Sweeper control method and device, equipment, storage medium and program product

Abstract

The invention relates to a sweeper control method and device, equipment, a storage medium and a program product. The method comprises the following steps: acquiring various sensor data of the sweeper; constructing a real-time positioning map according to various sensor data; obtaining the obstacle type of the target obstacle and the obstacle contour data of the target obstacle from the real-time positioning map; under the condition that the obstacle type belongs to a pre-constructed obstacle type database, obtaining a target control strategy according to the obstacle type and the obstacle contour data; and performing sweeping control on the sweeper according to the target control strategy and the real-time positioning map. By adopting the method, scene recognition and obstacle recognition can be more accurately realized through various types of sensor data, and the sweeping control strategy which is more suitable for the obstacle type and the obstacle contour data of the target obstacle is selected, so that the sweeper is more intelligent.

Description

Technical Field

[0001] The present application relates to the technical field of sweeping robots, and in particular to a sweeping robot control method, device, equipment, storage medium and program product. Background Art

[0002] With the development of robot vacuum cleaner technology, people have a growing demand for the cleaning accuracy of robot vacuum cleaners, which is not limited to a single application scenario and a single obstacle recognition requirement. However, the existing technology has a relatively simple obstacle detection and recognition process, and there are no more sophisticated countermeasures for the diversity of obstacle types, which may lead to cleaning accidents of robot vacuum cleaners, such as sucking in charging cables or being blocked by obstacles that cannot be cleaned. Therefore, it is impossible to further improve the intelligence of robot vacuum cleaners. Summary of the invention

[0003] Based on this, it is necessary to provide a sweeper control method, device, computer equipment, computer-readable storage medium and computer program product that can identify different types of obstacles and adopt corresponding cleaning strategies to clean obstacles for the above-mentioned technical problems.

[0004] In a first aspect, the present application provides a sweeping machine control method, comprising:

[0005] Obtain various sensor data of the sweeper;

[0006] Building a real-time positioning map based on the multiple sensor data;

[0007] Obtaining the obstacle type of the target obstacle and the obstacle profile data of the target obstacle from the real-time positioning map;

[0008] In the case where the obstacle type belongs to a pre-built obstacle type database, a target control strategy is obtained according to the obstacle type and obstacle profile data;

[0009] The sweeping machine is controlled to clean according to the target control strategy and the real-time positioning map.

[0010] In one embodiment, the multiple sensor data include: camera data, radar data and line laser data; the real-time positioning map includes: a real-time global positioning map and a real-time local positioning map; the real-time positioning map is constructed according to the multiple sensor data, including:

[0011] Constructing a real-time initial positioning map according to the radar data and a first detection range corresponding to the radar data;

[0012] Perform obstacle recognition according to the pre-built obstacle recognition model and the camera data to obtain the obstacle type and the obstacle contour data;

[0013] Annotating the initial positioning map by using the obstacle type and the obstacle contour data to obtain the real-time global positioning map;

[0014] A local map is constructed according to the line laser data and a second detection range corresponding to the line laser data to obtain the real-time local positioning map; wherein the first detection range is larger than the second detection range.

[0015] In one embodiment, the performing obstacle recognition according to the pre-built obstacle recognition model and the camera data to obtain the obstacle type and the obstacle contour data includes:

[0016] Performing obstacle type identification on the camera data according to the obstacle identification model to obtain the obstacle type;

[0017] Three-dimensional point cloud data is determined according to the camera data, and obstacle contour data is determined according to the three-dimensional point cloud data.

[0018] In one embodiment, the acquiring a target control strategy according to the obstacle type and obstacle profile data includes:

[0019] In the case where the obstacle type indicates that the obstacle is of pet feces type, determining the obstacle height according to the obstacle profile data;

[0020] When the obstacle height is greater than a first preset height, a strategy for staying away from obstacles is obtained from a preset strategy database, and the strategy for staying away from obstacles is used as the target control strategy; wherein the first preset height is used to indicate whether the target obstacle exceeds the obstacle handling height of the sweeper.

[0021] In one embodiment, the method further comprises:

[0022] determining the obstacle height according to the obstacle profile data;

[0023] When the obstacle height is less than a second preset height, a target control strategy is obtained from a preset strategy database according to the obstacle type; wherein the second preset height is used to indicate whether the target obstacle belongs to a low obstacle type.

[0024] In one embodiment, the method further comprises:

[0025] In the case where the obstacle type does not belong to a pre-built obstacle type database, determining a cleaning distance according to the obstacle profile data;

[0026] Formulate an edge cleaning strategy according to the cleaning distance to obtain a candidate edge cleaning strategy;

[0027] When there is no candidate edge cleaning strategy in the preset user habit database, the candidate edge cleaning strategy is sent to the client to obtain a target control strategy;

[0028] The target control strategy is added to the user habit database.

[0029] In a second aspect, the present application also provides a sweeping machine control device, comprising:

[0030] A first acquisition module is used to acquire various sensor data of the sweeping robot;

[0031] A map construction module, used to construct a real-time positioning map according to the multiple sensor data;

[0032] A second acquisition module, used to acquire the obstacle type of the target obstacle and the obstacle contour data of the target obstacle from the real-time positioning map;

[0033] A third acquisition module is used to acquire a target control strategy according to the obstacle type and obstacle profile data when the obstacle type belongs to a pre-built obstacle type database;

[0034] A cleaning control module is used to control the cleaning of the sweeper according to the target control strategy and the real-time positioning map.

[0035] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0036] Obtain various sensor data of the sweeper;

[0037] Building a real-time positioning map based on the multiple sensor data;

[0038] Obtaining the obstacle type of the target obstacle and the obstacle profile data of the target obstacle from the real-time positioning map;

[0039] In the case where the obstacle type belongs to a pre-built obstacle type database, a target control strategy is obtained according to the obstacle type and obstacle profile data;

[0040] The sweeping machine is controlled to clean according to the target control strategy and the real-time positioning map.

[0041] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0042] Obtain various sensor data of the sweeper;

[0043] Building a real-time positioning map based on the multiple sensor data;

[0044] Obtaining the obstacle type of the target obstacle and the obstacle profile data of the target obstacle from the real-time positioning map;

[0045] In the case where the obstacle type belongs to a pre-built obstacle type database, a target control strategy is obtained according to the obstacle type and obstacle profile data;

[0046] The sweeping machine is controlled to clean according to the target control strategy and the real-time positioning map.

[0047] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0048] Obtain various sensor data of the sweeper;

[0049] Building a real-time positioning map based on the multiple sensor data;

[0050] Obtaining the obstacle type of the target obstacle and the obstacle profile data of the target obstacle from the real-time positioning map;

[0051] In the case where the obstacle type belongs to a pre-built obstacle type database, a target control strategy is obtained according to the obstacle type and obstacle profile data;

[0052] The sweeping machine is controlled to clean according to the target control strategy and the real-time positioning map.

[0053] The above-mentioned sweeper control method, device, computer equipment, computer-readable storage medium and computer program product obtain various sensor data of the sweeper; construct a real-time positioning map based on the various sensor data; obtain the obstacle type of the target obstacle and the obstacle contour data of the target obstacle from the real-time positioning map; when the obstacle type belongs to a pre-built obstacle type database, obtain the target control strategy based on the obstacle type and obstacle contour data; and control the sweeper to clean according to the target control strategy and the real-time positioning map. Therefore, the present method can construct a more accurate and multi-dimensional real-time positioning map through various types of sensor data, thereby realizing more accurate scene recognition and obstacle recognition, and selects a target control strategy that is more suitable for the obstacle type and obstacle contour data of the target obstacle, making the sweeper's cleaning control performance more intelligent. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0055] Figure 1 1. is an application environment diagram of a sweeping machine control method in an embodiment;

[0056] Figure 2 A schematic diagram of a flow chart of a method for controlling a sweeping machine in one embodiment;

[0057] Figure 3 A schematic diagram of a flow chart of a method for controlling a sweeping machine in one embodiment;

[0058] Figure 4 is a structural block diagram of a sweeping machine control device in one embodiment;

[0059] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0061] The sweeping machine control method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the sweeper 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The server 104 obtains various sensor data of the sweeper 102; builds a real-time positioning map based on the various sensor data; obtains the obstacle type of the target obstacle and the obstacle contour data of the target obstacle from the real-time positioning map; when the obstacle type belongs to the pre-built obstacle type database, the target control strategy is obtained according to the obstacle type and the obstacle contour data; the sweeper is controlled to clean according to the target control strategy and the real-time positioning map. Among them, the sweeper 102 can be, but is not limited to, various sweeper devices equipped with independent computers, tablets, Internet of Things devices, and portable wearable devices. The server 104 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0062] In an exemplary embodiment, Figure 2 As shown, a sweeping machine control method is provided, and the method is applied to Figure 1 The server 104 in the example is used as an example to illustrate the method, which includes the following steps S202 to S210. Among them:

[0063] Step S202, obtaining various sensor data of the sweeping robot.

[0064] The various sensors used in the sweeper include: a laser radar sensor, a binocular camera, and three line laser sensors. The laser radar sensor is located inside the sweeper and is hidden and cannot be seen from the outside. The binocular camera is located in front of the sweeper. Two of the three line laser sensors are located on the left and right sides of the front of the sweeper and are horizontal structures, and the other is located on the right side of the sweeper and is vertical.

[0065] In some embodiments, a laser radar sensor can be used to collect real-time data of 210 degrees in front of the sweeping machine as radar data. The radar data of the rear part cannot be used due to obstruction by the machine. It should be noted that the front refers to the front in the field of view of the sweeping machine, and the field of view direction may be consistent with the direction of movement of the sweeping machine or inconsistent with it, and is not limited to this.

[0066] In some embodiments, a binocular camera can be used to obtain field of view data directly in front of the machine and output three-dimensional point cloud data, thereby achieving real-time acquisition of obstacle data at different heights.

[0067] In some embodiments, a line laser sensor can be used to obtain real-time three-dimensional point cloud data at a close distance in front of the sweeper, ensuring the detection accuracy of obstacles at close distances. Therefore, a high-precision local map can be provided for the sweeper at close range based on the line laser data obtained in real time at close range, thereby achieving more precise control. The line laser on the right side of the three line laser sensors is vertical, which can more conveniently detect the obstacle information on the right side quickly and accurately, so as to facilitate walking along obstacles at close range.

[0068] In this embodiment, various sensor data are acquired in real time through various types of sensors provided in the sweeping machine, and used for constructing a real-time positioning map in subsequent steps, thereby improving the accuracy of obstacle identification through the real-time positioning map and also improving the accuracy of the subsequent sweeping machine target control strategy.

[0069] Step S204: construct a real-time positioning map based on the data from various sensors.

[0070] Among them, the real-time positioning map technology that can be used is the SLAM (Simultaneous Localization And Mapping) map construction technology.

[0071] In some embodiments, the multiple sensor data include: camera data, radar data and line laser data; the real-time positioning map includes: a real-time global positioning map and a real-time local positioning map; constructing a real-time positioning map based on the multiple sensor data includes: constructing a real-time initial positioning map based on the radar data and the first detection range corresponding to the radar data; identifying obstacles based on a pre-built obstacle recognition model and camera data to obtain obstacle types and obstacle contour data; annotating the initial positioning map with the obstacle type and obstacle contour data to obtain a real-time global positioning map; constructing a local map based on the line laser data and the second detection range corresponding to the line laser data to obtain a real-time local positioning map; wherein the first detection range is larger than the second detection range.

[0072] Among them, the first detection range is the detection distance range of the laser radar sensor, which is usually 0.1~10 meters, but not limited to this.

[0073] In some embodiments, since the detection distance of the lidar sensor is much greater than the detection distance of the line laser sensor and it can only detect obstacles on the horizontal plane, in this embodiment, by constructing a real-time initial positioning map based on the radar data and the first detection range corresponding to the radar data, it is possible to establish a real-time initial positioning map that can achieve global real-time positioning.

[0074] In some embodiments, obstacle recognition is performed based on a pre-built obstacle recognition model and camera data to obtain obstacle type and obstacle contour data, including: performing obstacle type recognition on camera data based on the obstacle recognition model to obtain the obstacle type; determining three-dimensional point cloud data based on the camera data, and determining obstacle contour data based on the three-dimensional point cloud data.

[0075] The pre-built obstacle recognition model refers to a YOLO model that is pre-trained based on different types of obstacle training data, and is used to detect obstacle types.

[0076] In some embodiments, the camera data acquired in real time by the left camera of the binocular camera is used through the YOLO model to identify the type of obstacle, thereby obtaining the obstacle type, thereby achieving an accurate and efficient obstacle type identification process.

[0077] In some embodiments, three-dimensional point cloud data is output based on camera data acquired in real time by a binocular camera, and obstacle contour data is determined based on the three-dimensional point cloud data. It should be noted that by using the output three-dimensional point cloud data, data at different heights of obstacles can be detected, thereby improving the accuracy of obtaining obstacle contour data.

[0078] In some embodiments, more detailed obstacle information can be marked on the initial positioning map through obstacle type and obstacle contour data, thereby obtaining a real-time global positioning map containing accurate obstacle information.

[0079] In some embodiments, a local map is constructed based on the line laser data and the second detection range corresponding to the line laser data, which can provide a high-precision real-time local positioning map for the sweeper at close range, achieving more precise control, and the line laser data obtained by the line laser sensor on the right side of the line laser data is obtained vertically, which can more conveniently detect the obstacle information on the right side, so as to facilitate walking along the obstacle at close range.

[0080] Among them, the second detection range is the detection range of the line laser sensor. Since the detection range of the laser radar is usually larger than the detection range of the laser sensor, the first detection range is larger than the second detection range.

[0081] Step S206: Obtain the obstacle type of the target obstacle and the obstacle profile data of the target obstacle from the real-time positioning map.

[0082] Among them, the real-time positioning map has been marked with obstacle information identified near the binocular camera during the real-time construction process. The target obstacle refers to the first obstacle that the current sweeper needs to clean or avoid.

[0083] In some embodiments, the real-time positioning map is acquired from a real-time positioning map database, and the obstacle type of the target obstacle and the obstacle contour data of the target obstacle are acquired therefrom, but the present invention is not limited thereto.

[0084] Step S208: When the obstacle type belongs to the pre-built obstacle type database, a target control strategy is obtained according to the obstacle type and obstacle profile data.

[0085] In the case where the obstacle type belongs to the pre-built obstacle type database, it means that the target obstacle is a known obstacle type, and the target control strategy can be obtained according to the obstacle type and obstacle profile data.

[0086] In some embodiments, a target control strategy is obtained based on the obstacle type and obstacle contour data, including: when the obstacle type indicates that the obstacle is a pet feces type, determining the obstacle height based on the obstacle contour data; when the obstacle height is greater than a first preset height, obtaining a strategy to stay away from obstacles from a preset strategy database, and using the strategy to stay away from obstacles as the target control strategy; wherein the first preset height is used to indicate whether the target obstacle exceeds the obstacle handling height of the sweeper.

[0087] The preset strategy database is a pre-designed database containing candidate control strategies corresponding to different types of obstacle contour data and obstacle types. The specific control strategy may be different from that in this embodiment and is not limited thereto.

[0088] An example is needed to illustrate that for pet feces, the obstacle type is the pet feces type. The obstacle contour data is highly analyzed through the visual model to determine the obstacle height. If the contour is greater than the first preset height, it means that the sweeper cannot normally clean the target obstacle. The sweeper obtains the obstacle avoidance strategy from the preset strategy database and uses the obstacle avoidance strategy as the target control strategy, so as to keep the sweeper away from feces that cannot be handled during the cleaning process, thereby avoiding the secondary pollution of the surrounding environment caused by feces that are too high during the forced cleaning process.

[0089] In some embodiments, when the sweeping machine executes the strategy of staying away from obstacles, the sweeping machine will push a message to the target user's mobile phone to remind the user to first perform simple processing on the obstacle. The sweeping machine will deal with the residue left after the user's initial cleaning. First, the sweeping machine will clean the residue once and then immediately wash the mop, and then repeat the action. The binocular camera combined with the visual model will compare the residue area with the surrounding floor to determine whether it is cleaned. If it is not cleaned, the residue cleaning and mop cleaning will be repeated up to 10 times, but not limited to this.

[0090] In some embodiments, the method also includes: when the obstacle type indicates that the obstacle is a linear item such as an electric wire or a data cable, the sweeper will execute a strategy to stay away from the obstacle to prevent the obstacle from being stirred into the bottom of the sweeper, thereby avoiding the linear items from getting stuck in the wheels of the sweeper.

[0091] In some embodiments, the method also includes: determining the obstacle height based on the obstacle contour data; when the obstacle height is less than a second preset height, obtaining a target control strategy from a preset strategy database based on the obstacle type; wherein the second preset height is used to indicate whether the target obstacle belongs to a low obstacle type.

[0092] Among them, when the obstacle height is less than the second preset height, it indicates that the target obstacle is a low obstacle type. The setting for the second preset height can be set according to specific needs and is not limited thereto.

[0093] In some embodiments, the obstacle height is determined based on the obstacle contour data. When the obstacle height is less than the second preset height, that is, for the target obstacle of the low obstacle type, it is still necessary to determine whether the obstacle can be moved. Whether the obstacle can be moved can be determined based on the obstacle type. For example, if the obstacle type is a pushable object such as a slipper, the target control strategy obtained by the sweeper from the preset strategy database will be the obstacle pushing cleaning strategy. If the obstacle type indicates a fixed obstacle, the sweeper will also determine whether the target obstacle can be climbed over. If it can be climbed over, the target control strategy obtained by the sweeper from the preset strategy database will be the obstacle climbing cleaning strategy. If it cannot be climbed over, the sweeper will mark a wall at the coordinates of the target obstacle in the real-time positioning map, and update the real-time positioning map to prevent the sweeper from climbing over the target obstacle, thereby avoiding the sweeper from getting stuck on the fixed obstacle.

[0094] Step S210, controlling the cleaning of the sweeping machine according to the target control strategy and the real-time positioning map.

[0095] Among them, cleaning control includes cleaning strategy and moving path control when the sweeper performs the cleaning strategy.

[0096] In some embodiments, the cleaning accuracy of the sweeper is ensured by determining the moving path control corresponding to the target control strategy on the real-time positioning map and controlling the sweeper according to the moving path control and the target control strategy.

[0097] In the above-mentioned sweeping machine control method, multiple sensor data of the sweeping machine are obtained; a real-time positioning map is constructed based on the multiple sensor data; the obstacle type of the target obstacle and the obstacle contour data of the target obstacle are obtained from the real-time positioning map; when the obstacle type belongs to the pre-constructed obstacle type database, the target control strategy is obtained based on the obstacle type and obstacle contour data; the sweeping machine is controlled to clean based on the target control strategy and the real-time positioning map. Therefore, this method can construct a more accurate and multi-dimensional real-time positioning map through multiple types of sensor data, thereby realizing more accurate scene recognition and obstacle recognition, and selecting a target control strategy that is more suitable for the obstacle type and obstacle contour data of the target obstacle, making the sweeping machine's cleaning control performance more intelligent.

[0098] In an exemplary embodiment, Figure 3 As shown, the sweeping machine control method further includes steps S302 to S308. Among them:

[0099] Step S302: When the obstacle type does not belong to the pre-built obstacle type database, determine the cleaning distance according to the obstacle profile data.

[0100] If the obstacle type does not belong to the pre-built obstacle type database, it indicates that the target obstacle is an obstacle of unknown type.

[0101] In some embodiments, the cleaning distance of the obstacle contour data is judged by a pre-trained visual distance judgment model, so as to determine a suitable cleaning distance to ensure that the sweeper does not touch the target obstacle.

[0102] Step S304, formulate an edge cleaning strategy according to the cleaning distance, and obtain a candidate edge cleaning strategy.

[0103] In some embodiments, an edge cleaning strategy is formulated based on the cleaning distance to obtain a candidate edge cleaning strategy. The sweeper can ensure that it will not touch the target obstacle based on the candidate edge cleaning strategy, while still ensuring that the subsequent edge cleaning process can accurately clean the edge around the target obstacle.

[0104] Step S306: When there is no candidate edge cleaning strategy in the preset user habit database, the candidate edge cleaning strategy is sent to the client to obtain a target control strategy.

[0105] Among them, the user habit database is a database for storing user habit data. When there is no candidate edge cleaning strategy in the preset user habit database, it means that the user has not selected an edge cleaning strategy for the target obstacle type, and therefore the corresponding user habit data is not stored in the user habit database.

[0106] In some embodiments, if there are no candidate edge cleaning strategies in the preset user habit database, the candidate edge cleaning strategies are sent to the client, that is, the candidate edge cleaning strategies are pushed to the user's mobile phone APP, allowing the user to select a specific edge distance in the candidate edge cleaning strategy or choose whether to adopt the obstacle cleaning strategy, thereby obtaining the target control strategy generated according to the user's selection.

[0107] In some embodiments, when there are candidate edge cleaning strategies in a preset user habit database, the target control strategy corresponding to the target obstacle is directly obtained from the user habit database, that is, the sweeping machine is controlled to clean the floor according to the target control strategy adopted by the user last time for an unknown type of obstacle, thereby improving the intelligence of the sweeping machine.

[0108] Step S308: adding the target control strategy to the user habit database.

[0109] In some embodiments, after the user selects a target control strategy, the sweeping machine will add the target control strategy to the user habit database to remember the user's habits and directly execute the corresponding target control strategy next time, thereby improving the intelligence of the sweeping machine.

[0110] In this embodiment, when the obstacle type does not belong to the pre-built obstacle type database, the cleaning distance is determined according to the obstacle contour data; an edge cleaning strategy is formulated according to the cleaning distance to obtain a candidate edge cleaning strategy; when the candidate edge cleaning strategy does not exist in the preset user habit database, the candidate edge cleaning strategy is sent to the client to obtain a target control strategy; adding the target control strategy to the user habit database can improve the intelligence of the sweeper when facing obstacles of unknown types, thereby improving the cleaning efficiency of the sweeper.

[0111] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0112] Based on the same inventive concept, the embodiment of the present application also provides a sweeping machine control device for implementing the sweeping machine control method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more sweeping machine control device embodiments provided below can refer to the limitations of the sweeping machine control method above, and will not be repeated here.

[0113] In an exemplary embodiment, Figure 4 As shown, a sweeping machine control device is provided, including: a first acquisition module 401, a map construction module 402, a second acquisition module 403, a third acquisition module 404 and a cleaning control module 405, wherein:

[0114] The first acquisition module 401 is used to acquire various sensor data of the sweeping machine;

[0115] A map construction module 402, for constructing a real-time positioning map based on various sensor data;

[0116] The second acquisition module 403 is used to acquire the obstacle type of the target obstacle and the obstacle contour data of the target obstacle from the real-time positioning map;

[0117] The third acquisition module 404 is used to acquire the target control strategy according to the obstacle type and obstacle profile data when the obstacle type belongs to the pre-built obstacle type database;

[0118] The cleaning control module 405 is used to control the cleaning of the sweeper according to the target control strategy and the real-time positioning map.

[0119] In some embodiments, the multiple sensor data include: camera data, radar data and line laser data; the real-time positioning map includes: a real-time global positioning map and a real-time local positioning map; the map construction module 402 is also used to construct a real-time initial positioning map based on the radar data and the first detection range corresponding to the radar data; perform obstacle identification based on a pre-constructed obstacle recognition model and camera data to obtain obstacle type and obstacle contour data; annotate the initial positioning map with the obstacle type and obstacle contour data to obtain a real-time global positioning map; construct a local map based on the line laser data and the second detection range corresponding to the line laser data to obtain a real-time local positioning map; wherein the first detection range is larger than the second detection range.

[0120] In some embodiments, the map construction module 402 is further used to identify the obstacle type of the camera data according to the obstacle recognition model to obtain the obstacle type; determine the three-dimensional point cloud data according to the camera data, and determine the obstacle contour data according to the three-dimensional point cloud data.

[0121] In some embodiments, the third acquisition module 404 is also used to determine the obstacle height based on the obstacle contour data when the obstacle type indicates that the obstacle is a pet feces type; when the obstacle height is greater than a first preset height, obtain the obstacle avoidance strategy from a preset strategy database and use the obstacle avoidance strategy as the target control strategy; wherein the first preset height is used to indicate whether the target obstacle exceeds the obstacle handling height of the sweeper.

[0122] In some embodiments, the sweeping robot control device also includes: a fourth acquisition module, used to determine the obstacle height based on the obstacle contour data; when the obstacle height is less than a second preset height, obtaining the target control strategy from a preset strategy database according to the obstacle type; wherein the second preset height is used to indicate whether the target obstacle belongs to a low obstacle type.

[0123] In some embodiments, the sweeping machine control device also includes: a fifth acquisition module, which is used to determine the cleaning distance according to the obstacle contour data when the obstacle type does not belong to the pre-built obstacle type database; formulate an edge cleaning strategy according to the cleaning distance to obtain a candidate edge cleaning strategy; if there is no candidate edge cleaning strategy in the preset user habit database, send the candidate edge cleaning strategy to the client to obtain a target control strategy; and add the target control strategy to the user habit database.

[0124] In the above-mentioned sweeping machine control device, multiple sensor data of the sweeping machine are obtained; a real-time positioning map is constructed based on the multiple sensor data; the obstacle type of the target obstacle and the obstacle contour data of the target obstacle are obtained from the real-time positioning map; when the obstacle type belongs to the pre-constructed obstacle type database, the target control strategy is obtained based on the obstacle type and obstacle contour data; the sweeping machine is controlled to clean based on the target control strategy and the real-time positioning map. Therefore, the present method can construct a more accurate and multi-dimensional real-time positioning map through multiple types of sensor data, thereby realizing more accurate scene recognition and obstacle recognition, and selecting a target control strategy that is more suitable for the obstacle type and obstacle contour data of the target obstacle, making the sweeping machine's cleaning control performance more intelligent.

[0125] Each module in the above-mentioned sweeping machine control device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0126] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store obstacle type data, user habit data, real-time positioning maps and obstacle recognition models. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for controlling a sweeping machine is implemented.

[0127] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0128] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps of the above-mentioned sweeping machine control method when executing the computer program.

[0129] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned sweeping machine control method are implemented.

[0130] In one embodiment, a computer program product is provided, including a computer program, which implements the steps of the above-mentioned sweeping machine control method when executed by a processor.

[0131] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0132] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0133] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0134] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A sweeping machine control method, characterized in that: The method comprises: Obtain various sensor data of the sweeper; Building a real-time positioning map based on the multiple sensor data; Obtaining the obstacle type of the target obstacle and the obstacle profile data of the target obstacle from the real-time positioning map; In the case where the obstacle type belongs to a pre-built obstacle type database, a target control strategy is obtained according to the obstacle type and obstacle profile data; The sweeping machine is controlled to clean according to the target control strategy and the real-time positioning map.

2. The method according to claim 1, characterized in that The multiple sensor data include: camera data, radar data and line laser data; the real-time positioning map includes: real-time global positioning map and real-time local positioning map; the real-time positioning map is constructed according to the multiple sensor data, including: Constructing a real-time initial positioning map according to the radar data and a first detection range corresponding to the radar data; Perform obstacle recognition according to the pre-built obstacle recognition model and the camera data to obtain the obstacle type and the obstacle contour data; Annotating the initial positioning map by using the obstacle type and the obstacle contour data to obtain the real-time global positioning map; A local map is constructed according to the line laser data and a second detection range corresponding to the line laser data to obtain the real-time local positioning map; wherein the first detection range is larger than the second detection range.

3. The method according to claim 2, characterized in that The step of performing obstacle recognition according to the pre-built obstacle recognition model and the camera data to obtain the obstacle type and the obstacle contour data includes: Performing obstacle type identification on the camera data according to the obstacle identification model to obtain the obstacle type; Three-dimensional point cloud data is determined according to the camera data, and obstacle contour data is determined according to the three-dimensional point cloud data.

4. The method according to claim 1, characterized in that The acquiring of a target control strategy according to the obstacle type and obstacle profile data comprises: In the case where the obstacle type indicates that the obstacle is of pet feces type, determining the obstacle height according to the obstacle profile data; When the obstacle height is greater than a first preset height, a strategy for staying away from obstacles is obtained from a preset strategy database, and the strategy for staying away from obstacles is used as the target control strategy; wherein the first preset height is used to indicate whether the target obstacle exceeds the obstacle handling height of the sweeper.

5. The method according to claim 1, characterized in that The method further comprises: determining the obstacle height according to the obstacle profile data; When the obstacle height is less than a second preset height, a target control strategy is obtained from a preset strategy database according to the obstacle type; wherein the second preset height is used to indicate whether the target obstacle belongs to a low obstacle type.

6. The method according to claim 1, characterized in that The method further comprises: In the case where the obstacle type does not belong to a pre-built obstacle type database, determining a cleaning distance according to the obstacle profile data; Formulate an edge cleaning strategy according to the cleaning distance to obtain a candidate edge cleaning strategy; When there is no candidate edge cleaning strategy in the preset user habit database, the candidate edge cleaning strategy is sent to the client to obtain a target control strategy; The target control strategy is added to the user habit database.

7. A sweeping machine control device, characterized in that: The device comprises: A first acquisition module is used to acquire various sensor data of the sweeping robot; A map construction module, used to construct a real-time positioning map according to the multiple sensor data; A second acquisition module, used to acquire the obstacle type of the target obstacle and the obstacle contour data of the target obstacle from the real-time positioning map; A third acquisition module is used to acquire a target control strategy according to the obstacle type and obstacle profile data when the obstacle type belongs to a pre-built obstacle type database; A cleaning control module is used to control the cleaning of the sweeper according to the target control strategy and the real-time positioning map.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images