, the pollution index of the marked compensation area is calculated and updated, high-risk areas are marked in advance, and user-defined compensation strategies are supported.

[0117] On the other hand, the present application also provides a sweeping machine, which may include a removal component and the dynamic path planning system of the self-moving cleaning robot described above.

[0118] Regarding the beneficial effects of the dynamic path planning system of a self-moving cleaning robot and the sweeping robot provided by the present invention, reference can be made to the above description of the dynamic path planning method of a self-moving cleaning robot, which will not be repeated here.

[0119] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0120] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A dynamic path planning method for a self-propelled cleaning robot, characterized in that: The dynamic path planning method comprises: Generate the initial planning path and start cleaning; During the cleaning process, target obstacles on the initial planned path are identified, and location and size information of the target obstacles are obtained; Removing the target obstacle by using a removal component on the self-moving cleaning robot; Determining a compensation cleaning area based on the location and size information of the target obstacle; determining a compensation sweeping path located in the compensation sweeping area; and The compensated sweeping path is topologically fused with the initial planned path to generate an updated planned path.

2. The dynamic path planning method according to claim 1, characterized in that: The initial planned path includes: a first arcuate path; The compensating cleaning path includes a second arcuate path or a spirally extended path centered on a removal point of the target obstacle.

3. The dynamic path planning method according to claim 1, characterized in that: Determining the compensation cleaning area based on the location and size information of the target obstacle includes: Determine, based on the position and size information of the target obstacle, a circumscribed rectangle of the projection shape of the target obstacle on the ground, wherein sides of the circumscribed rectangle are parallel or perpendicular to the line of the initial planned path; Expanding the length and width of the circumscribed rectangle according to the expansion multiple to determine an expanded rectangle that is collinear with the diagonal of the circumscribed rectangle; and The expanded rectangle is determined as the compensation sweeping area.

4. The dynamic path planning method according to claim 3, characterized in that: The dynamic path planning method further includes: reducing the expansion multiple when the remaining power of the self-moving cleaning robot is less than a set power.

5. The dynamic path planning method according to claim 1, characterized in that: The topologically fusing the compensation sweeping path with the initial planned path includes: Stopping execution of the initial planned path and determining a current position of the self-moving cleaning robot; Determining a first shortest splicing point with the current position in the compensation cleaning path, and determining a second shortest splicing point with the compensation cleaning area in the initial planned path; and A first compensation path segment is inserted between the current position and the first shortest splicing point, and a second compensation path segment is inserted between the end point of the compensation cleaning path and the second shortest splicing point.

6. The dynamic path planning method according to claim 1, characterized in that: The topologically fusing the compensation sweeping path with the initial planned path includes: In the case where there are multiple target obstacles, determining whether there is a correlation between any two compensation cleaning areas having continuous movement trajectories according to the distance between the center points of the two compensation cleaning areas; When the distance between the center points of any two compensating sweeping areas with continuous moving trajectories is less than a set distance, determining that there is a correlation between the two compensating sweeping areas, and generating a merged compensating sweeping area by chain-compensating the two compensating sweeping areas; and A compensation sweeping path is generated according to the merged compensation sweeping area, and is topologically fused with the initial planned path to generate an updated planned path.

7. The dynamic path planning method according to claim 6, characterized in that: Generating a merged compensation sweeping area by chain-compensating the two compensation sweeping areas includes: Determine two points in the two compensation sweeping areas that are farthest apart; Determine a rectangular area with a line connecting the two points as a diagonal line, wherein sides of the rectangular area are parallel or perpendicular to the line of the initial planned path; and The rectangular area is determined as the merged compensation cleaning area.

8. The dynamic path planning method according to claim 6, characterized in that: The determining, based on the distance between the center points of any two compensation cleaning areas having continuous movement trajectories, whether there is a correlation between the two compensation cleaning areas further includes: Determining a pollution index for each compensation cleaning area based on a dynamic pollution prediction model, wherein the pollution index is dynamically determined based on real-time monitored pollution values ​​and historical cleaning times; and When the distance between the center points of any two compensating cleaning areas with continuous movement trajectories is less than a set distance and the pollution index difference between the two compensating cleaning areas is less than a set threshold, it is determined that there is a correlation between the two compensating cleaning areas.

9. The dynamic path planning method according to claim 1, characterized in that: The self-propelled cleaning robot includes a side brush. During the process of removing the target obstacle, the dynamic path planning method further includes: maintaining the side brush in continuous rotation.

10. The dynamic path planning method according to claim 1, characterized in that: The removal component is a robotic arm, configured to grab the target obstacle to remove the target obstacle, wherein the step of identifying the removable target obstacle on the initial planned path includes: identifying obstacles on the initial planned path and estimating the weight of each obstacle; determining a set weight threshold value that is positively correlated with the remaining power of the self-propelled cleaning robot; and When the weight of an obstacle is less than the set weight threshold, the obstacle is determined as a target obstacle.

11. A dynamic path planning system for a self-propelled cleaning robot, the self-propelled cleaning robot including a removal component, characterized in that: The dynamic path planning system includes: A first path planning device, configured to generate an initial planned path; an identification device for identifying removable target obstacles on the initial planned path during the cleaning process and obtaining position and size information of the target obstacles; a removal component control device, configured to control the removal component to remove the target obstacle; a compensation area determining device, configured to determine a compensation cleaning area according to the position and size of the target obstacle; a compensation path determining device for determining a compensation cleaning path located in the compensation cleaning area; and The second path planning device is used to topologically fuse the compensation sweeping path with the initial planned path to generate an updated planned path.

12. A sweeping machine, characterized in that: The invention comprises a removal component and a dynamic path planning system for a self-moving cleaning robot according to claim 11.

Images