Sweeping machine path planning method and device, sweeping machine and storage medium
By dividing the working area of the robot vacuum cleaner into zones and pre-building an underlying map, the problem of insufficient efficiency and accuracy in path planning of robot vacuum cleaners in complex environments is solved, achieving efficient and accurate path planning and adapting to environmental changes.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- QINGDAO TAPER ROBOTICS CO LTD
- Filing Date
- 2024-11-27
- Publication Date
- 2026-06-05
AI Technical Summary
In existing technologies, the efficiency and accuracy of path planning for robotic vacuum cleaners are poor when the environment is complex or the working area is large.
Using a zoning approach, the working area of the robot vacuum cleaner is divided into multiple zones. A bottom-level map is pre-built for each zone, and the path is planned using the upper-level map. Path planning is performed only for the zones to be traversed. Sub-paths are planned within each zone in combination with the bottom-level map, and only the zones that change are updated when the environment changes.
It improves the efficiency and accuracy of robot vacuum cleaner path planning, enabling it to quickly determine the path and avoid obstacles, adapting to complex or changing environments.
Smart Images
Figure CN122149448A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of smart home technology, and in particular to a method, device, robot vacuum cleaner path planning, and storage medium. Background Technology
[0002] As a smart home product, robotic vacuum cleaners focus on automated cleaning, achieving efficient floor cleaning through a variety of advanced technologies. With the continuous advancement of artificial intelligence and sensor technology, robotic vacuum cleaners have made significant improvements in navigation and operation capabilities.
[0003] In some applications, robotic vacuum cleaners need to plan and navigate their paths based on their current location and the target location specified in the cleaning command, ensuring they can move from their current location to the destination in the most efficient way. Some exemplary technologies leverage the advantages of Dijkstra's algorithm and combine it with heuristic search to effectively find the optimal path from start to finish in a home environment. By flexibly handling dynamic obstacles and complex layouts, this provides strong support for the intelligent navigation of robotic vacuum cleaners, enabling them to complete cleaning tasks more efficiently and improve the user's quality of life.
[0004] However, in some application scenarios, such as when the robot vacuum cleaner has a large working area or a complex environment, it takes a long time to determine the final path, and it may even be difficult to find an optimal path. Therefore, in existing technologies, the efficiency and accuracy of robot vacuum cleaner path planning are poor when the environment is complex or the working area is large. Summary of the Invention
[0005] This application provides a method, device, sweeper, and storage medium for sweeping robot path planning, which solves the shortcomings of the prior art in terms of poor efficiency and accuracy of sweeping robot path planning in complex environments or large working areas, thereby improving the efficiency and accuracy of sweeping robot path planning in complex environments or large working areas.
[0006] This application provides a path planning method for a robotic vacuum cleaner, the method comprising the following steps.
[0007] Determine the current location and target location of the sweeper.
[0008] Based on the current position and target position of the sweeping machine, an algorithm is invoked to access the upper-level map corresponding to the entire working area of the sweeping machine, and the partition to be traversed is determined from all partitions corresponding to the entire working area of the sweeping machine; wherein, the upper-level map is composed of the lower-level map corresponding to all partitions.
[0009] Based on the underlying map corresponding to each zone to be traversed, plan the sub-path of the robot vacuum in each zone to be traversed.
[0010] All sub-paths to be traversed are concatenated to obtain the complete path from the current position to the target position.
[0011] The beneficial effects of the above steps are as follows: By adopting the concept of partitioning, the robot vacuum only needs to plan the path through each partition, allowing it to quickly determine the path from its current location to the target location, thus improving the efficiency of path planning. Furthermore, based on the underlying map, the robot vacuum can plan a more precise path within each partition, effectively avoiding obstacles and improving the accuracy of its path planning. Therefore, these steps improve the efficiency and accuracy of the robot vacuum's path planning, especially in complex environments or large work areas.
[0012] According to the sweeping robot path planning method provided in this application, before determining the current position and target position of the sweeping robot, the method further includes the following steps.
[0013] The entire working area of the sweeper is divided into multiple zones.
[0014] For each partition, a path pre-construction process is performed to obtain the underlying map corresponding to the partition; wherein, the path pre-construction process includes: using a path planning algorithm to calculate the shortest path between each edge in the partition and other edges; constructing the underlying map corresponding to the partition, and storing the shortest paths between different edges in the partition into the underlying map corresponding to the partition.
[0015] The upper-level map is obtained by combining the underlying maps corresponding to all partitions.
[0016] The beneficial effects of the above steps are: by partitioning and pre-building the underlying map, efficient, accurate, flexible and scalable path planning is achieved, improving the efficiency and accuracy of the robot vacuum cleaner's path planning.
[0017] According to the sweeping robot path planning method provided in this application, the current position of the sweeping robot and the target position of the sweeping robot are located in non-adjacent partitions; the partitions to be traversed include a starting partition, an ending partition, and at least one intermediate partition; wherein, the starting partition is the partition where the current position of the sweeping robot is located; and the ending partition is the partition where the target position of the sweeping robot is located.
[0018] The step of planning the sub-path of the sweeping robot in each partition to be traversed based on the underlying map of that partition includes: Based on the underlying maps corresponding to the starting and ending partitions, the robot vacuum cleaner plans its sub-paths in the starting and ending partitions, respectively.
[0019] For each intermediate partition, determine the starting and ending edges of the robot vacuum in the intermediate partition, and select the sub-path of the robot vacuum in the intermediate partition from the shortest paths between different edges pre-stored in the underlying map corresponding to the intermediate partition based on the starting and ending edges of the robot vacuum in the intermediate partition.
[0020] The beneficial effects of the above steps are as follows: based on the detailed path information stored in the underlying map, the path planning of the intermediate zone can directly select the shortest path of the robot vacuum cleaner in the intermediate zone from the path information stored in the underlying map, which can improve the efficiency of path planning.
[0021] According to the robot vacuum cleaner path planning method provided in this application, after performing path pre-construction processing for each partition to obtain the underlying map corresponding to the partition, the method further includes the following steps.
[0022] If a layout change of the partition is detected, the path pre-construction process is performed on the partition with the layout change, the underlying map corresponding to the partition is updated, and the upper-layer map is updated.
[0023] The benefits of the above steps are as follows: when the layout of the zones changes, only the changed zones are updated, rather than the entire work area, saving computing resources and time. Furthermore, by updating the zones with changed layouts in a timely manner, the robot vacuum cleaner can quickly adapt to environmental changes without having to replan the path of the entire work area, thus improving the robot vacuum cleaner's response speed to environmental changes.
[0024] According to the sweeping robot path planning method provided in this application, the entire working area of the sweeping robot is divided into multiple zones, including: Obtain a cleaning map of the entire working area of the robot vacuum cleaner; Based on the cleaning map corresponding to the entire working area of the sweeping machine, the entire working area of the sweeping machine is divided into multiple zones through image morphology operations.
[0025] The beneficial effects of the above steps are as follows: Firstly, by dividing the work area into multiple partitions, the computational load of a single path planning task can be reduced, thereby improving the overall efficiency of path planning. Secondly, by dividing the work area into multiple partitions, more refined path planning at the partition level can be performed, which is better suited to path planning in complex environments and improves the accuracy and reliability of path planning.
[0026] According to the sweeping robot path planning method provided in this application, the current position of the sweeping robot and the target position of the sweeping robot are located in adjacent partitions; the partition to be traversed includes a starting partition and an ending partition; wherein, the starting partition is the partition where the current position of the sweeping robot is located; and the ending partition is the partition where the target position of the sweeping robot is located. The step of planning the sub-path of the sweeping robot in each partition to be traversed based on the underlying map of that partition includes: Based on the underlying maps corresponding to the starting and ending partitions, the robot vacuum cleaner plans its sub-paths in the starting and ending partitions, respectively.
[0027] The benefits of the above steps are twofold: First, by planning sub-paths separately for the starting and ending zones, the robot vacuum cleaner's path in these two key areas can be more precise, improving the overall accuracy of path planning. Second, planning paths only for the starting and ending zones reduces computational resource consumption compared to calculating the path for the entire work area.
[0028] According to the robot vacuum cleaner path planning method provided in this application, the step of concatenating all sub-paths of the zone to be traversed to obtain a complete path from the current position to the target position includes: Based on the current position and target position of the sweeper, determine the order in which the sweeper will pass through all the zones to be traversed. Based on the order in which the sweeping machine passes through all the zones to be traversed, the sub-paths of all the zones to be traversed are combined to obtain the complete path from the current position to the target position.
[0029] The beneficial effect of the above steps is that efficient, accurate, and continuous path planning is achieved by systematically planning and combining partitioned paths.
[0030] This application also provides a path planning device for a sweeping robot, the device comprising the following modules.
[0031] The location determination module is used to determine the current location and target location of the sweeper.
[0032] The partition determination module is used to perform an algorithm call on the upper-level map corresponding to the entire working area of the sweeping machine based on the current position and the target position of the sweeping machine, and determine the partition to be passed through from all partitions corresponding to the entire working area of the sweeping machine; wherein, the upper-level map is composed of the lower-level map corresponding to all partitions.
[0033] The zoning planning module is used to plan the sub-path of the robot vacuum cleaner in each zoning zone based on the underlying map corresponding to each zoning zone.
[0034] The connection processing module is used to concatenate all the sub-paths to be traversed by the partition to obtain the complete path from the current position to the target position.
[0035] The beneficial effects of the above modules are as follows: By adopting a zoned approach, the robot vacuum only needs to plan the path through each zone, allowing it to quickly determine the path from its current location to the target location, thus improving path planning efficiency. Furthermore, based on the underlying map, the robot vacuum can plan a more precise path within each zone, effectively avoiding obstacles and improving the accuracy of its path planning. Therefore, these steps improve the efficiency and accuracy of the robot vacuum's path planning, especially in complex environments or large work areas.
[0036] This application also provides a sweeping robot, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of any of the sweeping robot path planning methods described above.
[0037] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the sweeping robot path planning method described above.
[0038] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of any of the above-described robot vacuum cleaner path planning methods.
[0039] The robotic vacuum cleaner path planning method, device, robotic vacuum cleaner, and storage medium provided in this application adopt a partitioning approach. Through pre-constructed upper and lower level maps, the partitions to be traversed can be accurately and quickly determined. Path planning only needs to be performed on the partitions to be traversed, allowing the robotic vacuum cleaner to quickly determine the path from its current position to the target position. This avoids the need for real-time calculation of the entire work area, enabling the robotic vacuum cleaner to perform effective path planning even under limited resources, thus significantly improving the efficiency of path planning. Furthermore, based on the lower level map, the robotic vacuum cleaner can plan more precise paths within each partition, effectively avoiding obstacles and improving the accuracy of path planning. Moreover, because the path for each partition is calculated and stored independently, environmental changes only affect the path of a specific partition, not the entire work area. Therefore, the solution of this invention can adapt to complex or constantly changing environments. In summary, the solution of this invention, especially in complex environments or large work areas, can improve the efficiency and accuracy of robotic vacuum cleaner path planning. Attached Figure Description
[0040] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0041] Figure 1 This is a schematic diagram of the hardware environment for an interaction method of a smart device according to an embodiment of this application.
[0042] Figure 2 This is a flowchart illustrating the path planning method for the sweeping robot provided in this application.
[0043] Figure 3 This is a schematic diagram of the work area provided in this application.
[0044] Figure 4 This is a schematic diagram of the path planning device for the sweeping machine provided in this application.
[0045] Figure 5 This is a structural schematic diagram of the sweeper provided in this application. Detailed Implementation
[0046] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0047] It should be noted that the terms "first," "second," etc., in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0048] According to one aspect of the embodiments of this application, a robot vacuum cleaner path planning method is provided. This robot vacuum cleaner path planning method is widely used in whole-house intelligent digital control application scenarios such as smart homes, smart home ecosystems, and intelligence house ecosystems. Optionally, in this embodiment, the above-mentioned robot vacuum cleaner path planning method can be applied to, for example... Figure 1 The hardware environment shown consists of terminal device 102 and server 104. For example... Figure 1 As shown, server 104 is connected to terminal device 102 via a network and can be used to provide services (such as application services) to the terminal or clients installed on the terminal. A database can be set up on the server or independently of the server to provide data storage services for server 104. Cloud computing and / or edge computing services can be configured on the server or independently of the server to provide data processing services for server 104.
[0049] The aforementioned network may include, but is not limited to, at least one of the following: wired network, wireless network. The aforementioned wired network may include, but is not limited to, at least one of the following: wide area network, metropolitan area network, local area network. The aforementioned wireless network may include, but is not limited to, at least one of the following: Wi-Fi (Wireless Fidelity), Bluetooth. The terminal device 102 may not be limited to PC, mobile phone, tablet computer, smart air conditioner, smart range hood, smart refrigerator, smart oven, smart stove, smart washing machine, smart water heater, smart washing equipment, smart dishwasher, smart projector, smart TV, smart clothes rack, smart curtains, smart audio-visual equipment, smart socket, smart speaker, smart speaker box, smart fresh air equipment, smart kitchen and bathroom equipment, smart bathroom equipment, smart robot vacuum cleaner, smart window cleaning robot, smart mopping robot, smart air purifier, smart steam oven, smart microwave oven, smart water heater, smart air purifier, smart water dispenser, smart door lock, etc.
[0050] The technical solution of this application and how it solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The following is a combination of... Figure 2 and Figure 3 This application describes the path planning method for a robotic vacuum cleaner.
[0051] In practical applications, the execution entity of this robot vacuum cleaner path planning method can be a robot vacuum cleaner path planning device. There are various ways to implement robot vacuum cleaner path planning, such as through computer programs (e.g., application software); or through chips; or through media storing relevant computer programs (e.g., USB flash drives, cloud storage); or through physical devices integrating or installing relevant computer programs (e.g., servers, smart devices).
[0052] Figure 2 This is a flowchart illustrating the robot vacuum cleaner path planning method provided in this application, as shown below. Figure 2 As shown, the path planning method for the sweeping robot includes steps 201 to 204.
[0053] Step 201: Determine the current position and target position of the sweeper.
[0054] The current position of the robot vacuum cleaner is the starting position of this path planning. In this embodiment, the method for determining the robot vacuum cleaner's current position is not specifically limited. For example, the robot vacuum cleaner is equipped with various sensors, including but not limited to LiDAR, ultrasonic sensors, infrared sensors, and cameras. By fusing the data collected by these sensors, the robot vacuum cleaner can accurately determine its current position. As another example, the robot vacuum cleaner integrates a navigation module, which can be used to determine its current position. Yet another example is that by utilizing changes in the strength of Wi-Fi, Bluetooth, or other wireless signals, the robot vacuum cleaner uses wireless positioning technology to estimate its position relative to the wireless transmitter, thereby determining its current position.
[0055] Specifically, the target location of the robot vacuum cleaner can be determined based on instructions issued by the user. In practical applications, when a user needs to clean a target area, they issue instructions to the robot vacuum cleaner, including the target location and cleaning mode. Accordingly, the robot vacuum cleaner determines its target location based on the user's instructions, and plans and navigates its path based on its current location and the target location, enabling it to move from its current location to the target location.
[0056] Step 202: Based on the current position and target position of the sweeping machine, the algorithm calls the upper-level map corresponding to the entire working area of the sweeping machine to determine the partition to be passed through from all the partitions corresponding to the entire working area of the sweeping machine.
[0057] The upper-layer map is composed of the lower-layer maps corresponding to all zones. In practical applications, the entire working area is pre-divided into multiple zones, and a corresponding lower-layer map is built for each zone. The upper-layer map is then combined with the lower-layer maps corresponding to all zones. The upper-layer map is responsible for planning paths at a larger scale, determining the transfer path of the robot vacuum from one zone to another, and the zones that the robot vacuum needs to pass through from its current position to the target position. The lower-layer map is responsible for planning specific cleaning paths at a smaller scale, that is, within each zone, ensuring that the robot vacuum can navigate effectively within the zone.
[0058] Specifically, the bottom-layer map refers to the map corresponding to each zone, which stores detailed path information within that zone. The top-layer map is a higher-level map composed of these bottom-layer maps. In the top-layer map, each zone is treated as a whole, without involving the specific details within each zone, and is used for path planning at a more macroscopic level. This layered map concept is designed to optimize the path planning efficiency of robot vacuums. By storing the path information within each zone in the bottom-layer map and performing macroscopic path planning on the top-layer map, the overall path planning speed can be accelerated.
[0059] The following is combined Figure 3 The process of determining the partitions to be processed is illustrated by example. Figure 3 This is a schematic diagram of the work area provided in this application, such as... Figure 3 As shown, the entire working area of the robot vacuum cleaner is divided into 9 zones, namely zone 31, zone 32, zone 33, zone 34, zone 35, zone 36, zone 37, zone 38 and zone 39.
[0060] For example, the current position of the robot vacuum is located in partition 31, and the target position of the robot vacuum is located in partition 38. Specifically, based on the current position and the target position of the robot vacuum, an algorithm is called on the upper-level map corresponding to the entire working area of the robot vacuum to determine that the partitions to be traversed are partition 31, partition 32, partition 33, partition 35, partition 39 and partition 38 in sequence.
[0061] It is understandable that the upper-level map is constructed from the lower-level map as basic units. Whether a basic unit is reachable depends on whether there is a reachable path within the upper basic unit. If there is, it means that it is reachable. In the upper-level map, the starting point and the ending point are the partition where the robot vacuum cleaner is currently located (starting partition) and the partition where the robot vacuum cleaner's target location is located (ending partition), respectively. Based on the above conditions, the path in the upper-level map can be calculated using the shortest path algorithm, and thus the partitions to be traversed can be determined.
[0062] Step 203: Based on the underlying map corresponding to each zone to be traversed, plan the sub-path of the robot vacuum in each zone to be traversed.
[0063] Step 204: Concatenate all sub-paths of the partitions to be traversed to obtain the complete path from the current position to the target position.
[0064] In practical applications, based on the current position and target position of the sweeper, path planning can be divided into three cases: the current position and target position of the sweeper are in the same zone; the current position and target position of the sweeper are in adjacent zones; and the current position and target position of the sweeper are not in adjacent zones.
[0065] Specifically, when the current position and the target position of the robot vacuum cleaner are in the same partition, the robot vacuum cleaner can be planned in the partition based on the underlying map corresponding to the partition where the robot vacuum cleaner is located, so as to obtain the complete path from the current position to the target position.
[0066] Specifically, when the robot vacuum's current position and its target position are not in adjacent zones, the zones to be traversed include: the starting zone, the ending zone, and the intermediate zones. Based on the underlying map corresponding to each zone, a sub-path for the robot vacuum in each zone is planned. All sub-paths from each zone are then concatenated to obtain the complete path from the current position to the target position.
[0067] As an example, in one possible implementation, the current position and the target position of the sweeping machine are located in non-adjacent partitions; the partitions to be traversed include a starting partition, an ending partition, and at least one intermediate partition; wherein, the starting partition is the partition where the current position of the sweeping machine is located; and the ending partition is the partition where the target position of the sweeping machine is located.
[0068] Step 103 above includes: Based on the underlying maps corresponding to the starting and ending partitions, plan the sub-paths of the robot vacuum cleaner in the starting and ending partitions respectively; For each intermediate partition, determine the starting and ending edges of the robot vacuum in the intermediate partition, and select the sub-path of the robot vacuum in the intermediate partition from the shortest paths between different edges pre-stored in the underlying map corresponding to the intermediate partition based on the starting and ending edges of the robot vacuum in the intermediate partition.
[0069] In practical applications, the underlying map stores the shortest paths from each edge of a partition to other edges. Specifically, for the intermediate partition, the shortest path between the starting and ending edges of the robot vacuum cleaner in the intermediate partition is selected directly from the multiple shortest paths stored in the underlying map, based on the robot vacuum cleaner's starting and ending edges in the intermediate partition. This shortest path between the starting and ending edges of the intermediate partition is then used as the robot vacuum cleaner's sub-path in the intermediate partition.
[0070] For the starting zone, determine the boundary line where the robot vacuum leaves the starting zone, and combine it with... Figure 3 Partition 31 is the starting partition, and partition 38 is the ending partition. The robot vacuum cleaner sequentially passes through partitions 31, 32, 33, 35, 39, and 38. Therefore, the boundary line where the robot vacuum cleaner leaves the starting partition is the boundary line between partitions 31 and 32. Furthermore, according to the shortest path algorithm, the shortest path between the starting position of the robot vacuum cleaner and the boundary line is calculated, thus obtaining the sub-path of the robot vacuum cleaner in the starting partition.
[0071] Continue to combine Figure 3 For the ending partition, the boundary line for the robot vacuum to enter the ending partition is determined. The boundary line for the robot vacuum to enter the partition is the boundary line between partition 38 and partition 39. Further, according to the shortest path algorithm, the shortest path between this boundary line and the target position of the robot vacuum is calculated to obtain the sub-path of the robot vacuum in the ending partition.
[0072] In this embodiment, based on the detailed path information stored in the underlying map, the path planning of the intermediate partition can directly select the shortest path of the sweeping robot in the intermediate partition from the path information stored in the underlying map, which can improve the efficiency of path planning.
[0073] Conversely, when the current position and the target position of the robot vacuum are in adjacent zones, the robot vacuum's sub-paths in these two zones are planned based on the underlying maps corresponding to these two zones. Combining the sub-paths of these two zones will yield the complete path from the current position to the target position.
[0074] As an example, in one possible implementation, the current position and the target position of the robot vacuum are located in adjacent partitions; the partitions to be traversed include a starting partition and an ending partition; wherein, the starting partition is the partition where the current position of the robot vacuum is located; and the ending partition is the partition where the target position of the robot vacuum is located.
[0075] Step 103 includes: Based on the underlying maps corresponding to the starting and ending partitions, plan the sub-paths of the robot vacuum cleaner in the starting and ending partitions respectively.
[0076] Combination Figure 3For example, if the current position of the robot vacuum is in partition 31, then partition 31 is the starting partition; if the target position of the robot vacuum is in partition 32, then partition 32 is the ending partition.
[0077] Specifically, the boundary line or transfer point for the robot vacuum to move from the starting zone to the ending zone is determined. For the starting zone, the shortest path algorithm is used to calculate the shortest path between the robot vacuum's starting position and the boundary line (or transfer point), thus obtaining the robot vacuum's sub-path in the starting zone.
[0078] For the ending partition, the shortest path algorithm is used to calculate the shortest path between the boundary line (transfer point) and the target position of the sweeper, thus obtaining the sub-path of the sweeper in the ending partition.
[0079] In this embodiment, on the one hand, by planning sub-paths separately for the starting and ending zones, the robot vacuum cleaner's path in these two key areas can be more precise, improving the overall accuracy of path planning. On the other hand, planning paths only for the starting and ending zones reduces the consumption of computing resources compared to calculating the path for the entire work area.
[0080] Furthermore, after planning the sub-path of each partition to be traversed by the sweeper, it is necessary to generate the complete path between the sweeper's current position and its target position.
[0081] As an example, in one possible implementation, step 104 above includes: Based on the current position and target position of the sweeper, determine the order in which the sweeper will pass through all the zones to be traversed. Based on the order in which the robot vacuum passes through all the zones to be traversed, the sub-paths of all the zones to be traversed are combined to obtain the complete path from the current location to the target location.
[0082] In this embodiment, efficient, accurate, and continuous path planning is achieved by systematically planning and combining partitioned paths.
[0083] In this embodiment, a partitioning approach is adopted. Only path planning is needed within the partitions to be traversed, allowing the robot vacuum to quickly determine the path from its current location to the target location, thus improving path planning efficiency. Furthermore, based on the underlying map, the robot vacuum can plan more precise paths within each partition, effectively avoiding obstacles and improving the accuracy of its path planning. Therefore, the above steps improve the efficiency and accuracy of the robot vacuum's path planning, especially in complex environments or large work areas.
[0084] In practical applications, before path planning, the entire working area of the robot vacuum cleaner needs to be divided into multiple zones, and a bottom-level map corresponding to each zone and a top-level map corresponding to the entire working area need to be constructed. Specifically, in one possible implementation, before step 101 above, the method further includes: The entire working area of the sweeper is divided into multiple zones; For each partition, perform path pre-construction processing to obtain the underlying map corresponding to the partition; the path pre-construction processing includes: using a path planning algorithm to calculate the shortest path between each edge in the partition and other edges; constructing the underlying map corresponding to the partition, and storing the shortest paths between different edges in the partition into the underlying map corresponding to the partition; Combine the underlying maps corresponding to all partitions to obtain the upper-level map.
[0085] In practical applications, when dividing the entire work area into zones, the principle of zoning is to ensure that the area and obstacles in each zone are as evenly distributed as possible. For example, combining... Figure 3 The entire work area is divided into multiple zones by using relatively obvious obstacles as boundaries.
[0086] Specifically, in one example, the entire working area of the robot vacuum cleaner is divided into multiple zones, including: Obtain a cleaning map of the entire working area of the robot vacuum cleaner; Based on the cleaning map corresponding to the entire working area of the robot vacuum, the entire working area of the robot vacuum is divided into multiple zones through image morphology operations.
[0087] In practical applications, when a user uses a robotic vacuum cleaner for the first time, the machine will perform a full cleaning task to familiarize itself with the environment. The robot uses sensor data to identify room boundaries, including walls, furniture, and other obstacles. Users can set virtual walls or no-go zones via the app, instructing the robot to avoid specific areas during cleaning. As the robot moves through the room, it updates the cleaning map in real time, marking cleaned and uncleaned areas. Once the cleaning map is complete, the robot saves it to its internal storage and syncs it with the user's app, allowing the user to view and edit the cleaning map.
[0088] For example, regarding the implementation of partitioning, obstacles and non-obstacle areas in a clean map can be clearly distinguished by the computer; for instance, obstacles are generally black and identified as 0, while non-obstacle areas are generally white and identified as 1. Furthermore, the clean map image can be partitioned based on morphological operations.
[0089] Morphological operations on images include erosion and dilation. Erosion shrinks the boundaries of objects inward, removing fine noise and isolated pixels, and can be used to separate closely connected objects. Its mathematical definition is: for each pixel, if all corresponding structuring element pixels in its neighborhood are 1, then the pixel is preserved. Dilation expands the boundaries of objects outward. Its mathematical definition is: for each pixel, if at least one pixel in its neighborhood is 1, then the pixel is set to 1.
[0090] In practical applications, erosion can expand the area of black regions, while dilation can shrink them. Based on this characteristic, we can use erosion to partition a clean map. First, by applying erosion multiple times, the area of obstacles (black regions) on the map will become larger. This will divide the white areas of the map into several disconnected regions (regions without connection). Rendering these disconnected regions with different colors, merging them with the original image, and then dilating them will divide the image into different regions.
[0091] In this example, on the one hand, dividing the work area into multiple partitions reduces the computational load of a single path planning task, thereby improving the overall efficiency of path planning. On the other hand, dividing the work area into multiple partitions allows for more granular path planning at the partition level, which is better suited to path planning in complex environments and improves the accuracy and reliability of path planning.
[0092] Furthermore, after dividing the entire working area of the robot vacuum cleaner into multiple partitions, it is necessary to construct the underlying map corresponding to each partition. In the process of constructing the underlying map, the shortest path from each edge in the partition to other edges is calculated and stored.
[0093] Specifically, a point needs to be determined between zones, that is, a point needs to be determined on the boundary of each zone, to help the robot vacuum move between zones. Generally, the midpoint of the boundary line between adjacent zones is selected as the transfer point. If there is an obstacle between adjacent zones, the midpoint of the longest segment of the boundary line without obstacles is selected as the transfer point (the obstacle may divide the boundary line into multiple segments, and the midpoint of the longest segment is selected).
[0094] Specifically, in the lower-level map (within the partition), it is composed of 0 and 1 as basic units (0 for unobstructed and 1 for obstructed). When it is unobstructed, it means that the basic unit can be reached. Since the area of the partition is not too large, the path within the partition is calculated using the shortest path algorithm. After the calculation is completed, a storage device is needed to store it.
[0095] For example, in a partition, to calculate the shortest path from one edge to another edge, one can calculate the shortest path between the transition points on that edge and the transition points on the other edge, and take the shortest path between the transition points on that edge and the transition points on the other edge as the shortest path from that edge to the other edge.
[0096] Understandably, the shortest path from each edge to other edges is pre-stored in the underlying map. When the robot vacuum needs to traverse an entire partition, for example, if a partition is an intermediate partition, the shortest path for the robot vacuum to traverse that partition can be directly obtained from the pre-stored path information, which can improve the efficiency of path planning.
[0097] In this embodiment, efficient, accurate, flexible and scalable path planning is achieved by partitioning and pre-building the underlying map, which improves the efficiency and accuracy of the robot vacuum cleaner's path planning.
[0098] In addition, it should be noted that during the actual operation of the robot vacuum cleaner, the upper-layer map and the lower-layer map segments need to be continuously maintained. If changes are found in a certain area during the actual use of the robot vacuum cleaner, the lower-layer map needs to be regenerated and all paths in that segment need to be recalculated based on the changes.
[0099] As an example, in one possible implementation, after performing path pre-construction processing for each partition to obtain the underlying map corresponding to the partition, the method further includes: If a layout change of the partition is detected, then for the partition with the layout change, path pre-construction processing is performed to update the underlying map corresponding to the partition and update the upper-level map.
[0100] In this implementation, when the layout of the zones changes, only the changed zones are updated, rather than the entire work area, saving computing resources and time. Furthermore, by updating the zones with changed layouts in a timely manner, the robot vacuum cleaner can quickly adapt to environmental changes without having to replan the path of the entire work area, thus improving the robot vacuum cleaner's response speed to environmental changes.
[0101] The robot vacuum path planning method provided in this embodiment adopts a partitioning approach. Through pre-constructed upper and lower level maps, the partitions to be traversed can be accurately and quickly determined. Only path planning needs to be performed on the partitions to be traversed; the robot vacuum can quickly determine the path from its current position to the target position, avoiding the need for real-time calculation of the entire work area. This allows the robot vacuum to perform effective path planning even under limited resources, significantly improving path planning efficiency. Furthermore, based on the lower level map, the robot vacuum can plan more precise paths within each partition, effectively avoiding obstacles and improving the accuracy of path planning. Moreover, because the path for each partition is calculated and stored independently, environmental changes only affect the path of a specific partition, not the entire work area. Therefore, the solution of this invention can adapt to complex or constantly changing environments. In summary, the solution of this invention, especially in complex environments or large work areas, can improve the efficiency and accuracy of robot vacuum path planning.
[0102] The sweeping machine path planning device provided in this application is described below. The sweeping machine path planning device described below can be referred to in correspondence with the sweeping machine path planning method described above.
[0103] Figure 4 This is a schematic diagram of the path planning device for the sweeping machine provided in this application, as shown below. Figure 4 As shown, the above-mentioned sweeping robot path planning device includes: a location determination module 41, a zone determination module 42, a zone planning module 43, and a connection processing module 44.
[0104] The position determination module 41 is used to determine the current position and the target position of the sweeper. The partition determination module 42 is used to perform algorithm calls on the upper-level map corresponding to the entire working area of the sweeping machine based on the current position and target position of the sweeping machine, and determine the partition to be passed through from all partitions corresponding to the entire working area of the sweeping machine; wherein, the upper-level map is composed of the lower-level map corresponding to all partitions.
[0105] The zoning planning module 43 is used to plan the sub-path of the robot vacuum cleaner in each zoning zone based on the underlying map corresponding to each zoning zone.
[0106] The connection processing module 44 is used to concatenate all the sub-paths to be traversed by the partition to obtain a complete path from the current position to the target position.
[0107] In some embodiments, the above-described apparatus further includes: The partitioning module is used to divide the entire working area of the sweeper into multiple zones; The construction module is used to perform path pre-construction processing for each partition to obtain the underlying map corresponding to the partition. The path pre-construction processing includes: using a path planning algorithm to calculate the shortest path between each edge in the partition and other edges; constructing the underlying map corresponding to the partition; and storing the shortest paths between different edges in the partition into the underlying map corresponding to the partition. The combination module is used to combine the underlying maps corresponding to all partitions to obtain the upper-level map.
[0108] In some embodiments, the current position and the target position of the robot vacuum cleaner are located in non-adjacent partitions; the partitions to be traversed include a starting partition, an ending partition, and at least one intermediate partition; wherein, the starting partition is the partition where the current position of the robot vacuum cleaner is located; and the ending partition is the partition where the target position of the robot vacuum cleaner is located.
[0109] The aforementioned partition planning module 43 is specifically used for: planning the sub-paths of the robot vacuum cleaner in the starting partition and the ending partition according to the underlying maps corresponding to the starting partition and the ending partition respectively; for each intermediate partition, determining the starting edge and the ending edge of the robot vacuum cleaner in the intermediate partition, and selecting the sub-path of the robot vacuum cleaner in the intermediate partition from the shortest paths between different edges pre-stored in the underlying map corresponding to the intermediate partition according to the starting edge and the ending edge of the robot vacuum cleaner in the intermediate partition.
[0110] In some embodiments, the above apparatus further includes: an update module, configured to, if a layout change of a partition is detected, perform path pre-construction processing on the partition with the layout change, update the underlying map corresponding to the partition, and update the upper-layer map.
[0111] In some embodiments, the above-mentioned partitioning module is specifically used to: obtain a cleaning map corresponding to the entire working area of the sweeping machine; and based on the cleaning map corresponding to the entire working area of the sweeping machine, divide the entire working area of the sweeping machine into multiple partitions through image morphology operations.
[0112] In some embodiments, the current position and the target position of the robot vacuum cleaner are located in adjacent partitions; the partitions to be traversed include a starting partition and an ending partition; wherein, the starting partition is the partition where the current position of the robot vacuum cleaner is located; and the ending partition is the partition where the target position of the robot vacuum cleaner is located.
[0113] The partition planning module 43 is specifically used to: plan the sub-path of the sweeping robot in the starting partition and the ending partition according to the underlying map corresponding to the starting partition and the ending partition respectively.
[0114] In some embodiments, the connection processing module 44 is specifically used to: determine the order in which the sweeping machine passes through all the partitions to be passed according to the current position and the target position of the sweeping machine; and combine the sub-paths of all the partitions to be passed according to the order in which the sweeping machine passes through all the partitions to be passed to obtain a complete path from the current position to the target position.
[0115] The robot vacuum path planning device provided in this embodiment adopts a partitioning approach. Through pre-built upper and lower level maps, the partitions to be traversed can be accurately and quickly determined. Only path planning is needed for these partitions; the robot vacuum can quickly determine the path from its current position to the target position, avoiding the need for real-time calculation of the entire work area. This allows the robot vacuum to perform effective path planning even with limited resources, significantly improving path planning efficiency. Furthermore, based on the lower level map, the robot vacuum can plan more precise paths within each partition, effectively avoiding obstacles and improving the accuracy of path planning. Moreover, because the path for each partition is calculated and stored independently, environmental changes only affect the path of a specific partition, not the entire work area. Therefore, the solution of this invention can adapt to complex or constantly changing environments. In summary, the solution of this invention, especially in complex environments or large work areas, can improve the efficiency and accuracy of robot vacuum path planning.
[0116] Figure 5 This is a structural schematic diagram of the sweeper provided in this application, as shown below. Figure 5 As shown, the robotic vacuum cleaner may include a processor 510, a communication interface 520, a memory 530, and a communication bus 540. The processor 510, communication interface 520, and memory 530 communicate with each other via the communication bus 540. The processor 510 can call logical instructions from the memory 530 to execute the robotic vacuum cleaner's path planning method.
[0117] Furthermore, the logical instructions in the aforementioned memory 530 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0118] On the other hand, this application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions, and when the program instructions are executed by a computer, the computer is able to execute the sweeping robot path planning method provided by the above methods.
[0119] In another aspect, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the aforementioned sweeping robot path planning methods.
[0120] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.
[0121] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.
[0122] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.
Claims
1. A path planning method for a sweeping robot, characterized in that, The method includes: Determine the current location and target location of the sweeper; Based on the current position and target position of the sweeping machine, an algorithm is invoked to access the upper-level map corresponding to the entire working area of the sweeping machine, and the partition to be passed through is determined from all partitions corresponding to the entire working area of the sweeping machine; wherein, the upper-level map is composed of the lower-level map corresponding to all partitions; Based on the underlying map corresponding to each zone to be traversed, plan the sub-path of the robot vacuum in each zone to be traversed; All sub-paths to be traversed are concatenated to obtain the complete path from the current position to the target position.
2. The sweeping machine path planning method according to claim 1, characterized in that, Before determining the current position and target position of the sweeper, the method further includes: The entire working area of the sweeper is divided into multiple zones; For each partition, a path pre-construction process is performed to obtain the underlying map corresponding to the partition; wherein, the path pre-construction process includes: using a path planning algorithm to calculate the shortest path between each edge in the partition and other edges; constructing the underlying map corresponding to the partition, and storing the shortest paths between different edges in the partition into the underlying map corresponding to the partition; The upper-level map is obtained by combining the underlying maps corresponding to all partitions.
3. The sweeping machine path planning method according to claim 2, characterized in that, The current position and the target position of the sweeping machine are located in non-adjacent partitions; the partitions to be traversed include a starting partition, an ending partition, and at least one intermediate partition; wherein, the starting partition is the partition where the current position of the sweeping machine is located; and the ending partition is the partition where the target position of the sweeping machine is located. The step of planning the sub-path of the robot vacuum cleaner in each zone to be traversed, based on the underlying map corresponding to each zone, includes: Based on the underlying maps corresponding to the starting and ending partitions, respectively, plan the sub-paths of the robot vacuum cleaner in the starting and ending partitions; For each intermediate partition, determine the starting and ending edges of the robot vacuum in the intermediate partition, and select the sub-path of the robot vacuum in the intermediate partition from the shortest paths between different edges pre-stored in the underlying map corresponding to the intermediate partition based on the starting and ending edges of the robot vacuum in the intermediate partition.
4. The sweeping machine path planning method according to claim 2, characterized in that, After performing path pre-construction processing for each partition to obtain the underlying map corresponding to the partition, the method further includes: If a layout change of the partition is detected, the path pre-construction process is performed on the partition with the layout change, the underlying map corresponding to the partition is updated, and the upper-layer map is updated.
5. The sweeping machine path planning method according to claim 2, characterized in that, The entire working area of the sweeper is divided into multiple zones, including Obtain a cleaning map of the entire working area of the robot vacuum cleaner; Based on the cleaning map corresponding to the entire working area of the sweeping machine, the entire working area of the sweeping machine is divided into multiple zones through image morphology operations.
6. The sweeping machine path planning method according to claim 1, characterized in that, The current position and the target position of the sweeping machine are located in adjacent partitions; the partitions to be traversed include a starting partition and an ending partition; wherein, the starting partition is the partition where the current position of the sweeping machine is located; and the ending partition is the partition where the target position of the sweeping machine is located. The step of planning the sub-path of the robot vacuum cleaner in each zone to be traversed, based on the underlying map corresponding to each zone, includes: Based on the underlying maps corresponding to the starting and ending partitions, the robot vacuum cleaner plans its sub-paths in the starting and ending partitions, respectively.
7. The sweeping machine path planning method according to any one of claims 1-6, characterized in that, The step of concatenating all sub-paths of the partitions to be traversed to obtain the complete path from the current position to the target position includes: Based on the current position and target position of the sweeper, determine the order in which the sweeper will pass through all the zones to be traversed. Based on the order in which the sweeping machine passes through all the zones to be traversed, the sub-paths of all the zones to be traversed are combined to obtain the complete path from the current position to the target position.
8. A path planning device for a sweeping machine, characterized in that, The device includes: The location determination module is used to determine the current location and target location of the sweeper. The partition determination module is used to perform an algorithm call on the upper-level map corresponding to the entire working area of the sweeping machine based on the current position and the target position of the sweeping machine, and determine the partition to be passed through from all partitions corresponding to the entire working area of the sweeping machine; wherein, the upper-level map is composed of the lower-level map corresponding to all partitions; The zoning planning module is used to plan the sub-path of the robot vacuum cleaner in each zoning zone based on the underlying map corresponding to each zoning zone. The connection processing module is used to concatenate all the sub-paths to be traversed by the partition to obtain the complete path from the current position to the target position.
9. A sweeping machine, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the sweeping robot path planning method as described in any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the sweeping robot path planning method as described in any one of claims 1 to 7.