Cleaning robot multi-machine collaboration method, device, equipment, medium and program product

Abstract

The present application discloses a method, device, equipment, medium and program product for multi-machine collaboration of cleaning robots, which relates to the field of robot collaboration technology. The multi-machine collaboration method of cleaning robots includes: obtaining the time series data of the stain map of the site to be cleaned; dividing the site to be cleaned into multiple periodic cleaning areas according to the time series data of the stain map; generating a multi-machine collaboration strategy according to the multiple periodic cleaning areas, and controlling multiple cleaning robots to perform collaborative cleaning operations on the site to be cleaned based on the multi-machine collaboration strategy. The present application realizes the collaborative control of multiple cleaning robots based on the dynamic division of periodic cleaning areas, solves the problem in the prior art that the cleaning robots have insufficient adaptability and cannot guarantee the quality of collaborative cleaning during the multi-machine collaboration process, and improves the cleaning efficiency and cleanliness of the multi-machine cleaning collaboration.

Description

Technical Field

[0001] The present application relates to the technical field of cleaning robot collaboration, and in particular to a method, device, equipment, medium and program product for multi-machine collaboration of cleaning robots. Background Art

[0002] With the development of robotics technology, cleaning robots have become a common equipment for environmental cleaning. The demand for collaborative cleaning using multiple cleaning robots in large-space cleaning scenarios is increasing. Existing multi-cleaning robot collaborative cleaning will assign cleaning areas to the cleaning robots.

[0003] However, in existing multi-robot collaborative solutions, each cleaning robot usually works independently in its own cleaning area, lacks effective collaborative response capabilities, and cannot guarantee the cleaning quality of collaborative cleaning operations by multiple cleaning robots.

[0004] The above content is only used to assist in understanding the technical solution of this application and does not constitute an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of this application is to provide a cleaning robot multi-machine collaboration method, device, equipment, medium and program product, aiming to solve the technical problem that the existing cleaning robots have insufficient adaptability during the multi-machine collaboration process and cannot guarantee the quality of collaborative cleaning.

[0006] To achieve the above objectives, the present application proposes a multi-machine collaboration method for cleaning robots, which is applied to a multi-machine collaboration platform for robots, wherein the multi-machine collaboration platform is communicatively connected with multiple cleaning robots, and the multi-machine collaboration method for cleaning robots includes:

[0007] Obtaining time series data of the pollution map of the site to be cleaned;

[0008] Dividing the site to be cleaned into a plurality of periodic cleaning areas according to the stain map time series data;

[0009] A multi-machine cooperation strategy is generated according to the multiple periodic cleaning areas, and based on the multi-machine cooperation strategy, the multiple cleaning robots are controlled to perform a cooperative cleaning operation on the site to be cleaned.

[0010] In one embodiment, the step of obtaining the time series data of the stain map of the site to be cleaned includes:

[0011] Collecting pollution time series data of the site to be cleaned;

[0012] The pollution time series data is mapped into a preset site map to obtain the pollution map time series data of the site to be cleaned.

[0013] In one embodiment, before the step of mapping the pollution time series data into a preset site map to obtain the stain map time series data of the site to be cleaned, the method further includes:

[0014] Controlling the multiple cleaning robots to patrol the site to be cleaned, and collecting environmental data and positioning data of the site to be cleaned by the multiple cleaning robots;

[0015] Based on a simultaneous positioning and mapping algorithm, a site map is constructed according to the environmental data and the positioning data.

[0016] In one embodiment, the stain map temporal data includes at least map coordinates, timestamps, and cleanliness.

[0017] The step of dividing the site to be cleaned into a plurality of periodic cleaning areas according to the stain map time series data includes:

[0018] generating a stain map feature vector according to the map coordinates, timestamp, and cleanliness;

[0019] Clustering is performed on the stain map feature vectors to obtain a plurality of periodic cleaning areas.

[0020] In one embodiment, before the step of clustering the stain map feature vectors to obtain a plurality of periodic cleaning areas, the step further includes:

[0021] Calculating the cleanliness change rate in each time period in the stain map feature vector, and merging the time periods whose cleanliness change rates meet a preset merging condition to obtain a plurality of cleaning periods;

[0022] The step of clustering the stain map feature vectors to obtain a plurality of periodic cleaning areas includes:

[0023] According to the multiple cleaning cycles, clustering processing is performed on the stain map feature vectors to obtain multiple periodic cleaning areas.

[0024] In one embodiment, the step of generating a multi-machine collaboration strategy based on the multiple periodic cleaning areas includes:

[0025] generating a cleaning area matrix corresponding to the plurality of periodic cleaning areas and a cleaning capability matrix corresponding to the plurality of cleaning robots;

[0026] Calculating task compatibility between the plurality of cleaning robots and the plurality of periodic cleaning areas according to the cleaning area matrix and the cleaning capability matrix;

[0027] A multi-machine collaboration strategy is generated according to the task compatibility between the multiple cleaning robots and the multiple periodic cleaning areas.

[0028] In addition, to achieve the above-mentioned purpose, the present application also proposes a cleaning robot multi-machine collaboration device, which includes:

[0029] A data acquisition module is used to obtain time series data of the stain map of the site to be cleaned;

[0030] An area division module, configured to divide the site to be cleaned into a plurality of periodic cleaning areas according to the stain map time series data;

[0031] The collaboration control module is used to generate a multi-machine collaboration strategy according to the multiple periodic cleaning areas, and control the multiple cleaning robots to perform collaborative cleaning operations on the site to be cleaned based on the multi-machine collaboration strategy.

[0032] In addition, to achieve the above-mentioned purpose, the present application also proposes a cleaning robot multi-machine collaboration device, which includes: a memory, a processor, and a computer program stored on the memory and runnable on the processor, and the computer program is configured to implement the steps of the cleaning robot multi-machine collaboration method described above.

[0033] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium. A computer program is stored on the storage medium, and when the computer program is executed by the processor, the steps of the multi-machine collaboration method of cleaning robots as described above are implemented.

[0034] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the multi-machine collaboration method of cleaning robots as described above.

[0035] This application provides a method for multi-machine collaboration of cleaning robots. First, by acquiring the time-series data of the stain map of the site to be cleaned, the distribution and dynamic changes of the stains are perceived in real time, providing accurate environmental information for subsequent cleaning strategies. Then, based on the time-series data of the stain map, the site to be cleaned is divided into multiple periodic cleaning areas. The cleaning tasks can be flexibly adjusted according to the distribution and changes of the stains, avoiding the cleaning blind spots and resource waste caused by fixed task allocation in traditional methods. Finally, a multi-machine collaboration strategy is generated based on the divided periodic cleaning areas, and based on this strategy, multiple cleaning robots are controlled to perform collaborative cleaning operations. The task allocation and collaboration methods between the cleaning robots are dynamically adjusted to ensure the efficiency and high coverage of the cleaning operations, thereby realizing intelligent collaborative control of multiple cleaning robots. This method improves the adaptability of cleaning robots in the multi-machine collaboration process, optimizes task allocation and collaboration efficiency, and thus effectively ensures the cleanliness of collaborative cleaning. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0038] Figure 1 A schematic diagram of the flow chart provided for the first embodiment of the multi-machine collaboration method of cleaning robots of the present application;

[0039] Figure 2 A flowchart illustrating a second embodiment of the multi-machine collaboration method for cleaning robots of the present application;

[0040] Figure 3 This is a schematic diagram of the module structure of a multi-machine collaboration device of cleaning robots according to an embodiment of the present application;

[0041] Figure 4 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the multi-machine collaboration method of cleaning robots in the embodiment of the present application.

[0042] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0043] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0044] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0045] The main solution of the embodiment of the present application is: obtaining the stain map time series data of the site to be cleaned; dividing the site to be cleaned into multiple periodic cleaning areas based on the stain map time series data; generating a multi-machine collaboration strategy based on the multiple periodic cleaning areas, and based on the multi-machine collaboration strategy, controlling multiple cleaning robots to perform collaborative cleaning operations on the site to be cleaned.

[0046] Since the existing technology of multi-machine collaboration of cleaning robots usually adopts a method based on fixed task allocation, before the task begins, the site will be divided into several sub-areas based on the geometric shape of the site or fixed priority. Each sub-area is assigned to a specific cleaning robot, and the cleaning robot performs cleaning operations according to the preset path. The task allocation and path planning of the cleaning robot are relatively fixed and independent during the operation process. Its static task allocation method lacks adaptability. When the stains in a certain area suddenly increase, the task allocation cannot be adjusted in time, resulting in incomplete cleaning of the area.

[0047] In this application, first, by acquiring the time series data of the stain map of the site to be cleaned, the distribution and dynamic changes of the stains are perceived in real time, providing accurate environmental information for the subsequent cleaning strategy; then, based on the time series data of the stain map, the site to be cleaned is divided into multiple periodic cleaning areas, which can flexibly adjust the cleaning tasks according to the distribution and changes of the stains, avoiding the cleaning blind spots and resource waste caused by fixed task allocation in traditional methods; finally, a multi-machine collaboration strategy is generated based on the divided periodic cleaning areas, and multiple cleaning robots are controlled by this strategy to perform collaborative cleaning operations, dynamically adjusting the task allocation and collaboration methods between robots to ensure the efficiency and comprehensiveness of the cleaning operations. The adaptability and intelligence of the multi-machine collaboration of the cleaning robots are improved, the task allocation and collaboration efficiency are optimized, and thus the cleanliness of the collaborative cleaning is effectively guaranteed.

[0048] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, mobile phone, etc., or an electronic device capable of implementing the above functions, a multi-machine collaborative cleaning robot device, etc. The following uses a multi-machine collaborative cleaning robot device as an example to illustrate this embodiment and the following embodiments.

[0049] Based on this, the embodiment of the present application provides a cleaning robot multi-machine collaboration method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the multi-machine collaboration method of cleaning robots in this application.

[0050] In this embodiment, the cleaning robot multi-machine collaboration method is applied to a robot multi-machine collaboration platform, and the robot multi-machine collaboration platform is communicatively connected with multiple cleaning robots. The cleaning robot multi-machine collaboration method includes steps S10 to S30:

[0051] Step S10, obtaining time series data of a stain map of the site to be cleaned;

[0052] It should be noted that the stain map time series data refers to data that records the distribution of stains in the site to be cleaned and their changes over time, which may include data such as the location coordinates of the stains, pollution time, ground pollution values, and air pollution values.

[0053] In addition, it should be noted that a cleaning robot refers to a robot with a cleaning function. A cleaning robot can be a robot with a single cleaning function, such as a sweeping robot, a mopping robot, and an air purifier robot; it can also be a robot with two or more cleaning functions, such as a sweeping and mopping robot, an all-round cleaning robot, etc. Among them, a sweeping and mopping robot can have the ability to sweep and mop the floor, and an all-round cleaning robot can have functions such as sweeping, mopping, and air purification.

[0054] Understandably, in order to perceive the distribution and changing trends of stains in the area to be cleaned in real time, the system can adjust the cleaning strategy in a timely manner by dynamically sensing the distribution of stains, avoiding blind spots or waste of resources caused by changes in stain distribution, and providing accurate environmental information for subsequent cleaning area division and task allocation, thereby improving the cleaning efficiency and cleanliness of multiple cleaning robots working together.

[0055] Step S20, dividing the site to be cleaned into a plurality of periodic cleaning areas according to the stain map time series data;

[0056] It should be noted that the periodic cleaning area refers to an area with periodic cleaning needs that is dynamically divided according to the stain map time series data. For example, the basis for division can also include the distribution density of stains, the degree of pollution, the dynamic change trend and the cleaning ability of the cleaning robot.

[0057] Understandably, to optimize the allocation of cleaning tasks based on the dynamic distribution of stains, the site to be cleaned is divided into multiple periodic cleaning zones based on the time-series data of the stain map. By dynamically dividing the cleaning zones based on the site's dynamic changes, we ensure that high-contamination areas are cleaned first, while low-contamination areas are allocated resources on demand. This improves cleaning efficiency and cleanliness, provides a scientific basis for task allocation in multi-machine collaboration strategies, and avoids resource waste and blind spots in cleaning.

[0058] Optionally, the site to be cleaned can be divided into multiple periodic cleaning areas in the following ways: 1. Use a clustering algorithm (such as the K-means clustering algorithm) to analyze the time series data of the stain map, and divide areas with higher stain density into high-priority cleaning areas, and areas with lower stain density into low-priority cleaning areas. This can efficiently process large-scale data and is suitable for scenarios with relatively uniform stain distribution; 2. Through a dynamic programming algorithm, based on the growth rate and distribution trend of stains, predict the stain distribution in a future period of time, and divide the cleaning areas accordingly. This can predict the future stain distribution and is suitable for scenarios with obvious stain change trends; 3. Combined with a reinforcement learning algorithm, the cleaning area division strategy is dynamically adjusted according to historical cleaning data and current stain distribution to optimize cleaning efficiency. This can optimize the division strategy based on historical data and is suitable for complex dynamic environments.

[0059] For example, in an office building cleaning scenario, analyzing the time-series data of the stain map reveals that during work hours, the stain density is higher in conference rooms and corridors, while it is lower in rest areas. Using the K-means clustering algorithm, areas like conference rooms and corridors where the stain density meets the priority cleaning criteria are classified as high-priority cleaning areas for that time period, while areas like rest areas where the stain density does not meet the priority cleaning criteria are classified as low-priority cleaning areas for that time period. The reverse is true for rest periods. Furthermore, the collaboration platform recognizes that the stain density in conference rooms (or employee cafeterias) increases further during lunch hours, so cleaning robots should be prioritized for conference rooms after lunch.

[0060] Step S30 : generating a multi-machine cooperation strategy according to the multiple periodic cleaning areas, and controlling the multiple cleaning robots to perform a cooperative cleaning operation on the site to be cleaned based on the multi-machine cooperation strategy.

[0061] It should be noted that the multi-machine collaboration strategy refers to assigning specific periodic cleaning tasks to each cleaning robot based on the division results of the cleaning area, and coordinating the collaborative cleaning methods among multiple cleaning robots.

[0062] It can be understood that in order to optimize the execution process of the cleaning task according to the division results of the cleaning area, a multi-machine collaboration strategy is generated by using multiple periodic cleaning areas divided by the stain map time series data, and then tasks are allocated through the multi-machine collaboration strategy to control multiple cleaning robots for collaborative cleaning. This can ensure that resources are allocated on demand in different changing areas, thereby improving cleaning efficiency and cleanliness, and ensuring the efficient completion of cleaning tasks.

[0063] For example, in an airport cleaning scenario, the collaborative platform uses a task allocation algorithm to assign high-priority cleaning areas (such as the terminal) to robots with stronger cleaning capabilities, and low-priority cleaning areas (such as the baggage claim area) to robots with weaker cleaning capabilities. The collaborative platform also uses the A* algorithm to generate optimal cleaning paths for each robot and dynamically adjusts task allocations through a real-time scheduling algorithm. If the density of stains in the terminal suddenly increases, the collaborative platform will prioritize nearby cleaning robots for support, ensuring efficient completion of cleaning tasks.

[0064] In a feasible implementation, the step of obtaining the time series data of the stain map of the site to be cleaned includes:

[0065] Step S101, collecting pollution time series data of the site to be cleaned;

[0066] It should be noted that pollution time series data refers to data obtained through sensors or other data acquisition equipment, which records the pollution situation in the site to be cleaned and its changes over time. Pollution time series data can be collected through equipment such as lidar, visual sensors, and infrared sensors.

[0067] It is understandable that in order to perceive the pollution distribution and changing trends of the site to be cleaned in real time, by collecting the pollution time series data of the site to be cleaned and perceiving the dynamic distribution changes of pollution, the cleaning strategy can be adjusted in time to avoid cleaning blind spots or waste of resources caused by changes in pollution distribution.

[0068] Step S102 : Mapping the pollution time series data to a preset site map to obtain the pollution map time series data of the site to be cleaned.

[0069] It should be noted that stain map time series data refers to data generated by combining pollution time series data with a pre-set site map, recording the distribution of stains and changes in the site over time. A pre-set site map refers to a site map pre-generated using a simultaneous positioning and mapping algorithm or other mapping technology.

[0070] It can be understood that in order to generate a dynamic stain map, the pollution time series data is mapped to the preset site map to obtain stain map time series data that reflects the dynamic distribution and changes of stains in the site. This can ensure that the allocation and execution of cleaning tasks are based on environmental information that changes dynamically over time, thereby improving cleaning efficiency and cleanliness, and providing accurate dynamic data support for subsequent cleaning area division and task allocation.

[0071] In this implementation, by collecting pollution time-series data, the system can perceive pollution distribution and changing trends in real time, providing dynamic environmental information for subsequent cleaning task allocation. Secondly, by mapping pollution data onto a site map, a dynamic spot map can be generated, ensuring that cleaning task allocation and execution are based on the latest environmental information, improving the efficiency and cleanliness of multi-machine collaborative cleaning.

[0072] In a feasible implementation manner, before the step of mapping the pollution time series data into a preset site map to obtain the stain map time series data of the site to be cleaned, the method further includes:

[0073] Step S1021, controlling the multiple cleaning robots to patrol the site to be cleaned, and collecting environmental data and positioning data of the site to be cleaned by the multiple cleaning robots;

[0074] It should be noted that patrolling refers to the cleaning robot's patrol-style movement throughout the cleaning area, following a pre-set path or strategy to cover every area of ​​the site. Environmental data refers to information about the site environment collected by sensors, such as obstacle locations and surface type. Positioning data refers to the robot's own position information, acquired by positioning sensors (such as GPS or laser positioning). In this step, patrolling ensures that the robot fully covers the site and collects sufficient environmental and positioning data.

[0075] It is understandable that in order to obtain comprehensive information about the site, the cleaning robot is controlled to patrol and collect environmental data and positioning data. By patrolling, the comprehensiveness and uniformity of data collection can be ensured, thereby improving the accuracy and reliability of map construction.

[0076] Step S1022: constructing a site map based on the environmental data and the positioning data based on a simultaneous positioning and mapping algorithm.

[0077] It's important to note that the Simultaneous Localization and Mapping (SLAM) algorithm is a technology that simultaneously performs robot positioning and map construction. Environmental data refers to information collected by sensors about the site being cleaned, such as obstacle locations and ground conditions. Positioning data refers to the robot's own position information, acquired by positioning sensors. A site map is a two-dimensional or three-dimensional map of the site being cleaned.

[0078] It can be understood that based on the synchronous positioning and mapping algorithm, the environmental data and positioning data collected by multiple robots in the scene to be cleaned are used to build a site map. It can process the environmental and positioning data in real time, dynamically build and update the site map, thereby improving the adaptability and efficiency of the cleaning task.

[0079] In this implementation, by controlling the cleaning robots' patrols and collecting environmental and positioning data, the system can fully cover the site to be cleaned, providing high-quality data support for map construction. Finally, through the dynamic construction and updating of the site map using the SLAM algorithm, it can reflect environmental changes in real time, ensuring that the allocation and execution of cleaning tasks are based on the latest site information. This significantly improves the adaptability of the multi-robot collaborative cleaning system and optimizes task allocation and resource utilization.

[0080] This embodiment provides a method for multi-machine collaboration of cleaning robots. First, by acquiring the time-series data of the stain map of the site to be cleaned, the distribution and dynamic changes of the stains are perceived in real time, providing accurate environmental information for subsequent cleaning strategies. Then, based on the time-series data of the stain map, the site to be cleaned is divided into multiple periodic cleaning areas. The cleaning tasks can be flexibly adjusted according to the distribution and changes of the stains, avoiding the cleaning blind spots and resource waste caused by fixed task allocation in traditional methods. Finally, a multi-machine collaboration strategy is generated based on the divided periodic cleaning areas, and multiple cleaning robots are controlled by the multi-machine collaboration strategy to perform collaborative cleaning operations. The task allocation and collaboration methods between the cleaning robots are dynamically adjusted to ensure the efficiency of cleaning task execution and the integrity of regional coverage during the collaboration of multiple cleaning robots. At the same time, the adaptability and intelligence of the multi-machine collaboration of cleaning robots are improved, the task allocation and collaboration efficiency are optimized, and thus the cleanliness of collaborative cleaning is effectively guaranteed.

[0081] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the first embodiment can be referred to the above introduction and will not be described in detail later. Figure 2 , Figure 2 This is a flow chart of the second embodiment of the multi-machine collaboration method of cleaning robots in this application.

[0082] In this embodiment, the stain map time series data includes at least map coordinates, a timestamp, and cleanliness. The step of dividing the site to be cleaned into a plurality of periodic cleaning areas according to the stain map time series data includes:

[0083] Step S201, generating a stain map feature vector according to the map coordinates, timestamp and cleanliness;

[0084] It should be noted that the stain map feature vector refers to a high-dimensional mathematical model formed by key feature information such as map coordinates, timestamps, and cleanliness in the stain map time series data. Among them, each map coordinate can contain the cleanliness of different timestamps, representing the cleanliness level of a certain location in the site to be cleaned at a certain moment.

[0085] It can be understood that by extracting key features such as map coordinates, timestamps and cleanliness from the stain map time series data, the stain map time series data is converted into a compact mathematical representation, namely the stain map feature vector, and the complex stain distribution data is simplified into a processable feature vector, which can capture the main laws of stain distribution and improve the efficiency of clustering processing and analysis accuracy.

[0086] Step S202 : performing clustering processing on the stain map feature vector to obtain a plurality of periodic clean areas.

[0087] It should be noted that clustering processing refers to dividing feature vectors into multiple groups through a clustering algorithm, so that the similarity of feature vectors within the same group is high, and the similarity of feature vectors between different groups is low. It is used to divide the site to be cleaned into multiple periodic cleaning areas based on the similarity of the feature vectors of the stain map.

[0088] It is understandable that in order to optimize the allocation of cleaning tasks based on the similarity of stain distribution, a clustering algorithm is used to cluster the stain map feature vectors, dividing the stain areas with spatially connected relationship characteristics into the same cleaning area. After clustering, multiple periodic cleaning areas are obtained, thus avoiding resource waste and blind spots of cleaning robots.

[0089] In a feasible implementation manner, before the step of clustering the stain map feature vectors to obtain a plurality of periodic cleaning areas, the method further includes:

[0090] Step S2021, calculating the cleanliness change rate in each time period in the stain map feature vector, merging the time periods whose cleanliness change rates meet a preset merging condition to obtain multiple cleaning periods;

[0091] It should be noted that the term "time period" refers to the set of all timestamps between two moments in the stain map feature vector. Here, it refers to the time period obtained by evenly dividing the data of all stain map feature vectors by all timestamps. The cleanliness change rate refers to the rate at which cleanliness changes over time in the stain map feature vector. The preset merge condition is a condition for merging time periods with similar cleanliness change patterns based on the similarity of cleanliness change rates or other relevant indicators. A cleanliness period is a unit of time obtained by merging one or more consecutive time periods based on the cleanliness change rate.

[0092] It can be understood that in order to identify the law of stain distribution changing over time and calculate the cleanliness change rate, each continuous time period with similar cleaning requirements is merged into one cleaning cycle. After all time periods are merged, multiple cleaning cycles are obtained, which can optimize the distribution of cleaning tasks, reduce unnecessary cleaning operations, and improve cleaning efficiency.

[0093] The step of clustering the stain map feature vectors to obtain a plurality of periodic cleaning areas includes:

[0094] Step S2022: performing clustering processing on the stain map feature vectors according to the multiple cleaning cycles to obtain multiple periodic cleaning areas.

[0095] It can be understood that in order to identify areas with similar pollution characteristics and cleaning cycles, thereby providing support for subsequent cleaning task allocation, the stain map feature vector is clustered according to the multiple cleaning cycles obtained by merging different time periods in the stain map feature vector, and the spatially continuous stain coordinates with similar pollution degree changes in each cleaning cycle are divided into the same cleaning area, thereby obtaining multiple periodic cleaning areas.

[0096] For example, assuming the site to be cleaned is a restaurant, the restaurant's stain map feature vector is used to calculate the cleanliness change rate within each time period. The cleanliness change rate within the lunch-related time period and the dinner-related time period is relatively high, while the cleanliness change rate within other time periods is relatively low. By merging time periods, the lunch-related time period and the dinner-related time period can be merged into a high-contamination cleaning period, while the other time periods can be merged into a low-contamination cleaning period. After determining multiple cleaning periods, the stain coordinates corresponding to each cleaning period in the stain map feature vector are spatially clustered to obtain the contaminated area corresponding to each cleaning period. Finally, when allocating multi-machine collaborative tasks, a cleaning robot can be assigned to the contaminated area of ​​each cleaning period after the high-contamination cleaning period ends or before the low-contamination cleaning period begins, forming a multi-machine collaborative task for cleaning robots. After the task is assigned to the corresponding cleaning robot, the cleaning robot will perform multi-machine collaborative cleaning on the contaminated area of ​​the cleaning period at a fixed time and location. In addition, if there are multiple contaminated areas within a cleaning period, multiple cleaning robots will be assigned to the cleaning period for simultaneous collaborative cleaning.

[0097] In this implementation, by calculating the cleanliness change rate and incorporating time periods, the dynamic patterns of contaminated areas can be identified. By clustering the stain map feature vectors according to the cleaning cycle, the allocation and execution of cleaning tasks can be optimized. This allows cleaning robots to collaborate efficiently on the collaborative platform, improving cleaning efficiency and cleanliness while reducing conflicts and resource waste.

[0098] In a feasible implementation, the step of generating a multi-machine collaboration strategy based on the multiple periodic cleaning areas includes:

[0099] Step S301, generating a cleaning area matrix corresponding to the plurality of periodic cleaning areas and a cleaning capability matrix corresponding to the plurality of cleaning robots;

[0100] It should be noted that the cleaning area matrix is ​​a data structure that describes the characteristics of a periodic cleaning area (such as cleaning range, contamination level, and cleaning time range), while the cleaning capability matrix is ​​a data structure that describes the capabilities of a cleaning robot (such as cleaning function, cleaning efficiency, and battery life). Cleaning capabilities can include sweeping, mopping, and air purification capabilities.

[0101] It is understandable that in order to quantify the cleaning tasks and cleaning robot capabilities, and thus provide support for subsequent task suitability calculations, a cleaning area matrix and a cleaning capability matrix are generated by analyzing the regional characteristics of different periodic cleaning areas and the cleaning capabilities of different cleaning robots.

[0102] Optionally, the cleaning area matrix and cleaning capacity matrix can be generated by the following steps: 1. Extracting the features of each periodic cleaning area (e.g., the set of stain coordinates, the degree of ground pollution, the degree of air pollution, and the cleaning time) to generate the cleaning area matrix; 2. Extracting the capabilities of each cleaning robot (e.g., sweeping capability, mopping capability, air cleaning capability, cleaning unit speed, cleaning unit range, and battery life) to generate the cleaning capacity matrix; 3. Normalizing the matrix to ensure data consistency and comparability. This can improve the accuracy and adaptability of matrix generation. For example, combining feature extraction and normalization can achieve a comprehensive description of areas and capabilities.

[0103] For example, let's assume the site to be cleaned is an airport, where periodic cleaning areas include the terminal area, boarding gate, and baggage claim area. The cleaning area matrix can describe the scope, contamination level, and cleaning cycle of each area, while the cleaning capacity matrix can describe the cleaning capacity, cleaning efficiency, and battery life of each cleaning robot.

[0104] Step S302, calculating the task adaptability of the plurality of cleaning robots and the plurality of periodic cleaning areas according to the cleaning area matrix and the cleaning capability matrix;

[0105] It should be noted that task suitability refers to the degree of matching between the cleaning robot and the cleaning area, and the calculation methods usually include weighted scoring, similarity analysis, etc.

[0106] It is understandable that in order to achieve efficient allocation of cleaning tasks and thus improve cleaning efficiency and cleanliness, through appropriate similarity calculation methods, based on the cleaning area matrix and the cleaning capacity matrix, the task adaptability between multiple cleaning robots and multiple periodic cleaning areas is calculated, and the matching degree between the cleaning robots and the cleaning areas is quantified to identify the cleaning robot that is most suitable for each area, thereby optimizing the allocation of cleaning tasks and ensuring that the cleaning tasks in each area can be completed by the most suitable cleaning robot.

[0107] For example, if the airport's clean area matrix shows that the waiting area is large and has a high level of pollution, while the cleaning capability matrix shows that a certain cleaning robot has a high cleaning speed and a large cleaning range, then the task compatibility between the two will be relatively high. Furthermore, if the airport's clean area matrix shows that the ground and air in the restroom area are highly polluted, while the cleaning capability matrix shows that a certain cleaning robot has the corresponding mopping and air purification functions, then the task compatibility between the two will also be relatively high. By calculating the compatibility, it is possible to identify the cleaning robot most suitable for cleaning the waiting area and assign it the corresponding cleaning task.

[0108] Step S303: generating a multi-machine collaboration strategy according to the task compatibility between the multiple cleaning robots and the multiple periodic cleaning areas.

[0109] It's understandable that in order to optimize the allocation and execution of cleaning tasks and ensure efficient collaboration among multiple cleaning robots, task compatibility analysis can be used to assign the most appropriate cleaning task to each robot, generating a multi-robot collaboration strategy. This ensures efficient allocation and execution of cleaning tasks across multiple robots, resolves task conflicts and resource allocation issues through collaborative mechanisms, and improves cleaning efficiency and cleanliness.

[0110] In this embodiment, first, a cleaning area matrix and a cleaning capacity matrix are generated to quantify the cleaning tasks and cleaning robot capabilities; then, by calculating the task adaptability between periodic cleaning areas and cleaning robots, and generating a strategy for multi-machine collaboration of cleaning robots, the allocation of cleaning tasks can be optimized, the efficient execution of cleaning tasks can be achieved, the cleaning efficiency and cleanliness are improved, and the conflict of cleaning tasks and waste of resources are reduced.

[0111] In this embodiment, a stain map feature vector is generated by obtaining the stain map time series data, and the complex stain distribution data is simplified into a processable feature vector, thereby improving the computing efficiency and analysis accuracy, and being able to perceive the distribution and change trend of the stains in real time; then, by clustering the feature vectors, the division of the cleaning area can be optimized according to the correlation of the stain distribution, and the task execution between multiple cleaning robots can be coordinated to avoid waste of resources and cleaning blind spots.

[0112] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the multi-machine collaboration method of cleaning robots in the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0113] This application also provides a cleaning robot multi-machine collaboration device, please refer to Figure 3 , the cleaning robot multi-machine collaboration device includes:

[0114] The data acquisition module 10 is used to obtain the time series data of the stain map of the site to be cleaned;

[0115] An area division module 20 is configured to divide the site to be cleaned into a plurality of periodic cleaning areas according to the stain map time series data;

[0116] The collaboration control module 30 is configured to generate a multi-machine collaboration strategy according to the multiple periodic cleaning areas, and control the multiple cleaning robots to perform collaborative cleaning operations on the site to be cleaned based on the multi-machine collaboration strategy.

[0117] Optionally, the data acquisition module 10 is further configured to:

[0118] Collecting pollution time series data of the site to be cleaned;

[0119] The pollution time series data is mapped into a preset site map to obtain the pollution map time series data of the site to be cleaned.

[0120] Optionally, the data acquisition module 10 is further configured to:

[0121] Controlling the multiple cleaning robots to patrol the site to be cleaned, and collecting environmental data and positioning data of the site to be cleaned by the multiple cleaning robots;

[0122] Based on a simultaneous positioning and mapping algorithm, a site map is constructed according to the environmental data and the positioning data.

[0123] Optionally, the stain map time series data includes at least map coordinates, timestamps, and cleanliness, and the region division module 20 is further configured to:

[0124] generating a stain map feature vector according to the map coordinates, timestamp, and cleanliness;

[0125] Clustering is performed on the stain map feature vectors to obtain a plurality of periodic cleaning areas.

[0126] Optionally, the area division module 20 is further configured to:

[0127] Calculating the cleanliness change rate in each time period in the stain map feature vector, and merging the time periods whose cleanliness change rates meet a preset merging condition to obtain a plurality of cleaning periods;

[0128] According to the multiple cleaning cycles, clustering processing is performed on the stain map feature vectors to obtain multiple periodic cleaning areas.

[0129] Optionally, the collaboration control module 30 is further configured to:

[0130] generating a cleaning area matrix corresponding to the plurality of periodic cleaning areas and a cleaning capability matrix corresponding to the plurality of cleaning robots;

[0131] Calculating task compatibility between the plurality of cleaning robots and the plurality of periodic cleaning areas according to the cleaning area matrix and the cleaning capability matrix;

[0132] A multi-machine collaboration strategy is generated according to the task compatibility between the multiple cleaning robots and the multiple periodic cleaning areas.

[0133] The multi-machine collaborative cleaning robot device provided in this application adopts the multi-machine collaborative cleaning robot method of the above-mentioned embodiment, which can solve the technical problem in the prior art that cleaning robots have insufficient adaptability during the multi-machine collaborative process and cannot guarantee the quality of collaborative cleaning. Compared with the prior art, the beneficial effects of the multi-machine collaborative cleaning robot device provided in this application are the same as the beneficial effects of the multi-machine collaborative cleaning robot method provided in the above-mentioned embodiment, and the other technical features of the multi-machine collaborative cleaning robot device are the same as the features disclosed in the above-mentioned embodiment method, and are not further described here.

[0134] The present application provides a cleaning robot multi-machine collaboration device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the cleaning robot multi-machine collaboration method in the above-mentioned first embodiment.

[0135] Reference below Figure 4 , which shows a schematic diagram of the structure of a multi-machine collaborative cleaning robot device suitable for implementing the embodiments of the present application. The multi-machine collaborative cleaning robot device in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4 The cleaning robot multi-machine collaboration device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0136] like Figure 4As shown, the multi-machine cleaning robot collaborative device may include a processing device 1001 (e.g., a central processing unit, graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory 1002 or programs loaded from a storage device 1003 into a random access memory 1004. The random access memory 1004 also stores various programs and data required for the operation of the multi-machine cleaning robot collaborative device. The processing device 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An input / output interface 1006 is also connected to the bus. Typically, the following systems can be connected to the input / output interface 1006: an input device 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; a storage device 1003 including, for example, a magnetic tape or hard disk; and a communication device 1009. The communication device 1009 can allow the cleaning robot multi-machine collaboration device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a cleaning robot multi-machine collaboration device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided instead.

[0137] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a read-only memory 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are performed.

[0138] The multi-machine collaborative cleaning robot device provided in this application adopts the multi-machine collaborative cleaning robot method of the above-mentioned embodiment, which can solve the technical problem in the prior art that cleaning robots have insufficient adaptability during the multi-machine collaborative process and cannot guarantee the quality of collaborative cleaning. Compared with the prior art, the beneficial effects of the multi-machine collaborative cleaning robot device provided in this application are the same as the beneficial effects of the multi-machine collaborative cleaning robot method provided in the above-mentioned embodiment, and the other technical features of the multi-machine collaborative cleaning robot device are the same as the features disclosed in the method of the previous embodiment, and will not be repeated here.

[0139] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0140] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0141] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, a computer program) stored thereon, and the computer-readable program instructions are used to execute the multi-machine collaboration method of cleaning robots in the above-mentioned embodiment.

[0142] The computer-readable storage medium provided herein may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including, but not limited to, wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0143] The computer-readable storage medium may be included in the cleaning robot multi-machine collaboration device; or it may exist independently without being assembled into the cleaning robot multi-machine collaboration device.

[0144] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the cleaning robot multi-machine collaboration device, the cleaning robot multi-machine collaboration device enables the cleaning robot multi-machine collaboration device to: obtain the stain map time series data of the site to be cleaned; divide the site to be cleaned into multiple periodic cleaning areas according to the stain map time series data; generate a multi-machine collaboration strategy according to the multiple periodic cleaning areas, and based on the multi-machine collaboration strategy, control multiple cleaning robots to perform collaborative cleaning operations on the site to be cleaned.

[0145] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0146] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, program segment or part of code, and the module, program segment or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, as well as the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0147] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0148] The computer-readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned multi-robot collaborative cleaning robot method. This computer-readable storage medium can address the prior art technical issues of insufficient adaptability and inability to guarantee collaborative cleaning quality during multi-robot collaborative cleaning. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the multi-robot collaborative cleaning robot method provided in the aforementioned embodiments, and are not further elaborated here.

[0149] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned cleaning robot multi-machine collaboration method when executed by a processor.

[0150] The computer program product provided in this application can address the technical issues in the prior art whereby cleaning robots have insufficient adaptability during multi-robot collaboration, thus failing to guarantee the quality of collaborative cleaning. Compared to the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the multi-robot collaborative cleaning robot method provided in the aforementioned embodiment, and are not further elaborated here.

[0151] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A multi-machine collaboration method for cleaning robots, characterized in that: The multi-machine collaboration method for cleaning robots is applied to a multi-machine collaboration platform for robots, wherein the multi-machine collaboration platform is communicatively connected with a plurality of cleaning robots, wherein the cleaning robots are robots configured with at least one cleaning function, and the multi-machine collaboration method for cleaning robots comprises: Obtaining time-series data of a stain map of the site to be cleaned, and sensing the distribution and dynamic changes of stains in real time. The stain map time-series data includes at least the coordinates of the stain location, the time of contamination, the ground pollution value, and the air pollution value; Dividing the site to be cleaned into a plurality of periodic cleaning areas according to the stain map time series data; Generating a multi-machine collaboration strategy according to the multiple periodic cleaning areas, and controlling the multiple cleaning robots to perform collaborative cleaning operations on the site to be cleaned based on the multi-machine collaboration strategy; The step of generating a multi-machine collaboration strategy based on the multiple periodic cleaning areas includes: Generating a cleaning area matrix corresponding to the multiple periodic cleaning areas and a cleaning capability matrix corresponding to the multiple cleaning robots, wherein the cleaning area matrix includes at least a set of stain coordinates, a ground pollution degree, and an air pollution degree, and the cleaning capability matrix includes at least a sweeping capability, a mopping capability, and an air cleaning capability; Calculating task compatibility between the plurality of cleaning robots and the plurality of periodic cleaning areas according to the cleaning area matrix and the cleaning capability matrix; A multi-machine collaboration strategy is generated according to the task compatibility between the multiple cleaning robots and the multiple periodic cleaning areas.

2. The multi-machine collaboration method of cleaning robots according to claim 1, characterized in that: The step of obtaining the time series data of the stain map of the site to be cleaned includes: Collecting pollution time series data of the site to be cleaned; The pollution time series data is mapped into a preset site map to obtain the pollution map time series data of the site to be cleaned.

3. The cleaning robot multi-machine collaboration method according to claim 2, characterized in that: Before the step of mapping the pollution time series data into a preset site map to obtain the stain map time series data of the site to be cleaned, the method further includes: Controlling the multiple cleaning robots to patrol the site to be cleaned, and collecting environmental data and positioning data of the site to be cleaned by the multiple cleaning robots; Based on a simultaneous positioning and mapping algorithm, a site map is constructed according to the environmental data and the positioning data.

4. The multi-machine collaboration method of cleaning robots according to claim 1, characterized in that: The stain map time series data includes at least map coordinates, timestamp and cleanliness, The step of dividing the site to be cleaned into a plurality of periodic cleaning areas according to the stain map time series data includes: generating a stain map feature vector according to the map coordinates, timestamp, and cleanliness; Clustering is performed on the stain map feature vectors to obtain a plurality of periodic cleaning areas.

5. The multi-machine collaboration method of cleaning robots according to claim 4, characterized in that: Before the step of clustering the stain map feature vectors to obtain a plurality of periodic cleaning areas, the method further includes: Calculating the cleanliness change rate in each time period in the stain map feature vector, and merging the time periods whose cleanliness change rates meet a preset merging condition to obtain a plurality of cleaning periods; The step of clustering the stain map feature vectors to obtain a plurality of periodic cleaning areas includes: According to the multiple cleaning cycles, clustering processing is performed on the stain map feature vectors to obtain multiple periodic cleaning areas.

6. A multi-machine collaborative cleaning robot device, characterized in that: The cleaning robot multi-machine collaboration device is communicatively connected to a plurality of cleaning robots, wherein the cleaning robots are robots configured with at least one cleaning function, including: A data acquisition module is used to obtain the time series data of the stain map of the site to be cleaned, and to perceive the distribution and dynamic changes of the stains in real time. The stain map time series data includes at least the coordinates of the stain location, the time of contamination, the ground pollution value, and the air pollution value; An area division module, configured to divide the site to be cleaned into a plurality of periodic cleaning areas according to the stain map time series data; A collaboration control module is used to generate a multi-machine collaboration strategy according to the multiple periodic cleaning areas, and control the multiple cleaning robots to perform collaborative cleaning operations on the site to be cleaned based on the multi-machine collaboration strategy; Among them, the collaborative control module is also used to: generate a cleaning area matrix corresponding to the multiple periodic cleaning areas and a cleaning capability matrix corresponding to the multiple cleaning robots, the cleaning area matrix at least includes a set of stain coordinates, a degree of ground pollution and a degree of air pollution, and the cleaning capability matrix at least includes sweeping capability, mopping capability and air cleaning capability; based on the cleaning area matrix and the cleaning capability matrix, calculate the task adaptability of the multiple cleaning robots to the multiple periodic cleaning areas; based on the task adaptability of the multiple cleaning robots to the multiple periodic cleaning areas, generate a multi-machine collaboration strategy.

7. A cleaning robot multi-machine collaboration device, characterized in that: The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the multi-machine collaboration method of cleaning robots as claimed in any one of claims 1 to 5.

8. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the multi-machine collaboration method of cleaning robots as described in any one of claims 1 to 5 are implemented.

9. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the multi-machine collaboration method of cleaning robots as claimed in any one of claims 1 to 5 are implemented.

Images