Robot cleaning path planning method and device and floor washing robot

Abstract

The invention relates to the technical field of path planning, in particular to a robot cleaning path planning method and device and a ground washing robot, and the method comprises the steps that map information of a cleaning area is acquired, and the map information comprises ground materials and coverage area information; according to the map information, a sweeping route is planned on the road surface of the same material based on the sweeping starting point; acquiring indoor position information of the sweeper and synchronously displaying the indoor position information on the map information; distance information between the sweeper and the joint of the road surfaces made of the two materials is calculated on the map information, when the distance information is smaller than a preset value, a camera is started to recognize different road surface materials, and cleaning tools are automatically switched; and re-planning a cleaning line corresponding to the road surface of the cleaning tool based on the coordinates of the junction.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and in particular to a robot cleaning path planning method, device and a floor cleaning robot. Background Art

[0002] Cleaning robots are automated cleaning devices that are mainly used for floor cleaning in homes, commercial places, industrial facilities and public spaces. They use technologies such as lidar, visual sensors and infrared sensors to sense and locate the environment, use advanced path planning algorithms to efficiently cover the cleaning area, and avoid obstacles in real time. Cleaning robots usually have functions such as vacuuming, mopping and automatic charging. They can be remotely controlled through smartphone apps or voice assistants, preset cleaning times, and achieve scheduled tasks.

[0003] In factories or warehouses, the ground environment is often complex, generally with a variety of road surfaces such as cement, tiles, carpets, etc. These road surfaces require robots to use different cleaning media for cleaning, but existing robots generally only have one cleaning device, and it is not convenient to identify the material inside, so they cannot complete the factory cleaning task well. Summary of the invention

[0004] The purpose of the present invention is to provide a robot cleaning path planning method, device and floor cleaning robot, which are designed to effectively cope with complex and changeable indoor environments and significantly improve the overall efficiency and quality of cleaning work.

[0005] To achieve the above-mentioned object, in a first aspect, the present invention provides a robot cleaning path planning method, comprising obtaining map information of a cleaning area, wherein the map information includes ground material and coverage area information;

[0006] Planning a cleaning route on a road surface of the same material based on the cleaning starting point according to the map information;

[0007] Obtain the indoor location information of the sweeper and display it on the map information synchronously;

[0008] The distance between the road sweeper and the junction of two road materials is calculated based on the map information. When the distance is less than the preset value, the camera is activated to identify different road materials and the cleaning tool is automatically switched.

[0009] The cleaning route of the road surface corresponding to the cleaning tool is replanned based on the coordinates of the junction.

[0010] After replanning the cleaning route of the road surface corresponding to the cleaning tool based on the coordinates of the junction, the method further includes: detecting the cleaning effect and optimizing the spacing of the moving path.

[0011] The specific steps of obtaining the map information of the cleaning area include:

[0012] Use LiDAR to scan the contours of the cleaned area and generate a two-dimensional map;

[0013] The robot conducts autonomous exploration in the cleaning area, collecting material data using lidar and visual sensors;

[0014] According to the two-dimensional map on the map and the road material corresponding to the area, the coverage area of ​​roads with different materials is calculated respectively;

[0015] The coverage area information is marked on a two-dimensional map to form map information with coverage area information.

[0016] The specific steps of planning a cleaning route on a road surface of the same material based on the cleaning starting point according to the map information include:

[0017] Load the constructed map information;

[0018] Set the starting position of the cleaning robot;

[0019] According to the ground material information, the map is divided into multiple sub-areas, and the ground material in each sub-area is the same;

[0020] Generate the cleaning order of each sub-area based on the nearest neighbor priority strategy according to the starting position;

[0021] For each sub-area, use the Dijkstra algorithm to plan the cleaning path to ensure that all the ground in the sub-area is covered;

[0022] Connect the cleaning paths of each sub-area to form a complete cleaning route.

[0023] The specific steps of obtaining the indoor location information of the sweeper and synchronously displaying it on the map information include:

[0024] Pack the real-time location information and status data of the sweeper into a data packet;

[0025] Obtain indoor positioning data of the road sweeper;

[0026] Sending indoor positioning data to a central server via a wireless communication module;

[0027] Loading pre-built map information on a central server;

[0028] The location mark of the road sweeper is updated in real time on the map information.

[0029] The specific steps of calculating the distance information between the sweeper and the intersection of the two road materials on the map information, starting the camera to identify different road materials when the distance information is less than a preset value, and automatically switching the cleaning tool include:

[0030] Identify road areas of different materials on the map;

[0031] Calculate the distance between the sweeper and each road surface intersection;

[0032] When the distance between the sweeper and the road surface is less than a preset value, the camera is started to capture ground image data;

[0033] Use pre-trained deep learning models to classify ground image data and identify the material of the current road surface;

[0034] Select the corresponding cleaning tool based on the identified road material.

[0035] The specific steps of replanning the cleaning route of the road surface corresponding to the cleaning tool based on the coordinates of the junction include:

[0036] Update map information based on the identified road material;

[0037] Use Dijkstra algorithm to plan new cleaning paths to ensure that new road areas are covered;

[0038] Connect the new cleaning path with the existing cleaning path to form a complete cleaning line.

[0039] The specific steps of detecting the cleaning effect and optimizing the spacing of the moving path include:

[0040] Use a camera to capture images of the cleaned ground;

[0041] Use edge detection algorithms to identify uncleaned areas;

[0042] According to the image processing results, determine whether there is an uncleaned gap, and determine the coordinates and range of the uncleaned area;

[0043] Adjust the spacing of the cleaning paths and re-plan the cleaning paths based on the extent of the uncleaned area.

[0044] In a second aspect, the present invention further provides a robot cleaning path planning device, including a map information generation module, a first path planning module, an information synchronization module, a cleaning tool switching module, and a second path planning module:

[0045] The map information generation module is used to obtain map information of the cleaning area, and the map information includes ground material and coverage area information;

[0046] The first path planning module is used to plan a cleaning route on a road surface of the same material based on the cleaning starting point according to the map information;

[0047] The information synchronization module is used to obtain the indoor location information of the sweeper and synchronously display it on the map information;

[0048] The cleaning tool switching module is used to calculate the distance information between the cleaning vehicle and the intersection of the two road materials on the map information, and when the distance information is less than a preset value, the camera is activated to identify different road materials and the cleaning tool is automatically switched;

[0049] The second path planning module is used to re-plan the cleaning route of the road surface corresponding to the cleaning tool based on the coordinates of the junction.

[0050] In a third aspect, the present invention further provides a floor cleaning robot, comprising the above-mentioned robot cleaning path planning device.

[0051] The robot cleaning path planning method, device and floor cleaning robot of the present invention can obtain map information of the cleaning area through high-precision sensors or pre-recorded data. This information not only includes the basic outline of the cleaning area, but also records in detail the material of the ground (such as hard floor, carpet, etc.) and the coverage area of ​​each material area. This step is crucial for subsequent path planning because it provides the robot with the necessary environmental cognition.

[0052] After obtaining the above map information, the robot will plan the optimal cleaning path on the road surface of the same material according to the starting point of the cleaning task. This process usually takes into account the principles of maximizing cleaning efficiency and avoiding repeated cleaning to ensure that the entire cleaning process is both efficient and thorough.

[0053] In order to achieve precise positioning, the robot will use the built-in positioning system (such as laser radar, ultrasonic sensor, etc.) to obtain its precise position indoors in real time, and synchronize this information to the internally stored map data in real time. This can not only help the robot adjust its route at any time, but also effectively avoid obstacles to ensure the smooth progress of cleaning work. When the robot approaches the junction of different road materials, the system automatically calculates the distance between the robot and these junctions. If the detected distance is less than the preset safety threshold, the robot will activate its visual recognition system and use the camera to accurately determine the specific material type of the road ahead. Once the new road material is determined, the robot will automatically adjust its cleaning device, such as replacing the brush or vacuum cleaner head suitable for a specific material, to ensure that the most appropriate cleaning method can be used for each floor. Based on the newly identified road material and its boundary coordinates, the robot will recalculate and optimize the cleaning path to ensure that all areas can be effectively cleaned. This dynamic adjustment mechanism not only improves the cleaning effect, but also greatly enhances the adaptability and flexibility of the robot.

[0054] This robot cleaning path planning method can not only effectively cope with complex and changeable indoor environments, but also significantly improve the overall efficiency and quality of cleaning work. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0056] Figure 1 It is a flow chart of a robot cleaning path planning method of the present invention.

[0057] Figure 2 It is a flowchart of obtaining map information of a cleaning area according to the present invention, wherein the map information includes ground material and coverage area information.

[0058] Figure 3 It is a flow chart of the present invention for planning a cleaning route on a road surface of the same material based on the cleaning starting point according to the map information.

[0059] Figure 4 It is a flow chart of the present invention for obtaining indoor position information of a cleaning vehicle and synchronously displaying it on map information.

[0060] Figure 5It is a flow chart of calculating the distance information between a sweeper and the intersection of two road materials on map information, starting a camera to identify different road materials when the distance information is less than a preset value, and automatically switching cleaning tools.

[0061] Figure 6 It is a flow chart of the present invention for replanning the cleaning route of the road surface corresponding to the cleaning tool based on the coordinates of the junction.

[0062] Figure 7 It is a flow chart of the present invention for detecting the cleaning effect and optimizing the spacing of the moving path. DETAILED DESCRIPTION

[0063] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0064] First embodiment

[0065] See also Figure 1 to Figure 7 The present invention provides a robot cleaning path planning method, comprising:

[0066] S101 obtains map information of the cleaning area, where the map information includes ground material and coverage area information;

[0067] The specific steps include:

[0068] The S201 uses LiDAR to scan the contours of the cleaned area and generate a two-dimensional map;

[0069] The robot first activates its built-in LiDAR system to scan the entire cleaning area. LiDAR can emit lasers and receive beams reflected from the surface of objects to measure distances. In this way, the robot can accurately draw the boundaries of the cleaning area to form a detailed two-dimensional map. This map will serve as the basis for subsequent steps.

[0070] The S202 robot conducts autonomous exploration in the cleaning area, using lidar and visual sensors to collect material data;

[0071] With a preliminary two-dimensional map, the robot begins to move in the cleaning area, turning on the visual sensor and lidar to work together to collect information about the ground material. The visual sensor can identify the color, texture and other characteristics of different materials, while the lidar helps the robot maintain a sense of direction and avoid obstacles. Combining these two technologies, the robot can accurately distinguish between hardwood floors, carpets, tiles and other surface types.

[0072] S203 calculates the coverage area of ​​roads of different materials according to the two-dimensional map on the map and the road materials corresponding to the area;

[0073] After collecting enough ground material data, the robot uses an algorithm to process this information and combine it with the previously created two-dimensional map. In this way, the robot can calculate the total area occupied by each ground material.

[0074] S204: marking the coverage area information on the two-dimensional map to form map information with the coverage area information.

[0075] The robot will mark various ground materials and their corresponding coverage areas on the generated two-dimensional map. This information is used to guide the robot's cleaning plan to ensure that each area can be properly cleaned. S102 plans a cleaning route on the road surface of the same material based on the cleaning starting point according to the map information;

[0076] The specific steps include:

[0077] S301 loads the constructed map information;

[0078] The robot needs to load the map information previously collected and processed by the lidar and visual sensors. This includes two-dimensional maps and information about the ground material and coverage area of ​​each area. Loading this data is to ensure that the robot can fully understand the layout and characteristics of the cleaning area, providing a basis for subsequent cleaning path planning.

[0079] S302 sets the starting position of the cleaning robot;

[0080] The robot needs to determine the starting point of the cleaning task. This starting position can be specified by the user, or the robot can automatically select a suitable location. Either way, it is very important to ensure the safety and accessibility of the starting position so that the robot can start the cleaning task smoothly.

[0081] S303: dividing the map into a plurality of sub-areas according to the ground material information, wherein the ground material in each sub-area is the same;

[0082] After determining the starting position, the robot will divide the entire cleaning area into multiple sub-areas based on the ground material information on the map. The ground material in each sub-area is the same. This division helps the robot use different cleaning modes for different ground materials and improve the cleaning effect.

[0083] S304 generates a cleaning order for each sub-area based on the nearest neighbor priority strategy according to the starting position;

[0084] To optimize cleaning efficiency, the robot uses the nearest neighbor priority strategy to determine the cleaning order. This means that the robot will first clean the sub-area closest to the current starting position, and then gradually expand to other sub-areas. This can reduce the time the robot spends moving between different sub-areas and increase the overall cleaning speed.

[0085] S305 plans a cleaning path for each sub-area using the Dijkstra algorithm to ensure that all ground surfaces in the sub-area are covered;

[0086] After determining the cleaning order, the robot will plan the path for each sub-area separately. The Dijkstra algorithm is used here, which is a classic shortest path algorithm suitable for weighted graphs. Through the Dijkstra algorithm, the robot can find the optimal path from the starting point to every corner in the sub-area, ensuring that no place is missed during the cleaning process. At the same time, this also ensures the consistency and efficiency of the cleaning path.

[0087] S306 connects the cleaning paths of the sub-areas to form a complete cleaning route.

[0088] The robot will integrate the cleaning paths of all sub-areas into a complete cleaning route. This route not only covers all areas that need to be cleaned, but also ensures a smooth transition between paths, reducing unnecessary backtracking and repeated cleaning. In this way, the robot can complete the entire cleaning task in the shortest time while ensuring cleaning quality.

[0089] S103 obtains indoor location information of the cleaning vehicle and synchronously displays it on the map information;

[0090] The specific steps include:

[0091] S401 packages the real-time location information and status data of the sweeper into a data packet;

[0092] The robot needs to collect its current real-time location information and status data. This information usually includes but is not limited to:

[0093] Position coordinates: The precise coordinates (x, y) of the robot in the room.

[0094] Direction angle: The current direction angle of the robot.

[0095] Working status: The current working status of the robot (such as cleaning, returning to the charging station, etc.).

[0096] Cleaning progress: the ratio of the completed cleaning area to the total cleaning area.

[0097] These data will be packaged into a data packet for subsequent transmission and processing.

[0098] S402 obtains indoor positioning data of the cleaning vehicle;

[0099] The robot needs to use its built-in indoor positioning system to obtain the current location information. The indoor positioning technologies that can be used include:

[0100] Inertial Measurement Unit (IMU): Detects the robot's movement and posture changes through accelerometers and gyroscopes.

[0101] Wi-Fi Signal Strength: Estimates location by analyzing the strength of surrounding Wi-Fi signals.

[0102] Bluetooth Beacons: Use Bluetooth beacons deployed indoors for precise positioning.

[0103] These technologies can be used alone or in combination to improve positioning accuracy and reliability.

[0104] S403 sends the indoor positioning data to the central server via the wireless communication module;

[0105] Once the indoor positioning data is acquired, the robot will send the data packet to the central server through the built-in wireless communication module (such as Wi-Fi, Bluetooth or 4G / 5G module). The choice of wireless communication module depends on the specific application scenario and network environment to ensure the stability and real-time performance of data transmission.

[0106] S404 loads pre-built map information on the central server;

[0107] The central server needs to load the pre-built cleaning area map information. This map contains detailed information such as the two-dimensional layout of the cleaning area, ground material, coverage area, etc. The purpose of loading this data is to accurately display the robot's position and status on the map.

[0108] S405 updates the location mark of the road sweeper on the map information in real time.

[0109] When the central server receives the data packet sent by the robot, it will parse the real-time location information and status data and update the robot's location mark on the map. The specific steps include:

[0110] Extract key information such as position coordinates and direction angles from the data packet. Move the robot's position marker on the map to ensure that it is consistent with the actual position. Display additional information such as the robot's working status and battery power on the map so that users can understand the robot's operation at any time.

[0111] Through these steps, users can view the robot's location and status in real time through the interface provided by the central server, so as to better manage and monitor the progress of the cleaning task.

[0112] S104 calculates the distance information between the sweeper and the intersection of the two road materials based on the map information, and when the distance information is less than a preset value, activates the camera to identify different road materials and automatically switches the cleaning tool;

[0113] The specific steps include:

[0114] S501 identifies road areas of different materials on the map;

[0115] The central server loads the pre-built cleaning area map information, which contains road areas of different materials. Different colors or marks are used on the map to distinguish road areas of different materials. For example, blue can be used to represent hardwood floors, green to represent carpets, and yellow to represent tiles. The boundary lines of each material road surface are recorded on the map, and these boundary lines will be used for subsequent distance calculations.

[0116] S502 calculates the distance between the sweeper and each road surface intersection;

[0117] Get the real-time location information of the sweeper from the central server, including coordinates (x, y) and direction angles. Use geometric algorithms to calculate the distance between the current location of the sweeper and each road intersection. These distances can be calculated using the nearest point algorithm or the straight-line distance algorithm. Store the calculated distance information in the central server for subsequent judgment and processing.

[0118] S503: when the distance between the sweeper and the intersection of the road surface is less than a preset value, start the camera to capture ground image data;

[0119] A distance threshold is preset, for example, 0.5 meters. When the distance between the sweeper and the road surface is less than this threshold, the camera is triggered to start. When the distance is less than the threshold, the central server sends a command to the sweeper to start the camera. The camera captures the image data of the current ground and sends the image data back to the central server.

[0120] S504 uses a pre-trained deep learning model to classify ground image data and identify the material of the current road surface;

[0121] The central server loads a pre-trained deep learning model, which has been trained with a large amount of image data of different ground materials and can accurately identify ground materials. The captured ground images are pre-processed, including cropping, scaling, normalization, etc., to meet the model input requirements. The pre-processed images are input into the deep learning model, and the model outputs the material category of the current ground, such as hardwood floor, carpet, tile, etc.

[0122] S505: Select a corresponding cleaning tool according to the identified road surface material.

[0123] Based on the identified floor material, the central server selects the appropriate cleaning tool. For example, for carpets, select the high suction mode; for hardwood floors, select the dry sweeping mode. The central server sends instructions to the sweeper to switch to the appropriate cleaning tool and mode. The sweeper continues the cleaning task based on the new cleaning tool and mode.

[0124] S105 replans a cleaning route corresponding to the cleaning tool road surface based on the coordinates of the junction.

[0125] The specific steps include:

[0126] S601 updates the map information according to the identified road surface material;

[0127] Obtain the ground material information captured by the camera and identified by the deep learning model from the central server. Update the material information of the corresponding area on the map. For example, if an area is identified to change from hardwood floor to carpet, mark the material of the area as carpet on the map. Record the coordinates of the intersection of different material roads, which will be used for subsequent path planning.

[0128] S602 uses the Dijkstra algorithm to plan a new cleaning path to ensure that new road areas are covered;

[0129] Initialize the Dijkstra algorithm on the central server, which is a classic algorithm for finding the shortest path between two points in a graph. Set the current position of the sweeper as the starting point and the boundary or center point of the newly identified road area as the end point. Based on the updated map information, build a graph structure containing all nodes (i.e. key points on the map) and edges (i.e. paths between nodes). Use the Dijkstra algorithm to calculate the shortest path from the starting point to the end point. This path will ensure that new road areas are covered and duplicate cleaning is minimized. Convert the calculated shortest path into a cleaning path to ensure that the robot can efficiently clean new road areas along this path.

[0130] S603 connects the new cleaning path with the existing cleaning path to form a complete cleaning route.

[0131] Connect the newly planned cleaning path with the existing cleaning path. This can be achieved by inserting a transition path at the junction of the two paths to ensure the continuity and smoothness of the path. Optimize the merged path to ensure that there are no unnecessary detours and duplications in the path. You can use a path optimization algorithm (such as the A* algorithm) to further optimize the path. Use the optimized path as the final cleaning route to ensure that the robot can complete the cleaning task efficiently and orderly along this route. Send the final cleaning route to the sweeper, which will continue the cleaning work according to this path.

[0132] S106 detects the cleaning effect and optimizes the spacing of the moving path.

[0133] The specific steps include:

[0134] S701 uses a camera to capture images of the cleaned ground;

[0135] After the cleaning task is completed, the robot starts the camera to take pictures of the cleaning area. To ensure the comprehensiveness and accuracy of the image, the robot can take multiple ground images at different positions and angles. The captured ground images are stored locally or uploaded to the central server for subsequent processing.

[0136] S702 uses an edge detection algorithm to identify uncleaned areas;

[0137] Load the captured ground image from storage. Perform preprocessing on the image, including grayscale, denoising, contrast enhancement and other operations to improve the accuracy of edge detection. Use edge detection algorithms (such as Canny edge detection, Sobel operator, etc.) to identify edges in the image. These edges usually represent uncleaned areas or residual stains. Extract uncleaned areas from the edge detection results, which usually appear as continuous edges or patches.

[0138] S703: judging whether there is an uncleaned gap according to the image processing result, and determining the coordinates and range of the uncleaned area;

[0139] Further analyze the extracted uncleaned areas to determine the coordinates and range of each area. You can use contour detection algorithms (such as the findContours function in OpenCV) to obtain the boundaries of each uncleaned area. Based on the size and distribution of the uncleaned areas, determine whether there are obvious uncleaned gaps. If the uncleaned areas are large or densely distributed, it means that the cleaning path needs to be optimized. Record the coordinates and range of the uncleaned areas, which will be used for subsequent path optimization.

[0140] S704 adjusts the spacing of the cleaning paths and replans the cleaning paths according to the scope of the uncleaned area.

[0141] According to the distribution of uncleaned areas, analyze whether the spacing of the current cleaning path is reasonable. If the uncleaned areas are mainly concentrated in certain specific areas, it means that the cleaning density of these areas is insufficient. According to the analysis results, adjust the spacing of the cleaning paths. For example, if there are many uncleaned areas in a certain area, you can reduce the spacing of the cleaning paths in that area and increase the cleaning density. Use a path planning algorithm (such as the Dijkstra algorithm or the A* algorithm) to replan the cleaning path to ensure that the new path can cover the uncleaned areas. The coordinates of the uncleaned areas can be used as new target points to generate the optimal path. Optimize the replanned path to ensure the continuity and efficiency of the path. The path optimization algorithm (such as the genetic algorithm or the simulated annealing algorithm) can be used to further optimize the path. Send the optimized cleaning path to the robot, and the robot will continue the cleaning task according to the new path.

[0142] Second embodiment

[0143] The present invention provides a robot cleaning path planning device, comprising a map information generation module, a first path planning module, an information synchronization module, a cleaning tool switching module and a second path planning module: the map information generation module is used to obtain map information of a cleaning area, the map information including ground material and coverage area information; the first path planning module is used to plan a cleaning route on a road surface of the same material based on a cleaning starting point according to the map information; the information synchronization module is used to obtain indoor position information of a cleaning vehicle and synchronously display it on the map information; the cleaning tool switching module is used to calculate the distance information between the cleaning vehicle and the junction of two material roads on the map information, and when the distance information is less than a preset value, a camera is started to identify different road materials and the cleaning tool is automatically switched; the second path planning module is used to re-plan the cleaning route of the road surface corresponding to the cleaning tool based on the coordinates of the junction.

[0144] In this embodiment, the map information generation module is the foundation of the entire system. It is responsible for collecting detailed map data within the cleaning area. This is not limited to the spatial layout, but also includes important information such as floor material (such as wooden floor, tiles, carpets, etc.) and coverage area. With this data, the robot can have a comprehensive and accurate understanding of the cleaning area, laying the foundation for subsequent operations.

[0145] The first path planning module uses the above map information and the location of the cleaning starting point to plan the optimal cleaning route on the ground of the same material. This process takes into account the principles of maximizing cleaning efficiency and avoiding duplication of work, ensuring that each area can be fully and efficiently cleaned.

[0146] In order to achieve accurate navigation, the information synchronization module plays an important role. It can track the current position of the robot in real time and update this information to the established map model, so that the operator or the robot itself can always know its location and direction of travel, which is crucial to avoid getting lost or entering restricted areas.

[0147] When encountering a junction of different ground materials, the cleaning tool switching module will intervene. The module first calculates the distance between the robot and the junction point. Once it approaches within a certain range (that is, the distance is less than the preset threshold), it activates the camera for field detection to confirm the exact ground type in front. Based on the recognition results, the system automatically adjusts the cleaning equipment and selects the tool that best suits the current ground conditions to ensure the best cleaning effect.

[0148] Finally, the second path planning module comes into play after the robot reaches the material conversion point. It recalculates and generates a cleaning path suitable for the area based on the new ground type and its specific location. This dynamic adjustment mechanism ensures that the robot can maintain an efficient and orderly working state regardless of how the ground changes.

[0149] In summary, this robot cleaning path planning device integrates multiple advanced technologies to achieve highly automated processing of complex cleaning tasks, which not only improves work efficiency but also significantly enhances user experience.

[0150] Third embodiment

[0151] The present invention provides a floor scrubbing robot, comprising a robot cleaning path planning device in the second embodiment.

[0152] The present invention introduces an advanced floor-cleaning robot, which integrates a robot cleaning path planning device described in the second embodiment. This floor-cleaning robot not only has the basic functions of a traditional cleaning robot, such as automatic cleaning and vacuuming, but also has an optimized design specifically for the cleaning requirements of different floor materials, ensuring that it can provide excellent cleaning effects in various commercial environments.

[0153] What is disclosed above is only a preferred embodiment of the present invention, and it certainly cannot be used to limit the scope of rights of the present invention. Ordinary technicians in this field can understand that all or part of the processes of the above embodiment and equivalent changes made according to the claims of the present invention still fall within the scope of the invention.

Claims

1. A robot cleaning path planning method, characterized in that: include: Obtaining map information of the cleaning area, wherein the map information includes ground material and coverage area information; Planning a cleaning route on a road surface of the same material based on the cleaning starting point according to the map information; Obtain the indoor location information of the sweeper and display it on the map information synchronously; The distance between the road sweeper and the junction of two road materials is calculated based on the map information. When the distance is less than the preset value, the camera is activated to identify different road materials and the cleaning tool is automatically switched. The cleaning route of the road surface corresponding to the cleaning tool is replanned based on the coordinates of the junction.

2. A robot cleaning path planning method as claimed in claim 1, characterized in that: After replanning the cleaning route of the road surface corresponding to the cleaning tool based on the coordinates of the junction, the method further includes: detecting the cleaning effect and optimizing the spacing of the moving path.

3. A robot cleaning path planning method as claimed in claim 2, characterized in that: The specific steps of obtaining the map information of the cleaning area include: Use LiDAR to scan the contours of the cleaned area and generate a two-dimensional map; The robot conducts autonomous exploration in the cleaning area, collecting material data using lidar and visual sensors; According to the two-dimensional map on the map and the road material corresponding to the area, the coverage area of ​​roads with different materials is calculated respectively; The coverage area information is marked on a two-dimensional map to form map information with coverage area information.

4. A robot cleaning path planning method as claimed in claim 3, characterized in that: The specific steps of planning a cleaning route on a road surface of the same material based on the cleaning starting point according to the map information include: Load the constructed map information; Set the starting position of the cleaning robot; According to the ground material information, the map is divided into multiple sub-areas, and the ground material in each sub-area is the same; Generate the cleaning order of each sub-area based on the nearest neighbor priority strategy according to the starting position; For each sub-area, use the Dijkstra algorithm to plan the cleaning path to ensure that all the ground in the sub-area is covered; Connect the cleaning paths of each sub-area to form a complete cleaning route.

5. A robot cleaning path planning method as claimed in claim 4, characterized in that: The specific steps of obtaining the indoor location information of the sweeper and synchronously displaying it on the map information include: Pack the real-time location information and status data of the sweeper into a data packet; Obtain indoor positioning data of the road sweeper; Sending indoor positioning data to a central server via a wireless communication module; Loading pre-built map information on a central server; The location mark of the road sweeper is updated in real time on the map information.

6. A robot cleaning path planning method as claimed in claim 5, characterized in that: The specific steps of calculating the distance information between the sweeper and the intersection of the two road materials on the map information, starting the camera to identify different road materials when the distance information is less than a preset value, and automatically switching the cleaning tool include: Identify road areas of different materials on the map; Calculate the distance between the sweeper and each road surface intersection; When the distance between the sweeper and the road surface is less than a preset value, the camera is started to capture ground image data; Use pre-trained deep learning models to classify ground image data and identify the material of the current road surface; Select the corresponding cleaning tool based on the identified road material.

7. A robot cleaning path planning method as claimed in claim 6, characterized in that: The specific steps of replanning the cleaning route of the road surface corresponding to the cleaning tool based on the coordinates of the junction include: Update map information based on the identified road material; Use Dijkstra algorithm to plan new cleaning paths to ensure that new road areas are covered; Connect the new cleaning path with the existing cleaning path to form a complete cleaning line.

8. A robot cleaning path planning method as claimed in claim 7, characterized in that: The specific steps of detecting the cleaning effect and optimizing the spacing of the moving path include: Use a camera to capture images of the cleaned ground; Use edge detection algorithms to identify uncleaned areas; According to the image processing results, determine whether there is an uncleaned gap, and determine the coordinates and range of the uncleaned area; Adjust the spacing of the cleaning paths and re-plan the cleaning paths based on the extent of the uncleaned area.

9. A robot cleaning path planning device, using a robot cleaning path planning method according to any one of claims 1 to 8, characterized in that: It includes a map information generation module, a first path planning module, an information synchronization module, a cleaning tool switching module and a second path planning module: The map information generation module is used to obtain map information of the cleaning area, and the map information includes ground material and coverage area information; The first path planning module is used to plan a cleaning route on a road surface of the same material based on the cleaning starting point according to the map information; The information synchronization module is used to obtain the indoor location information of the sweeper and synchronously display it on the map information; The cleaning tool switching module is used to calculate the distance information between the cleaning vehicle and the intersection of the two road materials on the map information, and when the distance information is less than a preset value, the camera is activated to identify different road materials and the cleaning tool is automatically switched; The second path planning module is used to re-plan the cleaning route of the road surface corresponding to the cleaning tool based on the coordinates of the junction.

10. A floor-cleaning robot, characterized in that: Including a robot cleaning path planning device as described in claim 9.

Images