Control Method, Device, Equipment and Storage Medium of Intelligent Mobility Assistance System

Abstract

The present application provides a control method, device, equipment and storage medium for an intelligent mobility assistance system. The method includes: classifying mobility robots into first robots and second robots according to the available power values of the mobility robots; generating a task distribution density map according to the published tasks and a preset navigation map, the task distribution density map including a plurality of task-intensive areas; determining available charging piles according to the task-intensive areas and the preset navigation map, and obtaining the charging position information of the available charging piles; if the number of task-intensive areas is greater than the number of first robots, determining a first operation area and a second operation area according to the task distribution density map and the charging position information, the number of first operation areas being equal to the number of first robots, and the second operation area including at least one available charging pile; respectively controlling the first robots to execute the tasks included in one first operation area, and controlling a plurality of second robots to take turns to execute the tasks included in one second operation area.

Description

Technical Field

[0001] This application relates to the field of automation control technology, and particularly to a control method, device, equipment and storage medium for an intelligent mobility assistance system. Background Art

[0002] Currently, in modern industrial automation and service industries, the application of robots is becoming increasingly widespread. From production lines in manufacturing to customer reception in the service industry, robots are playing an increasingly important role. With the development of robot technology, multi-robot collaborative operation has become an important way to improve work efficiency and handle complex tasks. However, in practical applications, multi-robot systems face a series of challenges, and one of the most prominent problems is the contradiction between the concentrated outbreak of tasks and the battery management of robots. When multiple tasks appear simultaneously or a large number of tasks emerge in a short period of time, it is necessary to quickly allocate available robot resources for response. In this case, how to efficiently assign tasks to different robots and ensure that each robot can maintain sufficient battery power while completing tasks has become an urgent problem to be solved. Since the working intensity and time of each robot are different during use, there will be a large difference in their remaining battery power, which further increases the difficulty of unified scheduling. Summary of the Invention

[0003] This application provides a control method, device, equipment and storage medium for an intelligent mobility assistance system, which is used to improve the scheduling efficiency of mobility robots when tasks break out highly.

[0004] In a first aspect, an embodiment of this application provides a control method for an intelligent mobility assistance system, and the method includes:

[0005] When entering the task increment mode, obtain the available battery power value of the mobility robot, and divide the mobility robot into a first robot and a second robot according to the available battery power value;

[0006] Generate a task distribution density map according to the published tasks and a preset navigation map, where the task distribution density map includes multiple task-intensive areas;

[0007] Determine available charging piles according to the task-intensive areas and the preset navigation map, and obtain the charging position information of the available charging piles;

[0008] If the number of the task-intensive areas is greater than the number of the first robots, determine a first operation area and a second operation area according to the task distribution density map and the charging position information, where the number of the first operation areas is equal to the number of the first robots, and the second operation area includes at least one of the available charging piles;

[0009] Control the first robot to execute the tasks included in the one first work area respectively, and control the multiple second robots to take turns to execute the tasks included in one second work area.

[0010] In a second aspect, an embodiment of the present application provides a control device for an intelligent mobility assistance system, and the device includes:

[0011] A power measurement module, configured to obtain the available power value of the mobility robot when entering the task increment mode, and divide the mobility robot into a first robot and a second robot according to the available power value;

[0012] A task management module, configured to generate a task distribution density map according to the published tasks and a preset navigation map, where the task distribution density map includes multiple task dense areas;

[0013] A charging management and control module, configured to determine available charging piles according to the task dense areas and the preset navigation map, and obtain the charging position information of the available charging piles;

[0014] A region division module, configured to, if the number of the task dense areas is greater than the number of the first robots, determine a first work area and a second work area according to the task distribution density map and the charging position information, where the number of the first work areas is equal to the number of the first robots, and the second work area includes at least one of the available charging piles;

[0015] A motion control module, configured to control the first robot to execute the tasks included in the one first work area respectively, and control the multiple second robots to take turns to execute the tasks included in one second work area.

[0016] In a third aspect, an embodiment of the present application provides an electronic device, and the electronic device includes a memory and a processor;

[0017] The memory is used to store a computer program;

[0018] The processor is configured to execute the computer program and, when executing the computer program, implement the control method of the intelligent mobility assistance system according to any one of the embodiments of the present application.

[0019] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, and the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor is caused to implement the control method of the intelligent mobility assistance system according to any one of the embodiments of the present application.

[0020] An embodiment of the present application provides a control method for an intelligent mobility assistance system. The method includes: when entering the task increment mode, obtaining the available power value of the mobility robot, and dividing the mobility robot into a first robot and a second robot according to the available power value; generating a task distribution density map based on the published tasks and a preset navigation map, where the task distribution density map includes multiple task-intensive areas; determining available charging piles according to the task-intensive areas and the preset navigation map, and obtaining the charging position information of the available charging piles; if the number of task-intensive areas is greater than the number of first robots, determining a first working area and a second working area according to the task distribution density map and the charging position information, where the number of first working areas is equal to the number of first robots, and the second working area includes at least one available charging pile; respectively controlling the first robot to execute the tasks included in one first working area, and controlling multiple second robots to take turns to execute the tasks included in one second working area. Through the above method, the robots are divided into a first robot (high power) and a second robot (low power) based on the power value, and the working areas are reasonably divided by combining the task distribution density map and the charging pile position information. After identifying multiple task-intensive areas, the task ownership is divided according to the number of task-intensive areas and the number of first robots. The task-intensive area close to the charging pile is preferentially set as the second working area to ensure that they can be conveniently charged while performing tasks, and the task-intensive area far from the charging pile is divided into the first working area. Thus, not only the resource allocation is optimized, the ineffective movement is reduced, but also the service interruption problem caused by insufficient power is avoided. Even in the face of a large number of concurrent task requests, the tasks can be completed efficiently and stably, thereby greatly improving the overall service quality and user experience. Description of the Drawings

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0022] Figure 1 It is a schematic flowchart of a control method for an intelligent mobility assistance system provided by an embodiment of the present application;

[0023] Figure 2 It is a schematic block diagram of a control device for an intelligent mobility assistance system provided by an embodiment of the present application. Detailed Embodiments

[0024] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0025] The flowchart shown in the accompanying drawings is only an example illustration, and does not necessarily include all the contents and operations / steps, nor does it necessarily need to be executed in the described order. For example, some operations / steps can also be decomposed, combined, or partially merged. Therefore, the actual execution order may change according to the actual situation.

[0026] It should also be understood that the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. As used in the specification of this application and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms.

[0027] It should be further understood that the term "and / or" used in the specification of this application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0028] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of a control method for an intelligent mobility assistance system provided by an embodiment of this application. As Figure 1 shown, the specific steps of the control method of the intelligent mobility assistance system include: S101 - S105.

[0029] S101. When entering the task increment mode, obtain the available power value of the mobility robot, and divide the mobility robot into a first robot and a second robot according to the available power value.

[0030] Exemplarily, in the control system of a mobility robot, when the number of received tasks is greater than a preset increment threshold, it will enter the task increment mode. The preset increment threshold can be determined according to the number of mobility robots or the execution situation of historical tasks. The scenarios of the task increment mode include: factories, restaurants, and airports. Even during normal operations, due to unforeseen factors (such as weather changes, holiday effects, etc.), there may be more task requests than usual during certain periods. Adopting the task increment mode can make the mobility assistance system more flexible in dealing with these fluctuations and ensure that the service is always efficient and reliable. Before reallocating tasks, it is necessary to obtain the available battery level value of the mobility robot. The available battery level value is the difference between the current battery level value of the mobility robot and the return battery level value. The return battery level value is the battery level required for the farthest path between the task point and the charging pile.

[0031] When classifying robot types, a preset battery level threshold needs to be used as the classification basis. The preset battery level threshold can be set manually or determined according to historical data. For example, during the task increment mode, the initial battery level values of the mobility robots that need to be charged are statistically analyzed, and the largest one among the above initial battery level values is used as the preset battery level threshold.

[0032] The first type of robot (high battery level): The first type of robot can undertake multi-floor or cross-regional food delivery tasks because they have enough battery power to support long-term operations. For example, during the lunch peak period, these robots can be responsible for delivering food from the first-floor restaurant to high-rise guest rooms.

[0033] The second type of robot (low battery level): The second type of robot is more suitable for performing tasks within the same floor or near the available charging piles. For example, they can specifically serve the rooms near the elevator entrance, so that even with a low battery level, they can quickly return to the available charging piles to replenish energy and ensure continuous service capabilities.

[0034] The classification strategy of mobility robots based on the battery level value is one of the key factors to improve the scheduling efficiency in the task increment mode, which ensures that a high-efficiency and stable service level can be maintained whether facing daily operations or sudden high-demand situations.

[0035] S102. Generate a task distribution density map based on the published tasks and the preset navigation map. The task distribution density map includes multiple task-intensive areas.

[0036] Exemplarily, create a task distribution density map according to the published tasks and the preset navigation map. The task distribution density map will indicate the task-intensive degree of each area, that is, where there are more task requirements. Usually, this involves a comprehensive analysis of factors such as task locations, time requirements, and task types.

[0037] It should be noted that the task distribution density map can be two-dimensional or three-dimensional. For example, a two-dimensional task distribution density map is established in a flat factory, and a three-dimensional task distribution density map is established in a multi-story hotel. Combined with the current visual neural network, processing based on the task distribution density map can efficiently divide the task area.

[0038] It should also be noted that the task-intensive area must meet the following conditions: 1. The area of the task-intensive area is larger than the preset area; 2. The task path density in the task-intensive area is larger than the preset density threshold. In this way, after a fully charged walking robot completes the task in the task-intensive area, the remaining power value is 15%-25%.

[0039] Presenting it in a visual way can help decision makers intuitively see the hot spots where tasks are concentrated, providing a basis for the next step of task allocation.

[0040] S103: Determine available charging piles according to the task-intensive area and a preset navigation map, and obtain charging location information of the available charging piles.

[0041] For example, after determining the task-intensive areas, it is also necessary to identify the available charging piles in and around these task-intensive areas and collect the specific location information of the available charging piles. This is crucial for making a charging plan, especially for the second robots with low power.

[0042] It should be noted that the available charging piles are those in an idle state. There may be multiple charging piles in the scene, and other mobility robots may be charging. The charging piles in an idle state (no mobility robot is charging) are available charging piles.

[0043] By adding the specific location information of available charging stations, the work area can be planned more reasonably, allowing the mobility robot to replenish energy in time while completing the task, ensuring service continuity. In addition, this also provides an important reference point for the subsequent division of the work area.

[0044] S104. If the number of task-intensive areas is greater than the number of first robots, determine the first operating area and the second operating area according to the task distribution density map and the charging position information, wherein the number of first operating areas is equal to the number of first robots, and the second operating area includes at least one available charging pile.

[0045] Exemplarily, if it is found that the number of task-intensive areas exceeds the number of first robots (robots with high battery levels), then the second robot is required to assist in completing the corresponding work. Two types of working areas are defined based on the task distribution density map and the location information of available charging piles: the first working area and the second working area. The number of the first working areas is exactly equal to the number of first robots, which means that each such area will be solely responsible for by a robot with sufficient battery power. For the second working area, at least one available charging pile is included in its design so that multiple second robots with lower battery levels can take turns to execute tasks and charge in due course.

[0046] It should be noted that when it is detected that the number of task-intensive areas exceeds the number of first robots (robots with high battery levels), the second working area is preferentially planned to ensure that the second working area is the closest to the available charging pile in the task-intensive areas, and then the first working area is planned.

[0047] After confirming that there are task-intensive areas exceeding the number of first robots, the second working area is divided based on whether it is close to the available charging pile. A key feature of the second working area is that it includes at least one available charging pile. The reason for doing this is to solve the energy replenishment problem of the second robots. By arranging these second robots in positions close to the charging piles, it is convenient for them to take turns to charge during the task execution intervals, thereby extending their working cycles. The available charging piles in the second working area only allow the robots corresponding to the second working area to use them in the task increment mode.

[0048] In some embodiments, when ensuring that there are enough available charging piles, the first working area can also be preferentially determined. These first working areas are usually assigned to those robots with sufficient battery power to execute tasks. The selection criteria for the first working area may be based on multiple factors, such as the task urgency, the expected completion time, the complexity of the tasks within the area, etc. The goal is to ensure that each first working area can be efficiently processed by a first robot.

[0049] Through the above solution, the intelligent mobility assistance system can achieve the effective allocation of resources and ensure good operating performance even when facing a complex and changeable working environment. It not only improves the utilization rate of a single mobility robot but also enhances the ability of the entire system to cope with emergencies.

[0050] S105. Control the first robot to execute the tasks included in a first working area respectively, and control multiple second robots to take turns to execute the tasks included in a second working area.

[0051] Exemplarily, instructions are sent to the first robots respectively, enabling each of the first robots to undertake all tasks within a first operation area. For the second operation area, a rotation system is adopted, and multiple second robots execute the tasks in this area in sequence or as needed.

[0052] This method not only ensures the efficient utilization of limited resources even during peak periods, but also takes into account the battery life of the mobility robots, avoiding a decline in overall efficiency caused by excessive use of individual robots. Through this refined management, the entire intelligent mobility assistance system can maintain a highly efficient and stable operating state when facing a large number of concurrent requests.

[0053] To more clearly introduce the technical solution of this application, the technical solution of this application will also be introduced through specific embodiments below. It should be noted that the specific embodiments are used to expand the description of the technical solution of this application, rather than limiting this application.

[0054] In some embodiments, determining available charging piles according to the task-intensive area and a preset navigation map includes: determining working charging piles and non-working charging piles according to the preset navigation map. Determining an expansion area according to the available power value of the second robot, and determining an expansion region according to the expansion area and the task-intensive area. If the number of working charging piles in the expansion region is greater than a preset difference value, set the non-working charging piles corresponding to the preset difference value as available charging piles.

[0055] Exemplarily, according to the preset navigation map, first identify the positions of all known charging piles. Further distinguish these charging piles into two states: "working" and "non-working". A "working charging pile" is a charging pile currently in use; while a "non-working charging pile" is an idle charging pile. Based on the available power value of the second robot, calculate a reasonable "expansion area". This area is estimated based on the maximum movement range that the remaining power of the robot can cover. The specific value of the expansion area can be calculated according to empirical data in actual applications or a preset formula. For example, the average feasible distance at different power levels can be obtained through historical data analysis, and then the corresponding area can be deduced. Combining the information of the task-intensive area, according to the expansion area calculated above, determine an "expansion region" around the task-intensive area. This region aims to cover all potential task points that may require additional charging pile support. The boundary of the expansion region should consider the maximum feasible distance from the task point to the nearest charging pile to ensure that the robot can return to charge even in the most unfavorable situation. Select non-working charging piles corresponding to the preset difference value and set them as available charging piles. The preset difference value is the difference between the task-intensive area and the first robot. The selection criteria can be factors such as these charging piles being closer to the task-intensive area and easy to reach.

[0056] By dynamically allocating work areas, all available resources can be utilized more effectively during peak task periods, avoiding service interruptions caused by insufficient charging piles and providing more charging opportunities for robots with low battery levels, enabling them to maintain sufficient power while performing tasks, thus extending the endurance time of the entire team.

[0057] In some embodiments, a task distribution density map is generated based on the published tasks and a preset navigation map. The task distribution density map includes multiple task-intensive areas, including: determining the task start position information according to the published tasks. Generating a task path planning map according to the preset path planning algorithm, the task start position information, and the preset navigation map. The task path planning map includes multiple task paths. Dividing the task path planning map into multiple first grid cells, and determining the task path density in the first grid cells according to the multiple task paths and the first grid cells. Setting the first grid cells with a task path density greater than a preset first density threshold as second grid cells. Determining the task-intensive areas according to the preset density clustering algorithm, the preset distance weighting parameter, and the second grid cells.

[0058] Exemplarily, according to the published tasks, obtain the starting positions of each published task. These position information are based on user requirements or preset task points. Using the preset path planning algorithm, combined with the task starting positions and the preset navigation map, one or more possible paths will be generated for each task. These paths take into account factors such as obstacles and terrain, and optimize the route to reduce time and energy consumption. The generated task path planning map includes multiple task paths, and each path represents a feasible route for one or more tasks from the starting point to the end point. Divide the entire navigation map into a series of first grid cells of the same size. For each first grid cell, calculate its task path density according to the number of task paths passing through this cell. The task path density reflects the degree of task concentration in a specific area. Set a first density threshold as a criterion, and mark those first grid cells with task path density greater than this threshold as second grid cells. The second grid cells represent areas with a high degree of task concentration. Use the preset density clustering algorithm (such as DBSCAN) to process all second grid cells. The algorithm parameters include the neighborhood radius and the minimum number of neighborhood points, which are used to identify closely connected high-density areas. The result is to initially define some initial task areas and the third grid cells not included therein. For each second grid cell in the initial task area, calculate the first weighted distance value between them using the preset distance weighting function. Based on the first weighted distance value, further divide the initial task area into over-large areas and over-small areas. Reclassify the second grid cells on the edge of the over-large area as third grid cells for subsequent adjustment. Calculate the second weighted distance value between the third grid cells and the over-small areas. According to the second weighted distance value, assign the third grid cells to the closest over-small areas, thereby updating the initial task area to the first updated area and the second updated area. Finally, use the Voronoi diagram technology to construct the boundaries of each area and perform smoothing processing to obtain the final distribution of task-intensive areas.

[0059] Through the effective planning of the task path, the unnecessary moving distance is reduced, thereby reducing the energy consumption of the robot and extending the running time after a single charge. By scientifically analyzing the task distribution, it is possible to more quickly and accurately identify the areas with a high degree of task concentration, which helps to formulate a more reasonable robot scheduling strategy.

[0060] In some embodiments, determining a task-intensive area according to a preset clustering algorithm, a preset distance weighting parameter, and a second grid cell includes: performing density clustering processing on the second grid cell according to a preset neighborhood radius and a preset minimum number of neighborhood points to obtain an initial task area and a third grid cell outside the initial task area. Determining a first weighted distance value of each second grid cell in the initial task area according to a preset distance weighting function. Dividing the initial task area into an over-large area and an over-small area according to the first weighted distance value. Setting the second grid cells at the edge of the over-large area as the third grid cell. Calculating a second weighted distance value between the third grid cell and the over-small area. Assigning the third grid cell to the corresponding over-small area according to the second weighted distance value, updating the over-large area to a first updated area, and updating the over-small area to a second updated area. Constructing a Voronoi diagram based on the first updated area and the second updated area, and performing boundary smoothing processing to generate a task-intensive area.

[0061] Exemplarily, density clustering processing is performed on the second grid cells using a preset neighborhood radius and a minimum number of neighborhood points. The neighborhood radius defines the range considered around each cell, while the minimum number of neighborhood points specifies the minimum number of cells required to form a cluster. Through a density clustering algorithm (such as DBSCAN), regions with higher density are identified as initial task regions, and at the same time, the third grid cells not within these regions are determined. For each second grid cell in the initial task region, a preset distance weighting function is applied to calculate its first weighted distance value from other cells within the region. The distance weighting function can be based on Euclidean distance, Manhattan distance, or other suitable distance metrics, and combined with a weight factor to reflect the relative importance or closeness between cells. According to the first weighted distance value, the initial task region is divided into over-large regions and over-small regions. Over-large regions refer to those regions where the distance between internal cells is large and the distribution is sparse; while over-small regions are those where the distance between internal cells is small and the distribution is relatively concentrated. The specific division criteria can be set according to actual needs, for example, by setting a threshold to distinguish over-large regions and over-small regions. The second grid cells on the edge of the over-large region are reclassified as third grid cells to reduce the area of the over-large region and make it more compact. The second weighted distance value between the third grid cells and the over-small regions is calculated, and then the third grid cells are assigned to the nearest over-small regions according to these distance values, thereby updating the boundaries of the over-large regions and over-small regions. Based on the first updated region and the second updated region, a Voronoi diagram is constructed. The Voronoi diagram is a spatial partitioning method that divides the plane into several regions, each region containing all positions that are closer to a specific point than to any other point. The boundary of the generated Voronoi diagram is smoothed to eliminate unnecessary sharp corners and irregular shapes, making the boundary of the task-dense area more natural and smooth. After the above steps, an optimized distribution of task-dense areas is obtained. These task-dense areas not only reflect the actual distribution of tasks but also consider the efficiency of path planning and robot scheduling.

[0062] In some embodiments, if the number of task-dense areas is less than the number of first robots, the method further includes: detecting the task path density of the task-dense areas. The task-dense areas with a task path density greater than a preset second density threshold are set as the first working areas, and the task-dense areas with a task path density less than or equal to the preset second density threshold are set as the second working areas. The first robots are respectively set as third robots and fourth robots, where the number of third robots is equal to the number of second working areas. The third robots are respectively controlled to execute the tasks included in one second working area. Multiple fourth robots are controlled to jointly execute the tasks included in one first working area, or, multiple second robots are controlled to take turns to jointly execute the tasks included in one first working area with the third robots.

[0063] Exemplarily, when the number of task-intensive areas is less than the number of the first robots, it is first necessary to evaluate each task-intensive area. The actual workload of the task-intensive area is determined by calculating the task path density of each grid cell in the task path planning graph. Those task-intensive areas with a task path density higher than the preset second density threshold are defined as the first working areas. These areas need to be processed first because of the large amount of tasks. Conversely, the task-intensive areas with a task path density lower than or equal to the second density threshold are defined as the second working areas. These areas may contain fewer tasks or be more sparsely distributed. Select sufficient robots (the number of which is equal to the number of the first working areas) from the existing first robots as the third robots. The third robots will be specifically responsible for executing the tasks within the second working areas. The remaining first robots are assigned as the fourth robots. The fourth robots can jointly execute the tasks in a first working area or cooperate with the second robots to complete the tasks. The third robots will independently travel to their respective second working areas and execute all the tasks assigned to them within that area. For the first working areas, multiple fourth robots can be selected to work together to improve efficiency, or the fourth robots and the second robots can take turns to execute the tasks, which can take into account the charging requirements of the robots while ensuring the completion of the tasks. During the actual operation process, the configuration of the third robots and the fourth robots can be adjusted according to the real-time situation. For example, if the tasks in a certain second working area are completed in advance, the third robot originally responsible for that area can be reassigned to other task-intensive areas or assist in processing the tasks in the first working areas. Similarly, for the second working areas, the number of participating robots and the combination method are dynamically adjusted according to the changes in tasks and the robot status to ensure the maximization of resource utilization.

[0064] By dividing the task-intensive areas into the first working areas and the second working areas according to the task path density, and accordingly reassigning the robot roles as the third robots and the fourth robots, this strategy optimizes the work distribution of the robots, ensuring that the high-density task areas can be processed first, while the low-density task areas can also be effectively covered. This not only improves the overall work efficiency, but also ensures the effective utilization of the power of each robot through reasonable scheduling, enhancing the flexibility and adaptability of the system.

[0065] In some embodiments, controlling multiple second robots to take turns to execute tasks included in a second operation area includes: setting a second robot with a larger available power value as an on-duty robot, and setting the other second robot as a standby robot. Controlling the on-duty robot to execute tasks included in the second operation area, and controlling the standby robot to charge at an available charging pile corresponding to the second operation area. When the available power value of the on-duty robot is lower than a preset first power threshold, or when the available power value of the standby robot is greater than a preset second power threshold, controlling the standby robot to execute tasks included in the second operation area, and controlling the on-duty robot to charge at an available charging pile corresponding to the second operation area.

[0066] Exemplarily, in the second operation area, multiple second robots are divided into an on-duty robot and a standby robot according to the available power value. Specifically, one with a larger power value is selected as the on-duty robot to be responsible for executing tasks; while the other with a lower power value is used as the standby robot to prepare for charging or standby. The on-duty robot starts to execute tasks within the second operation area. During the execution process, its available power value is continuously monitored to ensure that it can successfully complete the assigned tasks. At the same time, the standby robot is controlled to go to an available charging pile within or near the second operation area for charging. This can ensure that the standby robot can replace the on-duty robot in time when needed. Monitor whether the available power value of the on-duty robot is lower than a preset first power threshold, or whether the available power value of the standby robot is higher than a preset second power threshold. If the power of the on-duty robot is lower than the first power threshold, it indicates that it may not be able to continue to complete the remaining tasks, and a switch is needed at this time. If the power of the standby robot is higher than the second power threshold, it indicates that it has been fully charged and can take over the work of the on-duty robot. When either of the above conditions is met, an immediate role switch is made. The standby robot becomes the new on-duty robot and starts to execute the unfinished tasks. The original on-duty robot then becomes the new standby robot and goes to the charging pile for charging to prepare for the next task. Continuously monitor the status of the two robots and continuously adjust their roles according to the actual situation to ensure the continuity and efficiency of the tasks.

[0067] In some embodiments, dividing the mobility robots into first robots and second robots according to the available power value includes: setting the mobility robots with available power values within a preset first power value range as first robots. Setting the mobility robots with available power values within a preset second power value range as second robots.

[0068] Exemplarily, when entering the task increment mode, first collect the current available power data of all the mobility robots with tasks to be assigned. This step is the basis for classifying the robot types. Define two preset power value ranges: the first power value range and the second power value range. These two ranges are set according to the actual requirements and the working performance of the robots. The first power value range usually represents a relatively high power level and is suitable for performing tasks with a long duration or distance. The second power value range represents a relatively low but still sufficient power level, which is suitable for performing tasks with a short duration or distance and is convenient for quick charging rotation.

[0069] According to the current task requirements and the specific conditions of each operation area, flexibly adjust the ratio of the first robot and the second robot to ensure the maximization of the overall working efficiency while maintaining good energy management.

[0070] Please refer to Figure 2 , Figure 2 FIG. is a schematic block diagram of a control device of an intelligent mobility assistance system provided by an embodiment of the present application. The control device 200 of the intelligent mobility assistance system is used to execute the control method of the foregoing intelligent mobility assistance system. Among them, the control device 200 of the intelligent mobility assistance system can be configured in a server.

[0071] Among them, the server can be an independent server, a server cluster, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms.

[0072] As Figure 2 shown, the control device 200 of the intelligent mobility assistance system includes: a power measurement module 201, a task management module 202, a charging control module 203, a region division module 204, and a motion control module 205.

[0073] The power measurement module 201 is used to obtain the available power value of the mobility robot when entering the task increment mode, and classify the mobility robot into a first robot and a second robot according to the available power value.

[0074] The task management module 202 is used to generate a task distribution density map according to the published tasks and the preset navigation map. The task distribution density map includes a plurality of task-intensive areas.

[0075] The charging control module 203 is used to determine the available charging piles according to the task-intensive areas and the preset navigation map, and obtain the charging position information of the available charging piles.

[0076] The area division module 204 is configured to, if the number of task-intensive areas is greater than the number of first robots, determine a first operation area and a second operation area according to the task distribution density map and the charging position information, where the number of first operation areas is equal to the number of first robots, and the second operation area includes at least one available charging pile.

[0077] The motion control module 205 is configured to control the first robot to execute the tasks included in a first operation area respectively, and control multiple second robots to take turns to execute the tasks included in a second operation area.

[0078] An embodiment of the present application provides an electronic device, which includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement the control method of the intelligent mobility assistance system according to any one of the embodiments of the present application when executing the computer program.

[0079] An embodiment of the present application provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the processor is caused to implement the control method of the intelligent mobility assistance system according to any one of the embodiments of the present application.

[0080] As described above, the above are only specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A control method for an intelligent mobility assistance system, characterized in that, The method includes: When entering the task increment mode, obtaining the available power value of the mobility robot, setting the mobility robot with the available power value within a preset first power value range as the first robot, and setting the mobility robot with the available power value within a preset second power value range as the second robot, where the power level corresponding to the preset first power value range is higher than the power level corresponding to the preset second power value range; Generating a task distribution density map according to the published tasks and a preset navigation map, where the task distribution density map includes multiple task dense areas; Determining available charging piles according to the task dense areas and the preset navigation map, and obtaining the charging position information of the available charging piles; If the number of the task dense areas is greater than the number of the first robots, determining a first operation area and a second operation area according to the task distribution density map and the charging position information, where the number of the first operation areas is equal to the number of the first robots, and the second operation area includes at least one of the available charging piles; Controlling the first robot to execute the tasks included in one of the first operation areas respectively, and controlling multiple second robots to execute the tasks included in one of the second operation areas in turn.

2. The control method of the intelligent walking assistance system according to claim 1, characterized in that, The determining the available charging piles according to the task dense areas and the preset navigation map includes: Determining working charging piles and non-working charging piles according to the preset navigation map; Determining an expansion area according to the available power value of the second robot, and determining an expansion region according to the expansion area and the task dense areas; If the number of the working charging piles in the expansion region is greater than a preset difference value, setting the non-working charging piles corresponding to the preset difference value as the available charging piles.

3. The control method of the intelligent mobility assistance system according to claim 1, characterized in that The generating a task distribution density map according to the published tasks and a preset navigation map, where the task distribution density map includes multiple task dense areas, includes: Determining task start position information according to the published tasks; Generating a task path planning map according to a preset path planning algorithm, the task start position information and the preset navigation map, where the task path planning map includes multiple task paths; Dividing the task path planning map into multiple first grid units, and determining the task path density in the first grid unit according to the multiple task paths and the first grid unit; Setting the first grid units with the task path density greater than a preset first density threshold as second grid units; Determining the task dense areas according to a preset density clustering algorithm, a preset distance weighting parameter and the second grid units.

4. The control method of the intelligent walking assistance system according to claim 3, characterized in that The determining the task dense areas according to a preset clustering algorithm, a preset distance weighting parameter and the second grid units includes: Performing density clustering processing on the second grid units according to a preset neighborhood radius and a preset minimum neighborhood point number, to obtain an initial task area and third grid units outside the initial task area; Determining a first weighted distance value of each of the second grid units in the initial task area respectively according to a preset distance weighting function; Divide the initial task area into an oversized area and an undersized area according to the first weighted distance value; Set the second grid cell at the edge of the oversized area as the third grid cell; Calculate the second weighted distance value between the third grid cell and the undersized area; Allocate the third grid cell to the corresponding undersized area according to the second weighted distance value, update the oversized area to a first updated area, and update the undersized area to a second updated area; Construct a Voronoi diagram based on the first updated area and the second updated area, and perform boundary smoothing to generate the task dense area.

5. The control method of the intelligent walking assistance system according to claim 1, characterized in that If the number of task dense areas is less than the number of the first robots, the method further includes: Detect the task path density of the task dense area; Set the task dense area with a task path density greater than a preset second density threshold as a first operation area, and set the task dense area with a task path density less than or equal to the preset second density threshold as a second operation area; Set the first robots as third robots and fourth robots respectively, where the number of the third robots is equal to the number of the second operation areas; Control the third robots to execute the tasks included in one of the second operation areas respectively; Control multiple fourth robots to jointly execute the tasks included in one of the first operation areas, or control multiple second robots to take turns to jointly execute the tasks included in one of the first operation areas with the third robots.

6. The control method of the intelligent walking assistance system according to claim 1, characterized in that, The controlling multiple second robots to take turns to execute the tasks included in one of the second operation areas includes: Set the second robot with a larger available power value as an on-duty robot, and set the other second robot as a standby robot; Control the on-duty robot to execute the tasks included in the second operation area, and control the standby robot to charge at the corresponding available charging pile in the second operation area; When the available power value of the on-duty robot is lower than a preset first power threshold, or the available power value of the standby robot is greater than a preset second power threshold, control the standby robot to execute the tasks included in the second operation area, and control the on-duty robot to charge at the corresponding available charging pile in the second operation area.

7. A control device for an intelligent walking assistance system, characterized in that, The control device of the intelligent walking assistance system includes: A power measurement module, configured to obtain the available power value of the walking robot when entering the task increment mode, set the walking robot with the available power value in a preset first power value range as a first robot, and set the walking robot with the available power value in a preset second power value range as a second robot, where the power level corresponding to the preset first power value range is higher than the power level corresponding to the preset second power value range; A task management module, configured to generate a task distribution density map according to the published tasks and a preset navigation map, where the task distribution density map includes multiple task dense areas; A charging control module, configured to determine available charging piles according to the task-intensive area and the preset navigation map, and obtain the charging position information of the available charging piles; An area division module, configured to, if the number of the task-intensive areas is greater than the number of the first robots, determine a first operation area and a second operation area according to the task distribution density map and the charging position information, wherein the number of the first operation areas is equal to the number of the first robots, and the second operation area includes at least one of the available charging piles; A motion control module, configured to control the first robots to execute the tasks included in one of the first operation areas respectively, and control a plurality of the second robots to execute the tasks included in one of the second operation areas in turn.

8. An electronic device, characterized in that, The electronic device includes a memory and a processor; The memory is configured to store a computer program; The processor is configured to execute the computer program and implement the control method of the intelligent walking assistance system according to any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor is caused to implement the control method of the intelligent walking assistance system according to any one of claims 1 to 6.

Images