Control method and device of a robot sweeper, electronic equipment and storage medium

Abstract

The application discloses a control method and device of a sweeping robot, electronic equipment and a storage medium, and the method comprises the following steps: when a sweeping instruction is triggered, the sweeping robot is controlled to move into a to-be-cleaned area to obtain image information of the to-be-cleaned area by the sweeping robot; a global scene graph of the sweeping robot in the to-be-cleaned area is determined based on the image information, so that a to-be-cleaned point corresponding to the sweeping robot is determined according to the global scene graph; a predicted cleaning path corresponding to the sweeping robot is determined according to the to-be-cleaned point, and a target cleaning time corresponding to the predicted cleaning path is calculated; and a target control instruction of the sweeping robot is determined based on the target cleaning time corresponding to the predicted cleaning path, so that the sweeping robot is controlled to work through the target control instruction. Thus, the same cleaning work does not need to be repeatedly performed, the cleaning time of the sweeping robot is reduced, the cleaning efficiency can be effectively improved, and the service life of the sweeping robot is prolonged.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of sweeping robots, and in particular to a control method and device for a sweeping robot, an electronic device and a storage medium. BACKGROUND

[0002] A sweeping robot can detect obstacles by means of a laser or a camera, so as to automatically complete floor cleaning work in a room. Generally, a sweeping and vacuuming method is adopted to suck floor debris into a garbage collection box of the sweeping robot, so as to complete the function of floor cleaning. In the prior art, the current sweeping robot usually adopts a preset program to work during the cleaning process, so as to complete the cleaning work of a house. Since the sweeping robot repeatedly performs the same cleaning work, the cleaning time of the sweeping robot is relatively long, and it is difficult to improve the cleaning efficiency and reduce the service life of the sweeping robot under the condition of frequent cleaning of the house. SUMMARY

[0003] In a first aspect, the main purpose of the present application is to provide a control method for a sweeping robot, comprising:

[0004] When a cleaning instruction is triggered, the sweeping robot is controlled to move into a to-be-cleaned area to obtain image information of the to-be-cleaned area by the sweeping robot;

[0005] A global scene graph of the sweeping robot in the to-be-cleaned area is determined based on the image information, so as to determine a to-be-cleaned point corresponding to the sweeping robot according to the global scene graph;

[0006] A predicted cleaning path corresponding to the sweeping robot is determined according to the to-be-cleaned point, and a target cleaning time corresponding to the predicted cleaning path is calculated;

[0007] A target control instruction of the sweeping robot is determined based on the target cleaning time corresponding to the predicted cleaning path, so as to control the sweeping robot to work through the target control instruction.

[0008] Preferably, when the cleaning instruction is triggered, the sweeping robot is controlled to move into the to-be-cleaned area to obtain the image information of the to-be-cleaned area by the sweeping robot, comprising:

[0009] When the cleaning instruction is triggered, the to-be-cleaned area corresponding to the cleaning instruction is determined;

[0010] A center point position of the to-be-cleaned area is determined according to the to-be-cleaned area corresponding to the cleaning instruction, and the sweeping robot is controlled to move to the center point position of the to-be-cleaned area;

[0011] When the sweeping robot moves to the center point position of the to-be-cleaned area, the sweeping robot is caused to take images in a first direction and a second direction to obtain image information of the to-be-cleaned area.

[0012] Preferably, the determining of the global scene graph of the sweeping robot in the to-be-cleaned area based on the image information comprises:

[0013] determining a first scene graph corresponding to the first direction and a second scene graph corresponding to the second direction of the sweeping robot based on the image information;

[0014] performing feature fusion on the first scene graph and the second scene graph to obtain the global scene graph;

[0015] performing feature detection on the global scene graph and determining the to-be-cleaned point corresponding to the sweeping robot according to the detection result.

[0016] Preferably, the performing of feature detection on the global scene graph and the determining of the to-be-cleaned point corresponding to the sweeping robot according to the detection result comprise:

[0017] inputting the global scene graph into a pre-trained feature detection model to perform feature detection and determine the trace points in the global scene graph;

[0018] labeling the trace points in the global scene graph to determine the to-be-cleaned point.

[0019] Preferably, the determining of the predicted cleaning path corresponding to the sweeping robot according to the to-be-cleaned point and the calculation of the target cleaning time corresponding to the predicted cleaning path comprise:

[0020] determining the to-be-cleaned points of the shortest path in sequence according to the to-be-cleaned points;

[0021] labeling the to-be-cleaned points of the shortest path in sequence and associating the to-be-cleaned points of the shortest path with the current position of the sweeping robot to obtain the predicted cleaning path;

[0022] calculating the target cleaning time corresponding to the predicted cleaning path according to the predicted cleaning path, the preset moving speed and the preset cleaning speed of the sweeping robot.

[0023] Preferably, the determining of the target control instruction of the sweeping robot based on the moving time corresponding to the predicted cleaning path and the controlling of the sweeping robot to work through the target control instruction comprise:

[0024] determine a target cleaning time corresponding to the predicted cleaning path based on the target cleaning time corresponding to the predicted cleaning path;

[0025] generate a target control instruction corresponding to each of the to-be-cleaned points according to the target cleaning time and the cleaning sub-time corresponding to each of the to-be-cleaned points, and control the sweeping robot through the target control instruction.

[0026] Preferably, the generating of the target control instruction corresponding to each of the to-be-cleaned points according to the target cleaning time and the cleaning sub-time corresponding to each of the to-be-cleaned points, and the controlling of the sweeping robot through the target control instruction, comprises:

[0027] calculate a cleaning speed corresponding to each of the to-be-cleaned points according to the target cleaning time and the cleaning sub-time corresponding to each of the to-be-cleaned points;

[0028] control the sweeping robot according to the cleaning speed corresponding to each of the to-be-cleaned points, and compare a real-time cleaning time of the sweeping robot at each of the to-be-cleaned points with the cleaning sub-time;

[0029] when the real-time cleaning time is the same as the cleaning sub-time, control the sweeping robot to move to a next to-be-cleaned point.

[0030] In a second aspect, an embodiment of the present application provides a control device of a sweeping robot, comprising:

[0031] a control module, configured to control the sweeping robot to move to a to-be-cleaned area to obtain image information of the to-be-cleaned area by the sweeping robot when a cleaning instruction is triggered;

[0032] a determination module, configured to determine a global scene graph of the sweeping robot in the to-be-cleaned area based on the image information, and determine a to-be-cleaned point corresponding to the sweeping robot according to the global scene graph;

[0033] a calculation module, configured to determine a predicted cleaning path corresponding to the sweeping robot according to the to-be-cleaned point, and calculate a target cleaning time corresponding to the predicted cleaning path;

[0034] the determination module is configured to determine a target control instruction of the sweeping robot based on the target cleaning time corresponding to the predicted cleaning path, so as to control the sweeping robot to work through the target control instruction.

[0035] In a third aspect, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the control method of the robot sweeper when executing the computer program.

[0036] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program, and the computer program implements the steps of the control method of the robot sweeper when executed by a processor.

[0037] The above scheme of the present application at least has the following beneficial effects:

[0038] The control method of the robot sweeper provided by the present application, when a cleaning instruction is triggered, first controls the robot sweeper to move into a to-be-cleaned area to obtain image information of the to-be-cleaned area by the robot sweeper, determines a global scene graph of the robot sweeper in the to-be-cleaned area based on the image information, determines a to-be-cleaned point corresponding to the robot sweeper according to the global scene graph, determines a predicted cleaning path corresponding to the robot sweeper according to the to-be-cleaned point, and calculates a target cleaning time corresponding to the predicted cleaning path, determines a target control instruction of the robot sweeper based on the target cleaning time corresponding to the predicted cleaning path, and controls the robot sweeper to work through the target control instruction. Thus, the same cleaning work does not need to be repeatedly performed, the cleaning time of the robot sweeper is reduced, the cleaning efficiency can be effectively improved, and the service life of the robot sweeper is prolonged. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from the structures shown in the drawings without creative labor.

[0040] Figure 1 The overall flowchart of the control method of the robot sweeper provided by the present application is shown in the figure.

[0041] Figure 2 The example diagram of the control method of the robot sweeper provided by the present application is shown in the figure.

[0042] Figure 3 The structure block diagram of the control device of the robot sweeper provided by the present application is shown in the figure.

[0043] Figure 4A structural block diagram of an electronic device provided by an embodiment of the present application is shown.

[0044] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0045] The technical solutions in the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0046] The terms “first”, “second” and “third” and the like in the specification and claims of the present application and the above-described drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the term “comprise” and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed, or can optionally include other steps or units inherent to the process, method, product or device.

[0047] First, the scheme of the embodiments of the present application will be introduced by way of example in conjunction with the related drawings.

[0048] As shown in Figure 1 A control method of a sweeping robot is provided by an embodiment of the present application, comprising:

[0049] S10, when a sweeping instruction is triggered, controlling the sweeping robot to move into a to-be-cleaned area to obtain image information of the to-be-cleaned area by the sweeping robot.

[0050] The sweeping instruction can be set by time, for example, the sweeping instruction can be triggered at a certain time point, so that when the preset time is reached, the sweeping instruction can be triggered to make the sweeping robot move into the to-be-cleaned area by itself, and the image information of the to-be-cleaned area can be collected by the camera of the sweeping robot. Alternatively, the image information can be a snapshot picture, an image frame intercepted in a video stream, etc. The to-be-cleaned area can be a living room, a room or the like. It can be understood that the sweeping robot can be connected with a cloud server, and the collected image information can be analyzed by the cloud server to determine the position to be cleaned in the to-be-cleaned area, and then to dynamically plan the sweeping robot to clean.

[0051] Specifically, the above-mentioned image information of the to-be-cleaned area is obtained by the sweeping robot when the sweeping robot is triggered to move to the to-be-cleaned area, including: when the sweeping instruction is triggered, the to-be-cleaned area corresponding to the sweeping instruction is determined; the center point position of the to-be-cleaned area is determined according to the to-be-cleaned area corresponding to the sweeping instruction, and the sweeping robot is controlled to move to the center point position of the to-be-cleaned area; when the sweeping robot moves to the center point position of the to-be-cleaned area, the sweeping robot is controlled to shoot in the first direction and the second direction to obtain the image information of the to-be-cleaned area.

[0052] In the embodiment, the sweeping instruction can be set by APP or the like, for example, the user outputs the instruction of sweeping the living room in the APP, and it can be determined that the to-be-cleaned area corresponding to the sweeping instruction is the living room. By determining the to-be-cleaned area corresponding to the sweeping instruction, the sweeping robot can be controlled to move to the center point position. When the sweeping robot moves to the to-be-cleaned area, the distance of the wall position of the to-be-cleaned area can be detected by the laser sensor of the sweeping robot, so as to determine the center point position by the distance of the wall position. The image shooting at the center point position of the to-be-cleaned area can ensure that the to-be-cleaned area can be more comprehensively shot. Optionally, the first direction and the second direction can be directions perpendicular to each other in the same horizontal plane. After the sweeping robot shoots in the first direction and the second direction in turn, the image information of the to-be-cleaned area can be obtained, for example, the shooting can be performed in turn from southeast, northwest, east and west, and the east-west direction can correspond to the first direction, and the north-south direction can correspond to the second direction. After shooting in the first direction and the second direction, the image information of the to-be-cleaned area can be more accurately analyzed.

[0053] S20, determining a global scene graph of the sweeping robot in the to-be-cleaned area based on the image information, so as to determine the to-be-cleaned point corresponding to the sweeping robot according to the global scene graph.

[0054] The image information collected by the sweeping robot can be input into the feature extraction network model. The feature extraction network model can be pre-trained. After the image information is processed by the feature extraction network model, the global scene graph is determined for feature detection. It can be understood that the to-be-cleaned point can be an abnormal position in the global scene graph, such as a footprint position, a water stain position, a litter position, etc. The to-be-cleaned point can be determined from the global scene graph by the pre-trained feature extraction network model, so as to control the sweeping robot to clean each to-be-cleaned point.

[0055] Specifically, the above determining the global scene graph of the sweeping robot in the to-be-cleaned area based on the image information comprises: determining a first scene graph corresponding to a first direction and a second scene graph corresponding to a second direction of the sweeping robot based on the image information; performing feature fusion on the first scene graph and the second scene graph to obtain the global scene graph; performing feature detection on the global scene graph, and determining the to-be-cleaned point corresponding to the sweeping robot according to the detection result.

[0056] In the embodiment, the image information can include the first scene graph and the second scene graph. The first image feature in the first scene graph and the second image feature in the second scene graph are determined by inputting the first scene graph and the second scene graph into the feature extraction network model for image feature extraction. The global scene graph can be obtained by performing feature fusion on the first image feature and the second image feature. After the global scene graph is determined, the to-be-cleaned point is determined by performing feature detection on the global scene graph.

[0057] Further, the above performing feature detection on the global scene graph and determining the to-be-cleaned point corresponding to the sweeping robot according to the detection result comprises: inputting the global scene graph into a pre-trained feature detection model for feature detection to determine the trace points in the global scene graph; and marking the trace points in the global scene graph to determine the to-be-cleaned point.

[0058] In the feature detection, the pixel points in the global scene graph can be divided into different regions. The luminance values of the divided different regions are calculated, and the luminance values of the two regions are compared, and the luminance difference between the two regions is calculated. When the luminance difference is large, the corresponding trace point can be determined from the two regions. When the luminance difference is small, the operation of comparing the luminance values of the two regions can be continued. It can be understood that after the trace points in the global scene graph are determined, the corresponding trace points can be marked as the to-be-cleaned point to perform path planning through the marked to-be-cleaned point, and then the sweeping robot is controlled to work. For example, the tiles in the living room can be divided into multiple regions. The luminance values of the tiles in each region are detected, and the luminance values of the tiles in the two regions are compared, and the corresponding luminance difference is calculated. Thus, the tile region with a large difference value can be marked as the to-be-cleaned point.

[0059] S30, determining the predicted cleaning path corresponding to the sweeping robot according to the to-be-cleaned point, and calculating the target cleaning time corresponding to the predicted cleaning path.

[0060] The predicted cleaning path can be planned according to the to-be-cleaned points, and the path of the sweeping robot is planned through the predicted cleaning path, so that the sweeping robot can clean the corresponding to-be-cleaned points through the predicted cleaning path, thereby avoiding the need to repeatedly perform the same cleaning work. By determining the predicted cleaning path and the corresponding target cleaning time, the working parameters of the sweeping robot can be controlled in the subsequent process to ensure higher working efficiency of the sweeping robot. In an optional embodiment, it can be determined whether there is an obstacle according to the predicted cleaning path. When there is an obstacle, an avoidance path can be planned according to the position of the obstacle, and the predicted cleaning path can be corrected according to the avoidance path. After the predicted cleaning path is corrected through the avoidance path, the target cleaning time corresponding to the corrected predicted cleaning path is calculated.

[0061] Specifically, the predicted cleaning path corresponding to the sweeping robot is determined according to the to-be-cleaned points, and the target cleaning time corresponding to the predicted cleaning path is calculated, including: the to-be-cleaned points of the shortest path are determined in sequence according to the to-be-cleaned points; the to-be-cleaned points of the shortest path are marked in sequence and associated with the current position of the sweeping robot to obtain the predicted cleaning path; the target cleaning time corresponding to the predicted cleaning path is calculated according to the predicted cleaning path, the preset moving speed and the preset cleaning speed of the sweeping robot.

[0062] In this embodiment, after the to-be-cleaned points are determined, the shortest paths between adjacent to-be-cleaned points can be calculated. After the shortest paths between adjacent to-be-cleaned points are calculated, each to-be-cleaned point can be marked and associated in sequence according to the shortest paths, so that the sweeping robot can move to the corresponding to-be-cleaned point in sequence to complete the cleaning work. That is, the predicted cleaning path is planned according to the shortest paths of each to-be-cleaned point. After the predicted cleaning path is determined, the corresponding target cleaning time can be calculated through the preset moving speed and the preset cleaning speed of the sweeping robot. The preset moving speed represents the moving speed of the sweeping robot, and the preset cleaning speed represents the rotating brush speed of the sweeping robot. In an optional embodiment, the area of the to-be-cleaned point can be calculated. After the area of the to-be-cleaned point is calculated, the cleaning speed of the sweeping robot in the to-be-cleaned point can be adjusted. When the area of the to-be-cleaned point is larger, the cleaning speed can be adjusted to be greater than the preset cleaning speed. When the area of the to-be-cleaned point is smaller, the preset cleaning speed can be used for cleaning to improve the cleaning efficiency of the sweeping robot in the to-be-cleaned point, thereby reducing the working time. For example, as shown in the figure, A, B, C, D, E and F are to-be-cleaned points. The predicted cleaning path is determined by associating A, B, C, D, E and F in sequence, so that the sweeping robot can clean the positions corresponding to A, B, C, D, E and F in sequence. Figure 2

[0063] ​S40, determine a target control instruction of the sweeping robot based on the target sweeping time corresponding to the predicted sweeping path, so as to control the sweeping robot to work through the target control instruction.

[0064] The target control instruction can correspond to a working parameter of the sweeping robot, and the working parameter of the sweeping robot can include a sweeping speed, a moving speed, and a sweeping time. After the target sweeping time is determined, time distribution can be performed on each to-be-swept point to determine the sweeping time of each to-be-swept point, and the sweeping speed is adjusted according to the sweeping time of each to-be-swept point, so as to determine the corresponding target control instruction to control the sweeping robot according to the target control instruction, so that the sweeping robot can selectively sweep during the working process, without repeating the same sweeping action, and the sweeping efficiency is improved.

[0065] Specifically, the target sweeping time corresponding to the predicted sweeping path is used to determine a sweeping sub-time of the sweeping robot at each to-be-swept point, and the corresponding target control instruction is generated according to the sweeping sub-time of the sweeping robot at each to-be-swept point and the target sweeping time, so as to control the sweeping robot through the target control instruction.

[0066] In this embodiment, the target sweeping time represents the sum of the time for the sweeping robot to sweep all to-be-swept points and the moving time. The sweeping sub-time of each to-be-swept point is calculated through the moving time of the sweeping robot and the target sweeping time, and it can be judged whether the to-be-swept point can be completed within the sweeping sub-time according to the sweeping sub-time. When it can be completed, the sweeping speed of the sweeping robot is determined as the preset sweeping speed. When it cannot be completed, the sweeping speed of the sweeping robot is increased to be greater than the preset sweeping speed, so as to ensure higher sweeping efficiency.

[0067] Further, the corresponding target control instruction is generated according to the sweeping sub-time of the sweeping robot at each to-be-swept point and the target sweeping time, so as to control the sweeping robot through the target control instruction, including: the sweeping speed corresponding to each to-be-swept point is calculated according to the sweeping sub-time of the sweeping robot at each to-be-swept point and the target sweeping time; the sweeping robot is controlled according to the sweeping speed corresponding to each to-be-swept point, and the real-time sweeping time of the sweeping robot at each to-be-swept point is compared with the sweeping sub-time; when the real-time sweeping time is the same as the sweeping sub-time, the sweeping robot is controlled to move to the next to-be-swept point.

[0068] In the embodiment, when the cleaning speed corresponding to each to-be-cleaned point is determined, the sweeping robot is controlled to clean each to-be-cleaned point, and the corresponding real-time cleaning time and cleaning sub-time are compared. When the real-time cleaning time is the same as the cleaning sub-time, a stop cleaning instruction is triggered, the rotation brush of the sweeping robot is controlled to stop running, and the sweeping robot is controlled to move to the next cleaning point for cleaning. In this way, after the sweeping robot cleans the determined to-be-cleaned point, the sweeping robot can return to the starting position when the cleaning work is completed. It can be understood that, by determining the to-be-cleaned points in the to-be-cleaned area, the sweeping robot can dynamically plan a cleaning path, and the cleaning efficiency is higher.

[0069] The control method of the sweeping robot provided by the application comprises the following steps: when a cleaning instruction is triggered, the sweeping robot is controlled to move into a to-be-cleaned area to obtain image information of the to-be-cleaned area by the sweeping robot; a global scene graph of the sweeping robot in the to-be-cleaned area is determined based on the image information, so as to determine a to-be-cleaned point corresponding to the sweeping robot according to the global scene graph; a predicted cleaning path corresponding to the sweeping robot is determined according to the to-be-cleaned point, and a target cleaning time corresponding to the predicted cleaning path is calculated; and finally, a target control instruction of the sweeping robot is determined based on the target cleaning time corresponding to the predicted cleaning path, so as to control the sweeping robot to work through the target control instruction. In this way, the same cleaning work does not need to be repeatedly performed, the cleaning time of the sweeping robot is reduced, the cleaning efficiency can be effectively improved, and the service life of the sweeping robot is prolonged.

[0070] As shown in Figure 3 The control device of the sweeping robot comprises:

[0071] The control module is configured to control the sweeping robot to move into a to-be-cleaned area to obtain image information of the to-be-cleaned area by the sweeping robot when a cleaning instruction is triggered.

[0072] The determination module is configured to determine a global scene graph of the sweeping robot in the to-be-cleaned area based on the image information, so as to determine a to-be-cleaned point corresponding to the sweeping robot according to the global scene graph.

[0073] The calculation module is configured to determine a predicted cleaning path corresponding to the sweeping robot according to the to-be-cleaned point, and calculate a target cleaning time corresponding to the predicted cleaning path.

[0074] The determination module is configured to determine a target control instruction of the sweeping robot based on the target cleaning time corresponding to the predicted cleaning path, so as to control the sweeping robot to work through the target control instruction.

[0075] The control device of the sweeping robot provided by the application first controls the sweeping robot to move into the to-be-cleaned area to obtain image information of the to-be-cleaned area by the sweeping robot when a cleaning instruction is triggered, determines a global scene graph of the sweeping robot in the to-be-cleaned area based on the image information, determines a to-be-cleaned point corresponding to the sweeping robot according to the global scene graph, determines a predicted cleaning path corresponding to the sweeping robot according to the to-be-cleaned point, calculates a target cleaning time corresponding to the predicted cleaning path, and finally determines a target control instruction of the sweeping robot based on the target cleaning time corresponding to the predicted cleaning path to control the sweeping robot to work through the target control instruction. Thus, the same cleaning work does not need to be repeatedly performed, the cleaning time of the sweeping robot is reduced, the cleaning efficiency can be effectively improved, and the service life of the sweeping robot is prolonged.

[0076] It should be noted that the control device 10 of the sweeping robot provided by the embodiments of the application is a device corresponding to the control method of the sweeping robot, all the embodiments of the control method of the sweeping robot are applicable to the control device 10 of the sweeping robot, and there are corresponding modules in the embodiments of the control device 10 of the sweeping robot to correspond to the steps in the control method of the sweeping robot, so that the same or similar beneficial effects can be achieved. To avoid too much repetition, each module in the control device 2 of the sweeping robot will not be described in detail here.

[0077] As shown in Figure 4 The embodiments of the application also provide an electronic device 20, which comprises a memory 202, a processor 201, and a computer program stored in the memory 202 and capable of running on the processor 201, and the processor 201 implements the steps of the control method of the sweeping robot when executing the computer program.

[0078] Specifically, the processor 201 is configured to call the computer program stored in the memory 202 and execute the following steps:

[0079] When a cleaning instruction is triggered, the sweeping robot is controlled to move into the to-be-cleaned area to obtain image information of the to-be-cleaned area by the sweeping robot;

[0080] A global scene graph of the sweeping robot in the to-be-cleaned area is determined based on the image information, and a to-be-cleaned point corresponding to the sweeping robot is determined according to the global scene graph;

[0081] A predicted cleaning path corresponding to the sweeping robot is determined according to the to-be-cleaned point, and a target cleaning time corresponding to the predicted cleaning path is calculated;

[0082] A target control instruction of the sweeping robot is determined based on the target cleaning time corresponding to the predicted cleaning path, and the sweeping robot is controlled to work through the target control instruction.

[0083] Optionally, the processor 201 executes the following steps when the cleaning instruction is triggered: controlling the sweeping robot to move into the to-be-cleaned area to obtain image information of the to-be-cleaned area by the sweeping robot, including:

[0084] When the cleaning instruction is triggered, the to-be-cleaned area corresponding to the cleaning instruction is determined;

[0085] The center point position of the to-be-cleaned area is determined according to the to-be-cleaned area corresponding to the cleaning instruction, and the sweeping robot is controlled to move to the center point position of the to-be-cleaned area;

[0086] When the sweeping robot moves to the center point position of the to-be-cleaned area, the sweeping robot is controlled to shoot in the first direction and the second direction to obtain image information of the to-be-cleaned area.

[0087] Optionally, the processor 201 executes the following steps based on the image information to determine a global scene graph of the sweeping robot in the to-be-cleaned area, so as to determine a to-be-cleaned point corresponding to the sweeping robot according to the global scene graph, including:

[0088] Based on the image information, a first scene graph corresponding to the first direction and a second scene graph corresponding to the second direction of the sweeping robot are determined;

[0089] The first scene graph and the second scene graph are fused to obtain the global scene graph;

[0090] The global scene graph is subjected to feature detection, and a to-be-cleaned point corresponding to the sweeping robot is determined according to the detection result.

[0091] Optionally, the processor 201 executes the following steps of feature detection on the global scene graph and determining a to-be-cleaned point corresponding to the sweeping robot according to the detection result:

[0092] The global scene graph is input into a pre-trained feature detection model for feature detection to determine a trace point in the global scene graph;

[0093] The trace point in the global scene graph is marked to determine the to-be-cleaned point.

[0094] Optionally, the processor 201 executes the following steps of determining a predicted cleaning path corresponding to the sweeping robot according to the to-be-cleaned point and calculating a target cleaning time corresponding to the predicted cleaning path:

[0095] The to-be-cleaned points of the shortest path are determined in sequence according to the to-be-cleaned points;

[0096] The to-be-cleaned points of the shortest path are marked in sequence and associated with the current position of the sweeping robot to obtain the predicted cleaning path;

[0097] According to the predicted cleaning path, the preset moving speed of the sweeping robot, and the preset cleaning speed, a target cleaning time corresponding to the predicted cleaning path is calculated.

[0098] Optionally, the processor 201 executes the target control instruction of the sweeping robot based on the moving time corresponding to the predicted cleaning path to control the sweeping robot to work, including:

[0099] According to the target cleaning time corresponding to the predicted cleaning path, a cleaning sub-time corresponding to each to-be-cleaned point of the sweeping robot is determined.

[0100] According to the cleaning sub-time corresponding to each to-be-cleaned point of the sweeping robot and the target cleaning time, a corresponding target control instruction is generated to control the sweeping robot through the target control instruction.

[0101] Optionally, the processor 201 executes the target control instruction of the sweeping robot according to the cleaning sub-time corresponding to each to-be-cleaned point of the sweeping robot and the target cleaning time, to control the sweeping robot, including:

[0102] According to the cleaning sub-time corresponding to each to-be-cleaned point of the sweeping robot and the target cleaning time, a cleaning speed corresponding to each to-be-cleaned point is calculated.

[0103] According to the cleaning speed corresponding to each to-be-cleaned point, the sweeping robot is controlled, and the real-time cleaning time of the sweeping robot at each to-be-cleaned point is compared with the cleaning sub-time.

[0104] When the real-time cleaning time is the same as the cleaning sub-time, the sweeping robot is controlled to move to the next cleaning point.

[0105] That is, in the specific embodiments of the present application, the processor 201 of the electronic device 20 executes the computer program to realize the steps of the above-mentioned control method of the sweeping robot, thereby without repeating the same cleaning work, reducing the cleaning time of the sweeping robot, and effectively improving the cleaning efficiency and prolonging the service life of the sweeping robot.

[0106] It should be noted that, since the processor 201 of the electronic device 20 executes the computer program to realize the steps of the above-mentioned control method of the sweeping robot, all embodiments of the above-mentioned control method of the sweeping robot are applicable to the electronic device 20, and can achieve the same or similar beneficial effects.

[0107] The computer readable storage medium provided in the embodiment of the present application has a computer program stored thereon, the computer program is executed by a processor to implement each process of the control method of the sweeping robot or the control method of the application-side sweeping robot provided by the embodiment of the present application, and the same technical effects can be achieved. To avoid repetition, details are not described herein.

[0108] It can be understood by those skilled in the art that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware, and the program can be stored in a computer readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiment methods. The storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM) or a random access memory (RAM).

[0109] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example" or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0110] The above only describes the preferred embodiments of the present application, and does not limit the patent scope of the present application. Any equivalent structural transformation made according to the content of the present application specification and drawings, or direct / indirect application in other related technical fields is included in the patent protection scope of the present application.

Claims

1. A control method for a sweeping robot, characterized in that, The method comprises the steps of: when a cleaning instruction is triggered, controlling the sweeping robot to move into a to-be-cleaned area to obtain image information of the to-be-cleaned area by the sweeping robot; determining a global scene graph of the sweeping robot in the to-be-cleaned area based on the image information, so as to determine a to-be-cleaned point corresponding to the sweeping robot according to the global scene graph; determining a predicted cleaning path corresponding to the sweeping robot according to the to-be-cleaned point, and calculating a target cleaning time corresponding to the predicted cleaning path; determining a target control instruction of the sweeping robot based on the target cleaning time corresponding to the predicted cleaning path, so as to control the sweeping robot to work through the target control instruction; when a cleaning instruction is triggered, controlling the sweeping robot to move into a to-be-cleaned area to obtain image information of the to-be-cleaned area by the sweeping robot; when a cleaning instruction is triggered, determining a to-be-cleaned area corresponding to the cleaning instruction; determining a center point position of the to-be-cleaned area according to the to-be-cleaned area corresponding to the cleaning instruction, and controlling the sweeping robot to move to the center point position of the to-be-cleaned area; when the sweeping robot moves to the center point position of the to-be-cleaned area, the sweeping robot is controlled to shoot in a first direction and a second direction to obtain image information of the to-be-cleaned area; determining a first scene graph corresponding to the first direction and a second scene graph corresponding to the second direction of the sweeping robot based on the image information; performing feature fusion on the first scene graph and the second scene graph to obtain the global scene graph; performing feature detection on the global scene graph, and determining a to-be-cleaned point corresponding to the sweeping robot according to the detection result; when performing feature detection, the pixel points of different regions in the global scene graph are determined, the luminance values corresponding to the different regions after division are calculated, the luminance values of two regions are compared, and the luminance difference between the two regions is calculated; when the luminance difference is large, the corresponding trace point is determined from the two regions. The feature detection model is pre-trained, and the trace points in the global scene graph are determined by inputting the global scene graph into the feature detection model for feature detection.

2. The control method of the robot cleaner according to claim 1, wherein, The trace points in the global scene graph are marked to determine the to-be-cleaned point. The method comprises the steps of: determining to-be-cleaned points of a shortest path according to the to-be-cleaned points; 3.The control method of the robot cleaner according to claim 1, wherein, the to-be-cleaned points of the shortest path are sequentially marked and associated with the current position of the sweeping robot to obtain a predicted cleaning path. ​ ​ According to the predicted cleaning path, the preset moving speed and the preset cleaning speed of the sweeping robot, a target cleaning time corresponding to the predicted cleaning path is calculated.

4. The control method of the robot cleaner according to claim 1, wherein, The target control instruction of the sweeping robot is determined based on the target cleaning time corresponding to the predicted cleaning path, so as to control the sweeping robot to work through the target control instruction. According to the target cleaning time and the cleaning sub-time corresponding to each of the to-be-cleaned points, a corresponding target control instruction is generated to control the sweeping robot through the target control instruction. According to the target cleaning time and the cleaning sub-time corresponding to each of the to-be-cleaned points, a corresponding target control instruction is generated to control the sweeping robot through the target control instruction.

5. The control method of the robot cleaner according to claim 4, wherein, According to the target cleaning time and the cleaning sub-time corresponding to each of the to-be-cleaned points, a corresponding target control instruction is generated to control the sweeping robot through the target control instruction. According to the target cleaning time and the cleaning sub-time corresponding to each of the to-be-cleaned points, a corresponding target control instruction is generated to control the sweeping robot through the target control instruction. According to the target cleaning time and the cleaning sub-time corresponding to each of the to-be-cleaned points, a corresponding target control instruction is generated to control the sweeping robot through the target control instruction. According to the target cleaning time and the cleaning sub-time corresponding to each of the to-be-cleaned points, a corresponding target control instruction is generated to control the sweeping robot through the target control instruction.

6. A control device of a robot sweeper, characterized by comprising: When the real-time cleaning time is the same as the cleaning sub-time, the sweeping robot is controlled to move to a next cleaning point. Comprise: The control module is used for controlling the sweeping robot to move to the to-be-cleaned area to obtain image information of the to-be-cleaned area through the sweeping robot when a cleaning instruction is triggered. The determination module is used for determining a global scene map of the sweeping robot in the to-be-cleaned area based on the image information, so as to determine the to-be-cleaned point corresponding to the sweeping robot according to the global scene map. The calculation module is used for determining a predicted cleaning path corresponding to the sweeping robot according to the to-be-cleaned point, and calculating a target cleaning time corresponding to the predicted cleaning path. The determination module is used for determining a target control instruction of the sweeping robot based on the target cleaning time corresponding to the predicted cleaning path, so as to control the sweeping robot to work through the target control instruction. The control module is used for controlling the sweeping robot to move to the to-be-cleaned area to obtain image information of the to-be-cleaned area through the sweeping robot when a cleaning instruction is triggered. When the cleaning instruction is triggered, the to-be-cleaned area corresponding to the cleaning instruction is determined. The center point position of the to-be-cleaned area is determined according to the to-be-cleaned area corresponding to the cleaning instruction, and the sweeping robot is controlled to move to the center point position of the to-be-cleaned area. When the sweeping robot moves to the center point position of the to-be-cleaned area, the sweeping robot is used to take pictures in a first direction and a second direction to obtain image information of the to-be-cleaned area. The determination module is used for determining a global scene map of the sweeping robot in the to-be-cleaned area based on the image information, so as to determine the to-be-cleaned point corresponding to the sweeping robot according to the global scene map. determine a first scene graph corresponding to a first direction and a second scene graph corresponding to a second direction of the robot cleaner based on the image information; fuse the first scene graph and the second scene graph to obtain a global scene graph; detect features of the global scene graph, and determine a to-be-cleaned point corresponding to the robot cleaner according to a detection result; when detecting the features, divide pixel points in the global scene graph into different regions, calculate luminance values corresponding to the different regions after the division, compare the luminance values of two regions, and calculate luminance difference values between the two regions, and when the luminance difference values are large, determine a trace point corresponding to the two regions.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the steps of the control method of the robot cleaner according to any one of claims 1 to 6.

8. A computer-readable storage medium storing a computer program, the computer-readable storage medium comprising: The computer program is executed by the processor to implement the steps of the control method of the robot cleaner according to any one of claims 1 to 6.

Images