Cooperative task dynamic allocation method and system for multi-robot decontamination

Abstract

The invention discloses a cooperative task dynamic allocation method and system for multi-robot decontamination, and relates to the technical field of robot cooperative decontamination, and the method comprises the steps: dividing a target region, obtaining each target sub-region, determining the standby position of each decontamination robot, obtaining the decontamination feature information of each target sub-region, and obtaining the decontamination feature information of each target sub-region; the method comprises the following steps: acquiring a target decontamination sub-region, analyzing to obtain a target decontamination sub-region, acquiring decontamination feature information and historical decontamination information of each adjacent region of the target decontamination sub-region, analyzing to obtain each decontamination robot corresponding to the target decontamination sub-region, and performing path planning on each decontamination robot of the target decontamination sub-region. According to the invention, real-time monitoring and real-time decontamination of the target area are realized, timeliness and decontamination efficiency of water area decontamination are improved, balance of timeliness of single-area decontamination and timeliness of global decontamination is realized, and optimization of a multi-robot scheduling scheme is ensured.

Description

Technical Field

[0001] This invention relates to the field of robot collaborative cleaning technology, specifically to a method and system for dynamic allocation of collaborative tasks for multi-robot cleaning. Background Technology

[0002] With the rapid increase in population and the continuous improvement of per capita consumption levels, domestic waste and algae have become major sources of pollution in rivers and lakes. The increasing amount of pollution pollutes water quality, and in some waters, aquatic plants are root-borne plants that need to be cut and collected once they grow to a certain height to maintain the aquatic ecosystem. Using traditional manual methods for dredging or cutting is not only inefficient but also poses certain risks to the personnel involved. As pollution control measures for rivers and lakes become increasingly stringent, floating debris can no longer be easily discharged downstream. Therefore, safe, efficient, and intelligent methods for cleaning up floating debris will be a long-term necessity.

[0003] The current technology still has some shortcomings when using robots to clean up water surface debris. Specifically, it is reflected in the following aspects: (1) In the current technology, when using robots to clean up water surface debris, the cleaning path of the robot is mostly obtained through path planning algorithm, and then the water surface is cleaned based on the cleaning path. The standby position of the robot is not analyzed and optimized, and the power consumption and wear caused by the robot's round-trip path are not considered.

[0004] (2) Current technologies mostly analyze the allocation of collaborative work content when multiple robots work together. When multiple robots work together on a certain part of the water area, the waiting time for cleaning other parts of the water area may be too long due to problems such as the length of operation and the round-trip path. When multiple robots traverse the water area, energy may be wasted due to ineffective cleaning. Summary of the Invention

[0005] To address the aforementioned technical shortcomings, the present invention aims to provide a method and system for dynamic allocation of collaborative tasks in multi-robot cleaning.

[0006] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: In the first aspect, the present invention provides a collaborative task dynamic allocation method for multi-robot cleaning, including: Step 1, dividing the target area to obtain each target sub-area, then determining the standby position of each cleaning robot, and obtaining the cleaning feature information of each target sub-area, thereby analyzing whether to clean each target sub-area.

[0007] Step 2: Obtain the cleaning characteristics and historical cleaning information of each adjacent target sub-region of the target cleaning sub-region, and then analyze and obtain the cleaning robots corresponding to the target cleaning sub-region.

[0008] Step 3: Perform path planning for each cleaning robot in the target cleaning sub-area.

[0009] In a second aspect, the present invention provides a collaborative task dynamic allocation system for multi-robot cleaning, comprising: a cleaning area division module: used to divide the target area to obtain each target sub-area, thereby determining the standby position of each cleaning robot, and obtaining the cleaning feature information of each target sub-area, thereby analyzing whether to clean each target sub-area.

[0010] Cleaning robot analysis module: used to obtain the cleaning feature information and historical cleaning information of each adjacent target sub-region of the target cleaning sub-region, and then analyze and obtain the cleaning robots corresponding to the target cleaning sub-region.

[0011] Cleaning path planning module: Used to plan the paths for each cleaning robot in the target cleaning sub-area.

[0012] The beneficial effects of the present invention are as follows: (1) By dividing the target area, the present invention clarifies the standby position of each cleaning robot and the cleaning area it is responsible for, which solves the problems of blurred cleaning area boundaries and disordered robot standby in the prior art. At the same time, it avoids the energy consumption and repetitive operation problems caused by frequent back-and-forth of cleaning robots. It can achieve real-time monitoring and real-time cleaning of the target area, which greatly improves the timeliness and cleaning efficiency of water area cleaning.

[0013] (2) This invention analyzes the cleaning waiting time of each adjacent sub-region in the target area, and then obtains a combination of cleaning robots under multiple constraints. This avoids the problems of excessive cleaning and cleaning delay in the current technology, and also achieves a balance between the timeliness of single-area cleaning and global cleaning. It avoids the situation of multiple robots being idle or having conflicting tasks. This not only ensures the optimization of the multi-robot scheduling scheme, but also improves the scientific nature of the cleaning priority determination. Attached Figure Description

[0014] 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, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 This is a schematic diagram of the implementation steps of the method of the present invention.

[0016] Figure 2 This is a schematic diagram of the system structure connection of the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Reference Figure 1 As shown, the present invention provides a method for dynamic allocation of collaborative tasks for multi-robot cleaning in a first aspect, including: Step 1, dividing the target area to obtain each target sub-area, then determining the standby position of each cleaning robot, and obtaining the cleaning feature information of each target sub-area, thereby analyzing whether to clean each target sub-area.

[0019] In a specific example, the target area is divided into target cleaning sub-areas, and the standby position of each cleaning robot is determined. The specific analysis process is as follows: the target area is divided into grids according to the preset horizontal and vertical diameters, and each grid area in the target area is obtained. Each grid area is recorded as a target sub-area, and the intersection of each grid is taken as the standby position of each cleaning robot.

[0020] It should be noted that the target area includes water areas such as rivers and lakes.

[0021] It should be noted that the specific values ​​of the transverse and longitudinal diameters are set by the relevant personnel based on the total area of ​​the target area and the navigation information of the cleaning robot, and no specific restrictions are imposed here. The navigation information includes the cleaning robot's travel speed and working distance.

[0022] In a specific example, the process of acquiring the cleaning and pollution characteristic information of each target sub-region to analyze whether to clean each target sub-region is as follows: The cleaning and pollution characteristic information of each target sub-region is collected in real time by the deployed sensing devices and transmitted to the central control and monitoring center. The cleaning and pollution characteristic information includes water surface information and aquatic biological information. Then, the cleaning and pollution characteristic information of each target sub-region is compared with the set cleaning and pollution trigger information. When the cleaning and pollution characteristic information of a target sub-region reaches the set cleaning and pollution trigger information, the target sub-region is recorded as a target cleaning and pollution sub-region and cleaning is carried out on the target sub-region. Otherwise, the target sub-region is not cleaned and continuous monitoring is carried out.

[0023] It should be noted that the various sensing devices include high-definition cameras, drones, and underwater visual samplers deployed in the target area, as well as infrared thermal imagers, lidar, and visible light cameras deployed on the body of the cleaning robot.

[0024] It should be noted that surface appearance information includes the coverage area and distribution density of floating debris such as domestic waste and aquatic plant remains on the water surface; aquatic biological information includes the growth area, distribution density, and growth height of aquatic plants on the bottom of the water.

[0025] It should also be noted that the cleaning trigger information is the baseline value for determining whether each cleaning robot should perform cleaning. This value can be set by the relevant personnel. For example, the cleaning trigger information can be set to indicate that the coverage area of ​​floating objects on the water surface is 3% of the corresponding target sub-area, and the distribution density is 1.0 objects / m². 2 When the area covered by floating objects on the water surface of a target sub-area is detected to be 3% of the target sub-area, cleaning is performed on the target sub-area because the area covered by floating objects on the water surface of the target sub-area has reached the set cleaning trigger information.

[0026] Step 2: Obtain the cleaning characteristics and historical cleaning information of each adjacent target sub-region of the target cleaning sub-region, and then analyze and obtain the cleaning robots corresponding to the target cleaning sub-region.

[0027] In a specific example, the process of obtaining the cleaning characteristic information and historical cleaning information of each adjacent target sub-region of the target cleaning sub-region, and then analyzing and obtaining the cleaning robots corresponding to the target cleaning sub-region, is as follows: Obtain the grid intersections of the grids that make up the target cleaning sub-region; record the cleaning robots waiting at each grid intersection as the candidate cleaning robots of the target cleaning sub-region; simultaneously obtain the other target sub-regions besides the target cleaning sub-region where each grid intersection is located; analyze and obtain the cleaning waiting time of the other target sub-regions based on the cleaning characteristic information and historical cleaning information of the other target sub-regions; simultaneously obtain the combinations of cleaning robots corresponding to the target cleaning sub-region based on the candidate cleaning robots of the target cleaning sub-region; then analyze and obtain the cleaning time of the target cleaning sub-region corresponding to each combination of cleaning robots; and finally, based on the cleaning waiting time of the other target sub-regions and the cleaning time of the target cleaning sub-region corresponding to each combination of cleaning robots, comprehensively analyze and obtain the target cleaning robot combination corresponding to the target cleaning sub-region.

[0028] It should be noted that the target cleaning robot assembly includes one or more cleaning robots.

[0029] In a specific example, the cleaning waiting time of the remaining target sub-regions is analyzed based on the cleaning and decontamination characteristic information and historical cleaning and decontamination information of the remaining target sub-regions. The specific analysis is as follows: the historical cleaning and decontamination interval of each of the remaining target sub-regions is obtained from the historical cleaning and decontamination information of the remaining target sub-regions, and then the average value of the historical cleaning and decontamination interval of each of the remaining target sub-regions is calculated. The waiting time from the last cleaning time to the current time of each of the remaining target sub-regions is obtained. The difference between the average value of the historical cleaning and decontamination interval of each of the remaining target sub-regions and the waiting time from the last cleaning time to the current time is recorded as the second type of reference value of the cleaning and decontamination waiting time of the remaining target sub-regions. When the difference between the average value of the historical cleaning and decontamination interval of each of the remaining target sub-regions and the waiting time from the last cleaning time to the current time is negative, the first type of reference value is recorded as 0.

[0030] Then, using the pollution change rate model: The waiting time required for the cleaning and decontamination feature information of each of the remaining target sub-regions to reach the set cleaning and decontamination trigger information is calculated and recorded as a reference value for the cleaning and decontamination waiting time of each of the remaining target sub-regions. Here, T is the waiting time required for the cleaning and decontamination feature information to reach the set cleaning and decontamination trigger information, X1 is the cleaning and decontamination trigger information, X2 is the cleaning and decontamination feature information, and K is the unit time growth rate of the cleaning and decontamination feature information.

[0031] It should be noted that the pollution control characteristics information of a target sub-region monitored within one week is retrieved, and then the unit time growth rate of the pollution control characteristics information of the target sub-region is calculated.

[0032] For all other target sub-regions with a reference value of 0, the cleaning waiting time is set to 0. For all other target sub-regions with a reference value that is not 0, the cleaning waiting time for each target sub-region is obtained by weighted summing of the reference values ​​for both the first and second categories. The weighted summation formula is as follows: .

[0033] In a specific example, the process involves simultaneously obtaining the combinations of cleaning robots corresponding to the target cleaning sub-region based on each candidate cleaning robot for the target cleaning sub-region, and then analyzing the cleaning time of each cleaning robot combination for the target cleaning sub-region. The specific analysis process is as follows: the area of ​​the target cleaning sub-region and the standard cleaning speed of the cleaning robots are obtained from the central monitoring center, and then the time required for the cleaning robots to traverse the target cleaning sub-region is calculated, which is recorded as the cleaning time of each cleaning robot combination for the target cleaning sub-region.

[0034] For example, if the cleaning robots corresponding to the target cleaning sub-area are A, B, and C, then the alternative cleaning robot combinations corresponding to the target cleaning sub-area are: combination 1 (A), combination 2 (B), combination 3 (C), combination 4 (A), combination 5 (A, B), combination 6 (A, B, C), combination 7 (A, C), and combination 8 (B, C).

[0035] In a specific example, the process of comprehensively analyzing the cleaning waiting time of each other target sub-region and the cleaning time of each cleaning robot combination corresponding to the target cleaning sub-region to obtain the target cleaning robot combination corresponding to the target cleaning sub-region is as follows: any cleaning robot combination corresponding to the target cleaning sub-region is denoted as the cleaning robot combination to be analyzed. The cleaning waiting time of each cleaning robot in the cleaning robot combination to be analyzed corresponding to each other target sub-region is compared with the cleaning time of the cleaning robot combination to be analyzed corresponding to the target cleaning sub-region. If the cleaning waiting time of each cleaning robot in the cleaning robot combination to be analyzed corresponding to each other target sub-region is greater than the cleaning time of the cleaning robot combination to be analyzed corresponding to the target cleaning sub-region, then the cleaning robot combination to be analyzed is denoted as the candidate cleaning robot combination of the target cleaning sub-region, and the candidate cleaning robot combinations of the target cleaning sub-region are obtained accordingly.

[0036] When the number of candidate cleaning robot combinations for the target cleaning sub-area is 0, the candidate cleaning robot combination with the largest number of cleaning robots is recorded as the target cleaning robot combination for the target cleaning sub-area. When the number of candidate cleaning robot combinations for the target cleaning sub-area is 1, the candidate cleaning robot combination is recorded as the target cleaning robot combination for the target sub-area.

[0037] When the number of candidate cleaning robot combinations for the target cleaning sub-region is greater than 1, obtain the minimum cleaning waiting time for each cleaning robot in each candidate cleaning robot combination for each other target sub-region, and record it as the feature value of each candidate cleaning robot combination. Record the candidate cleaning robot combination corresponding to the maximum feature value as the target cleaning robot combination for the target cleaning sub-region.

[0038] It should be noted that when the number of candidate cleaning robot combinations corresponding to the largest feature value is greater than 1, the target cleaning robot combinations of the target cleaning sub-region will be merged to obtain the unique target cleaning robot combination of the target cleaning sub-region.

[0039] Step 3: Perform path planning for each cleaning robot in the target cleaning sub-area.

[0040] In a specific example, the path planning for each cleaning robot in the target cleaning sub-area is as follows: the number of cleaning robots in the target cleaning robot combination is obtained. When the number of cleaning robots in the target cleaning robot combination is 1, the target sub-area is cleaned based on the collaborative cleaning mode. Specifically, a rectangular coordinate system is constructed with the standby position of the cleaning robot as the origin, and then the boundary coordinates of the target sub-area are determined. The shortest traversal path is selected based on the genetic algorithm, and the target sub-area is cleaned with the water flow direction as the path direction.

[0041] When the target cleaning robot combination is the candidate cleaning robot combination with the largest number of cleaning robots, the number of candidate cleaning robot combinations in the target cleaning sub-region is obtained. If the number of candidate cleaning robot combinations in the target cleaning sub-region is 0, the target sub-region is cleaned based on the partition cleaning mode. Specifically, the target cleaning sub-region is divided equally according to the number of cleaning robots to obtain the cleaning area responsible for each cleaning robot. A teaching coordinate system is established with the standby position of each cleaning robot as the origin, and then the boundary coordinates of the cleaning area responsible for each cleaning robot are determined. The shortest traversal path corresponding to each cleaning robot is obtained based on the genetic algorithm, and the target sub-region is cleaned with the water flow direction as the path direction. If the number of candidate cleaning robot combinations in the target cleaning sub-region is not 0, the cleaning mode of each cleaning robot in the target cleaning robot combination is analyzed and the path traversal of the target cleaning sub-region is performed based on the cleaning mode.

[0042] When the number of cleaning robots in the target cleaning robot combination is not 1, and the target cleaning robot combination is not the candidate cleaning robot combination with the largest number of cleaning robots, the cleaning mode of each cleaning robot in the target cleaning robot combination is analyzed, and the path traversal of the target cleaning sub-region is performed based on the cleaning mode.

[0043] In a specific example, the analysis yields the cleaning mode of each cleaning robot in the target cleaning robot group. The specific analysis process is as follows: The remaining power of each cleaning robot in the target cleaning robot group is compared with a set power threshold. If the remaining power of each cleaning robot in the target cleaning robot group is greater than or equal to the set power threshold, a collaborative cleaning mode is adopted to clean the target cleaning sub-area; otherwise, a partitioned cleaning mode is adopted to clean the target sub-area.

[0044] It should be noted that the power threshold is the power consumed by the cleaning robot when traversing the target cleaning sub-area with the highest cleaning power consumption and without path repetition.

[0045] It should be noted that the cleaning mode is divided into collaborative cleaning mode and zoned cleaning mode. When the number of cleaning robots is greater than 1 in collaborative cleaning mode, the cleaning content of each cleaning robot is assigned. For example, when there are 2 cleaning robots corresponding to the target sub-area, one cleaning robot is responsible for mowing the grass and the other cleaning robot is responsible for dredging.

[0046] Reference Figure 2 As shown, in a second aspect, the present invention provides a collaborative task dynamic allocation system for multi-robot cleaning, comprising: a cleaning area division module: used to divide the target area to obtain each target sub-area, thereby determining the standby position of each cleaning robot, and obtaining the cleaning feature information of each target sub-area, thereby analyzing whether to clean each target sub-area.

[0047] Cleaning robot analysis module: used to obtain the cleaning feature information and historical cleaning information of each adjacent target sub-region of the target cleaning sub-region, and then analyze and obtain the cleaning robots corresponding to the target cleaning sub-region.

[0048] Cleaning path planning module: Used to plan the paths for each cleaning robot in the target cleaning sub-area.

[0049] It should be noted that the cleaning robot in this invention also possesses functions such as autonomous identification, detection, and searching for floating objects on the water surface; accurate identification, positioning, and tracking of objects for autonomous obstacle avoidance; intelligent speed-controlled garbage collection; automatic return when low battery is reached; and monitoring alarms. This enables unmanned driving and intelligent control of floating object retrieval operations. The cleaning robot is equipped with a hydrological monitoring system for real-time monitoring of hydrological, water quality, and meteorological data, and can also provide underwater terrain surveys and topographic mapping of the waterway the robot traverses. It is also equipped with a rescue device for detecting and monitoring rescueable objects, and for implementing rescue operations and deploying rescue equipment. Furthermore, it is equipped with a multimedia system for executing relevant lighting, audio-visual playback, and water curtain laser video playback according to set effects. Users can adjust the system settings according to their needs to display diverse effects.

[0050] The examples described in this invention are not limited to the specific embodiments listed above. The examples are merely illustrative to facilitate understanding of the invention and do not constitute a limitation on the scope of protection of this invention. Any modifications, equivalent substitutions, etc., made within the spirit and principles of this invention should be included within the scope of protection.

[0051] The above description is merely an example and illustration of the concept of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described or use similar methods to replace them, as long as they do not deviate from the concept of the invention or exceed the scope defined in this specification, they should all fall within the protection scope of the present invention.

Claims

1. A method and system for dynamic allocation of collaborative tasks in multi-robot cleaning, characterized in that, Includes the following steps: Step 1: Divide the target area into sub-regions, determine the standby position of each cleaning robot, and obtain the cleaning characteristics of each sub-region to analyze whether to clean each sub-region. Step 2: Obtain the cleaning characteristics and historical cleaning information of each adjacent target sub-region of the target cleaning sub-region, and then analyze and obtain the cleaning robots corresponding to the target cleaning sub-region; Step 3: Perform path planning for each cleaning robot in the target cleaning sub-area.

2. The collaborative task dynamic allocation method and system for multi-robot cleaning as described in claim 1, characterized in that, The target area is divided into target cleaning sub-areas, and then the standby position of each cleaning robot is determined. The specific analysis process is as follows: The target area is divided into grids according to the preset horizontal and vertical diameters, thus obtaining each grid area in the target area. Each grid area is recorded as a target sub-area, and the intersection of each grid is used as the standby position of each cleaning robot.

3. The collaborative task dynamic allocation method and system for multi-robot cleaning as described in claim 2, characterized in that, The process of acquiring the cleaning and decontamination characteristic information of each target sub-region to analyze whether to clean each target sub-region is as follows: The system collects the cleanliness and pollution characteristics of each target sub-region in real time through various deployed sensors and transmits this information to the central control and monitoring center. The cleanliness and pollution characteristics include water surface appearance information and aquatic organism information. The system then compares the cleanliness and pollution characteristics of each target sub-region with the set cleanliness and pollution trigger information. When the cleanliness and pollution characteristics of a target sub-region reach the set cleanliness and pollution trigger information, the target sub-region is marked as a target cleanliness and pollution sub-region and cleanliness and pollution are carried out on the target sub-region. Otherwise, the target sub-region is not cleaned and is continuously monitored.

4. The collaborative task dynamic allocation method and system for multi-robot cleaning as described in claim 3, characterized in that, The process involves acquiring the cleaning characteristic information and historical cleaning information of each adjacent target sub-region of the target cleaning sub-region, and then analyzing the cleaning robots corresponding to the target cleaning sub-region. The specific analysis process is as follows: The process involves obtaining the intersection points of each grid that makes up the target cleaning sub-region, and marking each cleaning robot waiting at each grid intersection as a candidate cleaning robot for the target cleaning sub-region. Simultaneously, it involves obtaining the other target sub-regions (excluding the target cleaning sub-region) where each grid intersection is located. Based on the cleaning characteristic information and historical cleaning information of the other target sub-regions, the cleaning waiting time for each of the other target sub-regions is analyzed. Furthermore, based on the candidate cleaning robots for the target cleaning sub-region, the process involves obtaining the corresponding combinations of cleaning robots for each target cleaning sub-region, and then analyzing the cleaning time for each robot combination corresponding to the target cleaning sub-region. Finally, based on the cleaning waiting time for each of the other target sub-regions and the cleaning time for each robot combination corresponding to the target cleaning sub-region, a comprehensive analysis is performed to obtain the target cleaning robot combination for the target cleaning sub-region.

5. The collaborative task dynamic allocation method and system for multi-robot cleaning as described in claim 4, characterized in that, Based on the cleaning characteristics and historical cleaning information of the remaining target sub-regions, the cleaning waiting time of each target sub-region is analyzed and obtained, as detailed below: The historical cleaning interval duration of each target sub-region is obtained from the historical cleaning information of each target sub-region. The average value of the historical cleaning interval duration of each target sub-region is then calculated. The waiting time from the last cleaning time to the current time of each target sub-region is also obtained. The difference between the average value of the historical cleaning interval duration of each target sub-region and the waiting time from the last cleaning time to the current time is recorded as the second type of reference value of the cleaning waiting time of each target sub-region. When the difference between the average value of the historical cleaning interval duration of each target sub-region and the waiting time from the last cleaning time to the current time is negative, the first type of reference value is recorded as 0. Then, using the pollution change rate model: The waiting time required for the cleaning and decontamination characteristic information of each of the remaining target sub-regions to reach the set cleaning and decontamination trigger information is calculated and denoted as a reference value for the cleaning and decontamination waiting time of each of the remaining target sub-regions, where T is the waiting time required for the cleaning and decontamination characteristic information to reach the set cleaning and decontamination trigger information. This is a message triggered by the cleaning process. For the characteristics of the pollution, The rate of increase of the pollution characteristics information per unit time; For all other target sub-regions with a reference value of 0, the cleaning waiting time is set to 0. For all other target sub-regions with a reference value that is not 0, the cleaning waiting time for each target sub-region is obtained by weighted summing of the reference values ​​for both the first and second categories. The weighted summation formula is as follows: .

6. The collaborative task dynamic allocation method and system for multi-robot cleaning as described in claim 5, characterized in that, Simultaneously, based on the candidate cleaning robots for each target cleaning sub-region, the robot combinations corresponding to the target cleaning sub-region are obtained, and then the cleaning time for each robot combination corresponding to the target cleaning sub-region is analyzed. The specific analysis process is as follows: The area of ​​the target cleaning sub-region and the standard cleaning speed of the cleaning robot are obtained from the central monitoring center. The time required for the cleaning robot to traverse the target cleaning sub-region is then calculated and recorded as the cleaning time for each combination of cleaning robots corresponding to the target cleaning sub-region.

7. The collaborative task dynamic allocation method and system for multi-robot cleaning as described in claim 6, characterized in that, Based on the cleaning waiting time of each other target sub-region and the cleaning time of each cleaning robot combination corresponding to the target cleaning sub-region, the target cleaning robot combination corresponding to the target cleaning sub-region is obtained through comprehensive analysis. The specific analysis process is as follows: Any combination of cleaning robots corresponding to the target cleaning sub-region is denoted as the cleaning robot combination to be analyzed. The cleaning waiting time of each cleaning robot in the cleaning robot combination to be analyzed for the other target sub-regions is compared with the cleaning time of the cleaning robot combination to be analyzed for the target cleaning sub-region. If the cleaning waiting time of each cleaning robot in the cleaning robot combination to be analyzed for the other target sub-regions is greater than the cleaning time of the cleaning robot combination to be analyzed for the target cleaning sub-region, then the cleaning robot combination to be analyzed is denoted as the candidate cleaning robot combination for the target cleaning sub-region. Based on this, the candidate cleaning robot combinations for the target cleaning sub-region are obtained. When the number of candidate cleaning robot combinations for the target cleaning sub-area is 0, the candidate cleaning robot combination with the largest number of cleaning robots is recorded as the target cleaning robot combination for the target cleaning sub-area. When the number of candidate cleaning robot combinations for the target cleaning sub-area is 1, the candidate cleaning robot combination is recorded as the target cleaning robot combination for the target sub-area. When the number of candidate cleaning robot combinations for the target cleaning sub-region is greater than 1, obtain the minimum cleaning waiting time for each cleaning robot in each candidate cleaning robot combination for each other target sub-region, and record it as the feature value of each candidate cleaning robot combination. Record the candidate cleaning robot combination corresponding to the maximum feature value as the target cleaning robot combination for the target cleaning sub-region.

8. The collaborative task dynamic allocation method and system for multi-robot cleaning as described in claim 7, characterized in that, The specific process for path planning for each cleaning robot in the target cleaning sub-area is as follows: Obtain the number of cleaning robots in the target cleaning robot combination. When the number of cleaning robots in the target cleaning robot combination is 1, clean the target sub-region based on the collaborative cleaning mode. Specifically, a rectangular coordinate system is constructed with the standby position of the cleaning robot as the origin, and then the boundary coordinates of the target sub-region are determined. The shortest traversal path is selected based on the genetic algorithm, and the target sub-region is cleaned with the water flow direction as the path direction. When the target cleaning robot combination is the candidate cleaning robot combination with the largest number of cleaning robots, the number of candidate cleaning robot combinations in the target cleaning sub-region is obtained. If the number of candidate cleaning robot combinations in the target cleaning sub-region is 0, the target sub-region is cleaned based on the partition cleaning mode. Specifically, the target cleaning sub-region is divided equally according to the number of cleaning robots to obtain the cleaning area responsible for each cleaning robot. A teaching coordinate system is established with the standby position of each cleaning robot as the origin, and then the boundary coordinates of the cleaning area responsible for each cleaning robot are determined. The shortest traversal path corresponding to each cleaning robot is obtained based on the genetic algorithm, and the target sub-region is cleaned with the water flow direction as the path direction. If the number of candidate cleaning robot combinations in the target cleaning sub-region is not zero, the cleaning mode of each cleaning robot in the target cleaning robot combination is analyzed, and the target cleaning sub-region is traversed based on the cleaning mode. When the number of cleaning robots in the target cleaning robot combination is not 1, and the target cleaning robot combination is not the candidate cleaning robot combination with the largest number of cleaning robots, the cleaning mode of each cleaning robot in the target cleaning robot combination is analyzed, and the path traversal of the target cleaning sub-region is performed based on the cleaning mode.

9. The collaborative task dynamic allocation method and system for multi-robot cleaning as described in claim 8, characterized in that, The analysis yielded the cleaning modes of each cleaning robot in the target cleaning robot assembly. The specific analysis process is as follows: The remaining battery power of each cleaning robot in the target cleaning robot group is compared with the set battery power threshold. If the remaining battery power of each cleaning robot in the target cleaning robot group is greater than or equal to the set battery power threshold, the collaborative cleaning mode is adopted to clean the target cleaning sub-area. Otherwise, the partitioned cleaning mode is adopted to clean the target sub-area.

10. A system executed using the collaborative task dynamic allocation method for multi-robot cleaning as described in any one of claims 1-9, characterized in that, include: Cleaning area division module: used to divide the target area into target sub-areas, thereby determining the standby position of each cleaning robot and obtaining the cleaning feature information of each target sub-area, so as to analyze whether to clean each target sub-area; Cleaning robot analysis module: used to obtain the cleaning feature information and historical cleaning information of each adjacent target sub-region of the target cleaning sub-region, and then analyze and obtain the cleaning robots corresponding to the target cleaning sub-region; Cleaning path planning module: Used to plan the paths for each cleaning robot in the target cleaning sub-area.

Images