Sweeping robot control method and device, sweeping robot, system and storage medium

Abstract

A control method and a control device (121) of a sweeping robot (10), the sweeping robot (10), a control system and a computer readable storage medium. The control method comprises: determining semantic information of different objects located on a moving path (S201); determining different security execution distances of the different objects according to the semantic information of the different objects (S202); and controlling the sweeping robot (10) to perform a cleaning task and / or an obstacle avoidance task more flexibly, intelligently and safely according to different safe execution distances of different objects (S203).

Description

Control method, device, system and storage medium of sweeping robot Technical Field

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

[0002] With the rapid development of technology, more and more smart home appliances have entered thousands of households, greatly improving people's comfort and convenience. Among them, the representative robot vacuum is becoming increasingly popular. A type of smart home appliance, the robot vacuum uses artificial intelligence to automatically clean the floor in a room. Generally speaking, robots that perform cleaning, vacuuming, and mopping tasks are also collectively referred to as robot vacuums.

[0003] In order to make sweeping robots more widely used, how to control them to clean more flexibly and intelligently is an urgent problem to be solved.

[0004] Summary of the Invention

[0005] In view of this, one of the objects of the present application is to provide a control method, a control device, a sweeping robot, a control system and a computer-readable storage medium.

[0006] In a first aspect, an embodiment of the present application provides a control method for a sweeping robot, which is applied to the sweeping robot and includes:

[0007] Determine the semantic information of different objects located on the movement path;

[0008] determining different safe execution distances for the different objects based on semantic information of the different objects;

[0009] The sweeping robot is controlled to perform cleaning tasks and / or obstacle avoidance tasks according to the different safe execution distances of the different objects.

[0010] In this embodiment, different safety distances between the sweeping robot and different objects are flexibly determined according to the semantic information of different objects, which can not only avoid collisions between the sweeping robot and different objects, but also clean all cleanable locations as much as possible, thereby achieving more flexible, intelligent and safe execution of cleaning tasks and / or obstacle avoidance tasks.

[0011] In a second aspect, an embodiment of the present application provides a control method for a sweeping robot, which is applied to a terminal. The method includes:

[0012] Display the environment map in the interactive interface;

[0013] In response to a first touch operation received on the interactive interface, a first touch track is generated, wherein the first touch track includes at least one of the following: a sliding operation track in the form of a smear track, a pressing track, or a closed sliding track;

[0014] determining an area to be cleaned in the environment according to the first touch trajectory and the environment map;

[0015] The sweeping robot is controlled to perform a cleaning task in the environment according to the area to be cleaned.

[0016] In this embodiment, the user can perform the first touch operation according to his or her own cleaning needs, flexibly select the area he or she wants to clean, and can realize fine control of the sweeping robot for fixed-point cleaning, so that the sweeping robot can flexibly and intelligently clean the area desired by the user, thereby improving the cleaning efficiency of the sweeping robot.

[0017] In a third aspect, an embodiment of the present application provides a control device for a sweeping robot, comprising:

[0018] one or more processors;

[0019] a memory for storing instructions executable by the processor;

[0020] The one or more processors execute the executable instructions individually or collectively to execute the method described in any one of the first aspects.

[0021] In a fourth aspect, an embodiment of the present application provides a sweeping robot, comprising:

[0022] body;

[0023] a power system, disposed in the body, for providing power to the sweeping robot; and

[0024] The control device according to the third aspect is arranged in the body.

[0025] In a fifth aspect, an embodiment of the present application provides a control system, comprising the sweeping robot and the terminal as described in the fourth aspect;

[0026] The terminal is used to execute the method described in any one of the second aspects.

[0027] In a sixth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores executable instructions, and when the executable instructions are executed by a processor, the method described in any one of the first aspect or the second aspect is implemented.

[0028] The embodiments of the present application are conducive to making the sweeping robot clean more flexibly and intelligently, and the embodiments and beneficial effects will be further elaborated below. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0030] FIG1 is a schematic structural diagram of a control system provided by one embodiment of the present application;

[0031] FIG2 is a schematic diagram of an environment map provided by an embodiment of the present application;

[0032] FIG3 is a schematic structural diagram of a sweeping robot provided by one embodiment of the present application;

[0033] FIG4 is a flow chart of a control method of a sweeping robot provided by one embodiment of the present application;

[0034] FIG5A is a schematic diagram of a user performing a smearing operation on a displayed environment map provided by one embodiment of the present application;

[0035] FIG5B is a schematic diagram of a user performing a zoom-in operation on a displayed environment map provided by one embodiment of the present application;

[0036] FIG5C is a schematic diagram of a user performing a zoom-out operation on a displayed environment map provided by one embodiment of the present application;

[0037] 6A and 6B are different schematic diagrams of a user's scribbled line and a fitted closed figure provided by one embodiment of the present application;

[0038] FIG7 is a flow chart of another method for controlling a sweeping robot provided by an embodiment of the present application;

[0039] FIG8 is a schematic diagram of a sweeping robot provided by an embodiment of the present application performing cleaning according to a reciprocating cleaning strategy;

[0040] FIG9 is a schematic diagram of a sweeping robot provided with a mechanical switch according to an embodiment of the present application;

[0041] FIG10 is a schematic diagram of a sweeping robot provided with a wind speed sensor according to an embodiment of the present application;

[0042] FIG11 is a schematic structural diagram of a control device of a sweeping robot provided in one embodiment of the present application. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0044] Referring to FIG. 1 , a schematic diagram of the control system is provided. The control system includes a robot vacuum cleaner 10 and a terminal 20. The robot vacuum cleaner 10 and the terminal 20 are communicatively connected. A user can control the robot vacuum cleaner 10 through the terminal 20 to perform cleaning tasks, but the user is not limited thereto. For example, the user can also control the robot vacuum cleaner 10 to return to a base station or to move to a designated location when not cleaning. This embodiment does not impose any restrictions on this.

[0045] For example, the base station of the sweeping robot may include a charging pile. After returning to the base station, the sweeping robot 10 may automatically connect to the charging pile through a magnetic structure, thereby achieving automatic charging.

[0046] Exemplarily, the base station of a sweeping robot can have the function of cleaning the sweeping robot. For example, the sweeping robot includes at least one of the following structures: a brush for sweeping the floor, a mop for cleaning the floor, a trash collection box for sucking up floor debris, and a water tank for washing the mop. The base station can include a cleaning mechanism for cleaning at least one of the aforementioned structures of the sweeping robot. After the sweeping robot returns to the base station, the base station can use the cleaning mechanism to clean at least one of the aforementioned structures of the sweeping robot. For example, the base station can use the cleaning mechanism to suck out debris from the trash collection box or wastewater from the water tank. For another example, the base station can use the cleaning mechanism to clean the mop or brush of the sweeping robot.

[0047] For example, when the robot vacuum cleaner includes a water tank, the base station may also have the function of adding water to the water tank. When the robot vacuum cleaner includes a mop, the base station may also have the function of automatically drying the mop.

[0048] The terminal 20 can provide an interactive interface that displays a pre-built environment map. For example, Figure 2 shows an environment map of an indoor environment. The user can specify an area to be cleaned in the environment map. The terminal 20 can then control the robot vacuum 10 to clean the area specified by the user. The robot vacuum 10 can use at least one of the following cleaning methods: brushing, vacuuming, and mopping. During the cleaning process, the robot vacuum 10 can collect debris from the floor into its own trash collection box or perform wet cleaning on wet dirt, thereby completing the function of cleaning the floor.

[0049] Exemplarily, referring to FIG. 3 , the sweeping robot 10 includes a cleaning control system 12 and a power system 11 .

[0050] The power system 11 is used to provide power for the sweeping robot 10; for example, the power system 11 may include one or more electronic speed regulators 111 (referred to as ESCs), one or more walking mechanisms 113, and one or more motors 112 corresponding to the one or more walking mechanisms 113, wherein the motor 112 is connected between the electronic speed regulator 111 and the walking mechanism 113; the electronic speed regulator 111 is used to receive the driving signal generated by the cleaning control system 12, and provide a driving current to the motor 112 according to the driving signal to control the speed of the motor 112. The motor 112 is used to drive the walking mechanism 113 to move, thereby providing power for the walking of the sweeping robot 10, and this power enables the sweeping robot 10 to achieve one or more degrees of freedom of movement. It should be understood that the motor 112 can be a DC motor or an AC motor. In addition, the motor 112 can be a brushless motor or a brushed motor.

[0051] The cleaning control system 12 may include a control device 121, a sensing system 122, and an execution system 123. The sensing system 122 is used to measure the posture information of the sweeping robot 10, that is, the position information and state information of the sweeping robot 10 in space, such as three-dimensional position, three-dimensional angle, three-dimensional velocity, three-dimensional acceleration, and three-dimensional angular velocity; and / or, the sensing system is also used to sense the surrounding environment of the sweeping robot 10 in order to avoid obstacles or build an environmental map. The sensing system may include, for example, at least one of a gyroscope, an ultrasonic sensor, an electronic compass, an inertial measurement unit (IMU), a visual sensor, a lidar, an infrared sensor, a global navigation satellite system, a barometer, a collision sensor, and a fall sensor. For example, the global navigation satellite system may be a global positioning system (GPS). The control device 121 is used to control the sweeping robot 10 to perform cleaning tasks and / or obstacle avoidance tasks. For example, the movement of the sweeping robot 10 can be controlled according to the posture information measured by the sensing system 122. It should be understood that the control device 121 can control the cleaning robot 10 according to pre-programmed instructions, or can control the cleaning robot 10 by responding to one or more control signals from the terminal 20 .

[0052] The execution system 123 includes but is not limited to at least one of the following structures: a dry cleaning component (for example, a brush for sweeping the floor, a garbage collection box for collecting debris on the floor, etc.), a dust collection component and (a dust collection mechanism (blower or fan, etc.) located near the dust collection port) a wet cleaning component (for example, a mop for cleaning the floor and a water tank for cleaning the mop, etc.). Among them, the brushes of the sweeping robot are divided into two types: roller brushes and side brushes. The roller brush is located at the bottom of the sweeping robot, generally in front of the dust collection port. Its main function is to sweep up the dust at the bottom of the sweeping robot and allow the dust to enter the garbage collection box through the dust collection port. The side brush is set at the edge of the sweeping robot body, generally 5 to 8 cm beyond the body. Its function is to clean the dust from the walls or corners that the sweeping robot cannot reach. The mop includes two types: flat mop and rotating mop. The flat mop is a one-way scraping clean, while the rotating mop is a cleaning by rotating the two mops inward.

[0053] The above-mentioned cleaning tasks may include sweeping tasks and / or scrubbing tasks; sweeping tasks refer to tasks of sweeping the floor using a brush and / or a vacuum assembly; scrubbing tasks refer to tasks of scrubbing the floor using a mop.

[0054] If the sensing system 122 detects that the object to be cleaned contains liquid dirt, the robot vacuum can be controlled to perform a scrubbing task. For example, the control device can control the mop to scrub the liquid dirt. Before scrubbing, if the mop is detected to be relatively dry, the mop can be rehydrated using water from the water tank. During or after scrubbing, the mop can be rinsed using water from the water tank. For example, the water tank can include two separate containers: one for holding clean water and the other for holding wastewater from rinsing the mop.

[0055] When the sensing system 122 detects that the object to be cleaned is dry dirt such as dust or hair, the sweeping robot can be controlled to perform the cleaning task. For example, the control device can control the brush to brush or control the dust suction component to perform the dust suction operation. For example, the dust suction mechanism in the dust suction component can absorb dry dirt such as dust or hair into the garbage collection box through the dust suction port.

[0056] Exemplarily, the terminal 20 includes, but is not limited to, a smart phone / mobile phone, a tablet computer, a personal digital assistant (PDA), a laptop computer, a desktop computer, a media content player, a video game station / system, a virtual reality system, an augmented reality system, a wearable device (e.g., a watch, glasses, gloves, headwear (e.g., a hat, a helmet, a virtual reality headset, an augmented reality headset, a head-mounted device (HMD), a headband), a pendant, an armband, a leg band, a shoe, a vest), a remote control, or any other type of device.

[0057] It should be noted that the terminal 20 can be far away from the sweeping robot 10 to achieve remote control of the sweeping robot 10; alternatively, the terminal 20 can also be fixedly or detachably provided on the sweeping robot 10, and the specific setting can be based on needs.

[0058] It should be understood that the above naming of the control system and the various components of the sweeping robot is for identification purposes only and should not be understood as limiting the embodiments of the present application.

[0059] In some embodiments, the sweeping robots may also communicate with each other to collaboratively clean the same area.

[0060] In order to make sweeping robots more widely used, how to control them to clean more flexibly and intelligently is an urgent problem to be solved.

[0061] One control method used in related technologies is to divide the indoor environment into functional areas, such as bedrooms, kitchens, living rooms, or bathrooms. Users can select the area to be cleaned based on their actual needs, such as the bedroom or kitchen. This area selection method is less flexible, as users may not want to clean the entire room, and it cannot meet their needs for refined control.

[0062] In response to the above problems, this embodiment provides a control method for a sweeping robot, which allows the user to customize the area to be cleaned through a first touch operation on the terminal, thereby controlling the sweeping robot to clean flexibly and intelligently according to user needs.

[0063] Please refer to FIG4 , which shows a flow chart of a control method for a sweeping robot, which is applied to a terminal. The method includes:

[0064] In step S101 , an environment map is displayed in an interactive interface.

[0065] In step S102 , a first touch track is generated in response to a first touch operation received on the interaction interface.

[0066] In step S103 , an area to be cleaned in the environment is determined according to the first touch track and the environment map.

[0067] In step S104 , the sweeping robot is controlled to perform a cleaning task in the environment according to the area to be cleaned.

[0068] In this embodiment, referring to Figure 2 , within the interactive interface displaying an environment map, the user can perform a first touch operation based on their cleaning needs. This first touch operation can include at least one of the following: a smearing operation, a press operation, or a sliding operation in the form of a closed sliding track, allowing the user to flexibly select the area they want to clean. For example, Figure 5A shows a schematic diagram of a user performing a smearing operation within the interactive interface displaying an environment map. This makes setting the area to be cleaned more flexible and intuitive, while also increasing interest and enhancing the user experience.

[0069] The terminal can then generate a first touch trajectory in response to the first touch operation received on the interactive interface, and then determine the area to be cleaned in the environment based on the first touch trajectory and the environment map, the first touch trajectory including at least one of the following: a smearing trajectory, a pressing trajectory, or a sliding operation trajectory in the form of a closed sliding trajectory; finally, the sweeping robot is controlled to perform a cleaning task in the environment based on the area to be cleaned.

[0070] Through the first touch operation, users can flexibly select the area they want to clean, and can achieve fine-grained control of the sweeping robot for fixed-point cleaning, so that the sweeping robot can flexibly and intelligently clean the area desired by the user, thereby improving the cleaning efficiency of the sweeping robot.

[0071] In one example, referring to FIG5A , the first touch operation is a smear operation. The smear operation can be performed by touching the interactive interface with a single finger and then smearing on the interactive interface. For example, FIG5A shows a smeared line displayed on the interactive interface due to the user's smearing operation. Other touch methods (such as two-finger touch) can also be used, and this embodiment does not impose any restrictions on this. In another example, the smear operation can also be performed by using a tool such as a mouse or stylus to smear on the interactive interface, and this embodiment does not impose any restrictions on this.

[0072] Exemplarily, the interactive interface also displays a reset control. When the user is not satisfied with the area covered by the smear lines displayed on the interactive interface, the user can click to trigger the reset control; in response to the reset control being triggered, the terminal can clear the smear lines displayed on the interactive interface due to the user's last smear operation, so that the user can perform the smear operation again.

[0073] For example, the environment map displayed on the interactive map can be zoomed in or out to assist the user in defining the area to be cleaned.

[0074] In one possible implementation, considering that the area the user wants to clean is very small in some scenarios, in order to improve the accuracy of determining the area to be cleaned, the terminal can display an enlarged environment map on the interactive interface in response to the user's zoom operation; the user can perform a smear operation on the enlarged environment map to accurately delineate the area to be cleaned. The zoom operation can be an operation in which the user touches the interactive interface with two fingers and then spreads them apart, as shown in Figure 5B; or it can be an operation in which the user clicks on the zoom control displayed on the interactive interface. After displaying the enlarged environment map on the interactive interface, the terminal can also display a default-size environment map on the interactive interface in response to the user's restore operation; for example, the user's restore operation can be an operation of double-finger single-clicking or double-clicking the interactive interface, but is not limited to this.

[0075] In another possible implementation, considering that the area that the user wants to clean is very large in some scenarios, in order to reduce the number of steps of the user's smearing operation, the terminal can display a reduced environment map on the interactive interface in response to the user's zoom-out operation; the user can perform a smearing operation in the reduced environment map so as to quickly delineate the area to be cleaned and improve the smearing efficiency. The zoom-out operation can be an operation of pinching the user's two fingers after touching the interactive interface as shown in FIG5C; or it can be an operation of the user clicking the zoom-out control displayed on the interactive interface. After displaying the reduced environment map on the interactive interface, the terminal can also display a default-size environment map on the interactive interface in response to the user's restore operation; for example, the user's restore operation can be an operation of clicking or double-clicking the interactive interface with two fingers, but is not limited to this.

[0076] In some embodiments, when determining the area to be cleaned in the environment, the terminal can determine the area to be cleaned in the environment based on the area covered by several circles with the first touch track (the smear track is taken as an example below) as the center in the environment map; as shown in Figure 5A, Figure 5A shows a smear line 201 displayed on the interactive interface due to the user's smear operation. The smear line 201 is composed of several circles with the smear track as the center. The terminal can determine the area to be cleaned in the environment based on the area covered by the smear line 201 in the environment map, thereby realizing refined determination of the area to be cleaned according to user needs.

[0077] The radius of the circle can be determined based on the first instruction. For example, the first instruction is a user instruction, that is, the user can customize the radius of the circle (or customize the thickness of the smear line 201 as shown in Figure 5A) according to actual needs. Alternatively, the first instruction can be a standard circle radius corresponding to the terminal.

[0078] Furthermore, considering that when the user attempts to paint a larger area, manual operation may cause the area covered by the several circles to have jagged edges, that is, the area covered by the several circles may be irregular, which may increase the difficulty and complexity of subsequent path planning. Therefore, in order to facilitate the subsequent path planning process, after generating the smearing trajectory, the terminal can obtain several circles with the smearing trajectory as the center, and fit the outer edges of the several circles to obtain a closed figure; then, based on the area covered by the closed figure in the environmental map, determine the area to be cleaned in the environment. This embodiment effectively reduces the difficulty and complexity of subsequent path planning and improves the efficiency of path planning by fitting several circles to a certain extent.

[0079] The fitting process involves determining the smooth, closed shape that most closely matches the circles. Figures 6A and 6B show schematic diagrams of the fitted closed image. The gray portion represents the smeared lines composed of circles formed by the user's smearing operation, while the closed shape composed of black lines represents the fitted result. It can be understood that the purpose of fitting is to smoothen the uneven areas, thereby reducing the complexity of the path rule. The closed shape obtained by fitting is not significantly different from the shape formed by the user's smeared lines.

[0080] In other embodiments, in order to reduce the number of smearing operation steps for the user, when the generated smearing track is a closed track or close to a closed track, the interior of the closed track can also be automatically filled, and then the area to be cleaned in the environment is determined based on the area covered by the filled graphic in the environmental map.

[0081] In one example, after determining multiple areas to be cleaned, the user can also specify the cleaning order of the multiple areas to be cleaned in the interactive interface according to actual needs. This embodiment does not impose any restrictions on this. After the terminal determines the area to be cleaned based on the user's smearing operation, it can control the sweeping robot to perform the cleaning task in the environment based on the area to be cleaned; for example, the terminal can generate to-be-cleaned information indicating that there is an area to be cleaned, and then send the to-be-cleaned information to the sweeping robot. The sweeping robot can plan the movement path of the sweeping robot based on the area to be cleaned indicated by the to-be-cleaned information, and then perform the cleaning task according to the movement path.

[0082] For example, controlling a robot vacuum to perform a cleaning task in an environment based on the area to be cleaned may include: obtaining the robot vacuum's current position; determining a movement path based on the robot vacuum's current position and the area to be cleaned; and controlling the robot vacuum to move along the movement path. In this embodiment, the robot vacuum is not directly located in the area to be cleaned, and it is necessary to determine the robot vacuum's current position so as to at least plan a movement path for the robot vacuum from its current position to the area to be cleaned.

[0083] Exemplarily, the moving path includes at least: a first moving path, which is used to represent the path from the current position of the mobile robot to the area to be cleaned; and / or a second moving path, which is used to represent the path of the mobile robot when performing a cleaning task in the area to be cleaned. The first moving path can be further understood as the moving path from the current position of the mobile robot to the first position of the area to be cleaned. For example, the current position of the mobile robot can be understood as the location of the base station or the location of the sweeping robot when performing other tasks, and the first position is the starting cleaning position of the area to be cleaned. The second moving path can be further understood as the moving path from the first position of the mobile robot to the second position. For example, the first position is the starting cleaning position of the area to be cleaned, and the second position is the final cleaning position of the area to be cleaned.

[0084] In some embodiments, the labeling of the area to be cleaned and the marking of the starting cleaning position and the final cleaning position can be customized on the terminal through a first touch operation, such as by loading a file. The markings include but are not limited to: triangles, origins, circles, crosshairs, aiming marks, etc. The starting cleaning position and the final cleaning position can be set by user operation, such as a user clicking two locations on a semantic map on the terminal's interactive interface, such as one or more coordinates entered by the user. The starting cleaning position and the final cleaning position can also be automatically set by the sweeping robot, such as using the starting coordinates when the robot starts moving as the starting cleaning position and the ending coordinates when the robot finishes the cleaning task as the final cleaning position.

[0085] For example, the second moving path can be implemented by first planning along the edge and then planning in a bow shape. For example, first, the sweeping robot is controlled to plan the path of the edge of the area to be cleaned to obtain the overall shape of the area to be cleaned, and then according to the starting cleaning position and final cleaning position of the area to be cleaned set by the user, the bow-shaped traversal is completed at preset intervals to obtain the second moving path of the area to be cleaned with different shapes.

[0086] Exemplarily, controlling the sweeping robot to move on the moving path includes: under a first condition, controlling the sweeping robot to move from the current position to the area to be cleaned via the first moving path, or, under a second condition, giving priority to controlling the sweeping robot to move from the current position to the area to be cleaned via the first moving path, or, under a third condition, giving priority to controlling the sweeping robot to perform tasks according to the most recently received control instructions. For example, the first condition may be: the sweeping robot currently has no tasks to perform, and the current relevant parameters of the sweeping robot are capable of performing cleaning tasks, for example, it is in a standby state with sufficient power. Then, under the first condition, upon receiving the information of the area to be cleaned indicated by the user, the sweeping robot can move directly from the current position to the area to be cleaned via the first moving path. For example, the second condition may be: the sweeping robot is currently performing other tasks, such as mapping tasks for other areas, cleaning tasks for other areas, or other areas. Then, under the second condition, upon receiving the information of the area to be cleaned indicated by the user, the sweeping robot will prioritize the task of moving from the current position to the area to be cleaned via the first moving path, and only after the sweeping robot cleans the area to be cleaned via the second moving path will it return to the current position to continue performing other tasks. For example, the third condition may be: the sweeping robot is currently performing a basic task, such as a charging task when the battery is low, a task in which the cleaning component of the sweeping robot is cleaned by the base station, or a task in which the sweeping robot is adding water / cleaning liquid. Then, under the third condition, upon receiving the area to be cleaned indicated by the user, the sweeping robot will continue to perform the current basic task, and only after the sweeping robot completes the current basic task will it move from the current position to the area to be cleaned via the first moving path. It can be understood that in some embodiments, when the charging task in the third condition, the task of cleaning the cleaning components of the sweeping robot by the base station, or the task of adding water / cleaning liquid to the sweeping robot is about to be completed, so that the relevant parameters of the sweeping robot can be used to perform tasks on the area to be cleaned, the third condition can be converted into the first condition.

[0087] Through the above implementation, the control difficulty of the sweeping robot can be effectively reduced, and corresponding tasks can be performed according to the user's preferences, which effectively improves the user experience.

[0088] For example, when cleaning an area to be cleaned, semantic information of different objects located on the moving path is determined; different safe execution distances for the different objects are determined based on the semantic information of the different objects; and the sweeping robot is controlled to perform cleaning tasks and / or obstacle avoidance tasks according to the different safe execution distances for the different objects. The specific implementation of this embodiment will be described in detail below.

[0089] In related technologies, considering that when a sweeping robot performs a cleaning task in an area to be cleaned, there may be different objects in the area to be cleaned, the sweeping robot may be at risk of colliding with different objects during the cleaning task, thereby causing damage to the sweeping robot or the objects.

[0090] In response to the above-mentioned problems, an embodiment of the present application provides a control method for a sweeping robot, which can control the sweeping robot to perform cleaning tasks and / or obstacle avoidance tasks according to different safe execution distances of different objects, thereby protecting both the sweeping robot and the objects during the cleaning process, and realizing more flexible, intelligent and safe execution of cleaning tasks and / or obstacle avoidance tasks.

[0091] Please refer to Figure 7, which is a flow chart of a control method for a sweeping robot provided in an embodiment of the present application. The method is applied to the sweeping robot, and the method includes:

[0092] In step S201 , semantic information of different objects on the moving path is determined.

[0093] In step S202 , different safe execution distances for the different objects are determined according to the semantic information of the different objects.

[0094] In step S203, the cleaning robot is controlled to perform a cleaning task and / or an obstacle avoidance task according to different safe execution distances of different objects.

[0095] In this embodiment, different safety distances between the sweeping robot and different objects are flexibly determined according to the semantic information of different objects, which can not only avoid collisions between the sweeping robot and different objects, but also clean all cleanable locations as much as possible, thereby achieving more flexible, intelligent and safe execution of cleaning tasks and / or obstacle avoidance tasks.

[0096] In some embodiments, before determining the semantic information of different objects on the moving path, the sweeping robot may receive the to-be-cleaned information sent by the terminal, and then plan the moving path of the sweeping robot according to the to-be-cleaned area indicated by the to-be-cleaned information. The to-be-cleaned area may be determined according to the first touch trajectory in the above embodiment; or it may be determined in other ways, such as a default cleaning area (such as the entire indoor environment), or according to the area selected in the environment map. This embodiment does not impose any restrictions on this.

[0097] Semantic information refers to meaningful information that can eliminate uncertainty about an object. The semantic information of different objects can distinguish the object types of different objects.

[0098] In one possible implementation, as shown in FIG3 , a robot vacuum cleaner includes a sensor system capable of sensing its surroundings. The sensor system may include, but is not limited to, a visual sensor, a lidar, an ultrasonic sensor, or an infrared sensor. While performing cleaning tasks along a moving path, the robot vacuum cleaner may acquire sensory data collected by the sensor system along the moving path and then identify semantic information about different objects along the moving path based on the sensory data.

[0099] The perception data includes, but is not limited to, at least one type of data, such as images, point clouds, ultrasonic signals, or infrared signals. For example, using images as the perception data, the robot vacuum cleaner can use a pre-trained semantic segmentation model to perform semantic segmentation on the image, obtaining semantic information about different objects along its path. Semantic segmentation is the process of classifying each pixel in an image, categorizing identical objects into one category and different objects into different categories.

[0100] In another possible implementation, the sweeping robot may pre-store an environmental map of the environment. Exemplarily, the environmental map includes a semantic map, which carries semantic information of different objects in the map. Exemplarily, the semantic map may be a pixel image (which may be in tif / tfw format), in which each pixel in the image corresponds to a real-world coordinate position, and the pixel stores a semantic information corresponding to the position, marking the object type corresponding to the position. In order to facilitate the use of the semantic map, a plurality of adjacent pixels with the same semantics may be combined into an image area. Each image area has corresponding semantic information. For example, please refer to FIG2 . The environmental map shown in FIG2 describes the semantic information corresponding to different image areas. For example, the semantic information of the image area in the upper left corner is "bedroom", the semantic information of the image area in the upper right corner is "bathroom", the semantic information of the image area in the lower left corner is "kitchen", the semantic information of the image area in the lower right corner is "living room", and the semantic information of the image area in the middle part is "corridor".

[0101] Semantic maps can be obtained in a variety of ways, regardless of their source. For example, semantic maps can come from robot vacuums, manual delineation by users, or downloads from third parties.

[0102] Exemplarily, the semantic map can be pre-built by a sweeping robot. For example, after the sweeping robot arrives at a new environment, it can move in the new environment and perceive the surrounding environment based on its own sensor system to obtain perception data during the movement. The sweeping robot can obtain semantic information in the environment based on the perception data, such as furniture, walls, doors or corridors, etc., thereby constructing a semantic map of the new environment.

[0103] For example, a semantic map can be input by a user into a robot vacuum or a terminal connected to the robot vacuum. In one example, a user can manually define a semantic map, such as displaying an environment map containing semantic information on the terminal's interactive interface. The user can then edit the semantic information in the environment map as needed, such as modifying the semantic information of various locations in the environment map, marking them as walls, sofas, steps, carpets, and other semantic information, thereby obtaining a semantic map.

[0104] For example, the semantic map may be automatically downloaded by the sweeping robot or a terminal connected to the sweeping robot from a third party. The semantic map may be constructed by a third-party device.

[0105] The semantic map can be stored in the local storage space of the robot or a terminal connected to it, and automatically retrieved from the storage space after the robot is powered on. As the robot performs its cleaning task along its movement path, it can use the pre-stored semantic map to search for semantic information about different objects along its path based on its current location.

[0106] In some embodiments, after determining the semantic information of different objects located on the moving path, the sweeping robot can determine different safe execution distances for the different objects based on the semantic information of the different objects. In one possible implementation, the sweeping robot pre-stores a first mapping relationship, which indicates different safe execution distances corresponding to objects with different semantic information. The sweeping robot can determine the different safe execution distances for the different objects from the pre-stored first mapping relationship based on the semantic information of the different objects, so as to achieve flexible, intelligent and safe execution of cleaning tasks and / or obstacle avoidance tasks.

[0107] The granularity of semantic information classification is adjustable. For example, the granularity can be increased based on actual needs. For example, different objects can be classified into objects to be cleaned and obstacles based on their semantic information; the different objects include obstacles and objects to be cleaned. The safe execution distance for objects to be cleaned is 0; the safe execution distance for obstacles is greater than or equal to 0.

[0108] For example, the granularity can be adjusted to a smaller value according to actual needs. For example, different obstacles can be divided into obstacles made of soft materials, obstacles made of ordinary materials, and obstacles made of fragile materials according to their semantic information; wherein, the safe execution distance of obstacles made of soft materials is smaller than that of obstacles made of ordinary materials, and the safe execution distance of obstacles made of ordinary materials is smaller than that of obstacles made of fragile materials.

[0109] For example, different obstacles include those made of soft materials, ordinary materials, and fragile materials. Soft obstacles can be cleaned very close to the robot vacuum, ensuring they do not harm the robot vacuum or the obstacle itself. Therefore, the safe distance for soft obstacles can be set to 0. For ordinary obstacles, to avoid collisions, a safe distance greater than 0 can be set, such as 1 to 5 cm. For fragile obstacles, to avoid causing catastrophic damage, a safe distance greater than 0 can be set, such as greater than 5 cm.

[0110] Of course, there may be other ways to divide different obstacles, and this embodiment does not impose any restrictions on this. For example, please refer to Table 1. For example, in an indoor environment, different objects can be divided into objects to be cleaned and obstacles according to a first granularity; then the obstacles and objects to be cleaned can be further divided according to a second granularity; wherein the first granularity is greater than the second granularity. Table 1 shows the safe execution distances corresponding to different obstacles and the safe distances corresponding to the objects to be cleaned. The sweeping robot can perform cleaning tasks and / or obstacle avoidance tasks more flexibly, intelligently and safely according to the different safe execution distances of the different objects. For example, it can perform cleaning tasks around obstacles according to the different safe execution distances of different obstacles; for example, it can perform obstacle avoidance tasks and bypass obstacles according to the different safe execution distances of different obstacles.

[0111] Table 1

[0112]

[0113]

[0114] In some embodiments, the robot vacuum can perform the obstacle avoidance task according to different obstacle avoidance strategies. For example, the different obstacle avoidance strategies indicate different obstacle avoidance methods and / or different obstacle avoidance speeds. In this embodiment, using different obstacle avoidance strategies for different obstacles is safer and more efficient.

[0115] In one possible implementation, the robot vacuum can determine the obstacle avoidance speed for different obstacles based on the semantic information of the different obstacles. For example, obstacles can be divided into obstacles made of soft materials, obstacles made of ordinary materials, and obstacles made of fragile materials based on their semantic information. The obstacle avoidance speed for obstacles made of soft materials is faster than that for obstacles made of ordinary materials, and the speed for obstacles made of ordinary materials is faster than that for obstacles made of fragile materials.

[0116] For example, obstacles made of soft materials can be cleaned very close to the robot vacuum, preventing damage to the soft obstacle itself. The obstacle avoidance speed for soft obstacles can be set to 5m / min. For obstacles made of ordinary materials, to avoid collisions, the obstacle avoidance speed can be set to 4m / min. For obstacles made of fragile materials, to avoid causing devastating damage, the obstacle avoidance speed can be set to 2m / min.

[0117] In one possible implementation, the robot vacuum can determine different obstacle avoidance strategies for different obstacles based on semantic information and / or physical parameters of the obstacles, thereby achieving more reasonable and safe obstacle avoidance. The physical parameters include, but are not limited to, height, width, diameter, object shape, and the like.

[0118] Exemplarily, the different obstacle avoidance methods include a first obstacle avoidance method and / or a second obstacle avoidance method; the first obstacle avoidance method indicates circumventing the obstacle from the side; the second obstacle avoidance strategy indicates climbing over the obstacle. In one example, the sweeping robot can pre-store a second mapping relationship, where the second mapping relationship indicates the obstacle avoidance methods corresponding to obstacles with different semantic information; the sweeping robot can determine the obstacle avoidance methods for different obstacles from the second mapping relationship based on the different semantic information of different obstacles. For example, the second mapping relationship can be shown in Table 2.

[0119] Table 2

[0120]

[0121] Exemplarily, a sweeping robot can determine whether the physical parameters of an obstacle meet the preset climbing conditions of the sweeping robot; if the physical parameters of the obstacle do not meet the preset climbing conditions of the sweeping robot, the obstacle avoidance method corresponding to the obstacle is the first obstacle avoidance method; if the physical parameters of the obstacle meet the preset climbing conditions of the sweeping robot, the obstacle avoidance method corresponding to the obstacle is the second obstacle avoidance method. The physical parameters include but are not limited to height, width, diameter, object shape, etc. This embodiment determines a reasonable and safe obstacle avoidance method based on the physical parameters of the obstacle, allowing the sweeping robot to perform obstacle avoidance tasks more flexibly, intelligently, and safely.

[0122] Taking the steps as an example, if the height of the steps is less than or equal to the preset climbing height of the sweeping robot, the obstacle avoidance method corresponding to the steps is the second obstacle avoidance method, that is, the sweeping robot can try to climb over the steps; conversely, if the height of the steps is greater than the preset climbing height of the sweeping robot, the obstacle avoidance method corresponding to the steps is the first obstacle avoidance method, that is, the sweeping robot can bypass the steps.

[0123] Taking a rope as an example, if the shape of the rope meets the preset shape indicated by the preset climbing condition of the sweeping robot, the obstacle avoidance method corresponding to the rope is the second obstacle avoidance method, meaning the sweeping robot can attempt to climb over the rope. Conversely, if the shape of the rope does not meet the preset shape indicated by the preset climbing condition, the obstacle avoidance method corresponding to the rope is the first obstacle avoidance method, meaning the sweeping robot can bypass the rope. In one possible implementation, the sweeping robot can jointly determine obstacle avoidance strategies for different obstacles based on the semantic information and physical parameters of the different obstacles. For example, candidate obstacle avoidance strategies for the obstacle are first determined based on the semantic information of the obstacle. If there are multiple candidate obstacle avoidance strategies, a target obstacle avoidance strategy corresponding to the obstacle is further selected from the multiple candidate obstacle avoidance strategies based on the physical parameters of the obstacle.

[0124] In one possible implementation, when the physical parameters of the obstacle meet the preset climbing conditions of the sweeping robot, the sweeping robot attempts to climb over the obstacle in a second obstacle avoidance mode. If the first climbing is successful, the sweeping robot can mark the obstacle avoidance mode corresponding to the obstacle as the second obstacle avoidance mode in the semantic map; if the climbing fails, the obstacle avoidance mode corresponding to the obstacle can be marked as the first obstacle avoidance mode in the semantic map; in the subsequent cleaning process, the obstacle avoidance task can be performed according to the marking information for the same obstacle in the semantic map, avoiding trying to climb over the obstacle that cannot be climbed again in the next cleaning process, thereby improving the cleaning efficiency. In some embodiments, the sweeping robot can determine different cleaning strategies for different objects based on the semantic information of different objects, and then perform the cleaning task according to the different cleaning strategies. Exemplarily, the sweeping robot can pre-store a third mapping relationship, and the third mapping relationship indicates the cleaning strategies corresponding to objects with different semantic information; in the process of performing the cleaning task, the sweeping robot can determine the cleaning strategies for different obstacles from the third mapping relationship based on the different semantic information of different objects. In this embodiment, different cleaning strategies are adopted for different objects, which is more energy-efficient and effectively improves the cleaning ability, so that the sweeping robot can perform cleaning tasks more flexibly and intelligently.

[0125] Exemplarily, the different cleaning strategies indicate different cleaning intensities. For example, the different cleaning strategies include 5 types, namely, off cleaning strategy, light cleaning strategy, medium cleaning strategy, heavy cleaning strategy and reciprocating cleaning strategy. For dust, a light cleaning strategy (cleaning intensity is light) can be adopted; for hair, paper scraps, etc., a medium cleaning strategy (cleaning intensity is medium) can be adopted; for larger liquid stains, larger solid dirt or food residues, etc., a heavy cleaning strategy (cleaning intensity is heavy) can be adopted; for oily, air-dried stains and other difficult-to-remove dirt, a reciprocating cleaning strategy can be adopted. For example, the above-mentioned third mapping relationship can be shown in Table 3.

[0126] Exemplarily, the reciprocating cleaning strategy instructs the cleaning robot to perform at least one of the following reciprocating cleaning: front-to-back reciprocating cleaning, left-to-right reciprocating cleaning, and rotating reciprocating cleaning.

[0127] For example, if the robot vacuum cleaner includes a flat mop that performs unidirectional scraping and cleaning, the robot vacuum cleaner's reciprocating cleaning strategy may be back-and-forth or left-and-right. If the robot vacuum cleaner includes a rotating mop that rotates its two mops inward, the robot vacuum cleaner's reciprocating cleaning strategy may be rotating reciprocating. Other cleaning strategies, such as an off cleaning strategy, a light cleaning strategy, a medium cleaning strategy, and a heavy cleaning strategy, can be distinguished by at least one of different cleaning powers, different mop pressures, different mop scrubbing frequencies, and different mop wetness levels.

[0128] For example, if the robot vacuum cleaner includes a brush and a suction port, and the brush includes a roller brush and / or a side brush, the robot vacuum cleaner may employ at least one of a forward-backward reciprocating cleaning strategy, a left-right reciprocating cleaning strategy, and a rotary reciprocating cleaning strategy, which is not limited in this embodiment. Other cleaning strategies, such as an off-cleaning strategy, a light cleaning strategy, a medium cleaning strategy, and a heavy cleaning strategy, may be distinguished by at least one of different cleaning powers, different suction port areas, different brush cleaning frequencies, and different brush downward pressures.

[0129] Table 3

[0130]

[0131] Among them, for objects with a safe execution distance greater than 0 and a cleaning strategy other than "off cleaning", the sweeping robot can perform cleaning tasks around the object according to the corresponding cleaning strategy based on the safe execution distance of different objects. For example, for walls, as shown in Table 1, the safe execution distance is 2cm, as shown in Table 3, the cleaning strategy is medium cleaning, then the sweeping robot can maintain a distance of 2cm from the wall and then use medium cleaning intensity for cleaning. For another example, for glass, as shown in Table 1, the safe execution distance is greater than 5cm, as shown in Table 3, the cleaning strategy is light cleaning, then the sweeping robot can maintain a distance of 2cm from the glass and then use light cleaning intensity for cleaning.

[0132] In some embodiments, the sweeping robot is provided with a visual sensor. Here, an example of the reciprocating cleaning strategy among different cleaning strategies is given: when the sweeping robot cleans the object to be cleaned at any cleaning position according to the reciprocating cleaning strategy, it can repeat the following steps until there is no object to be cleaned at the cleaning position: after cleaning the object to be cleaned at the cleaning position, using the visual sensor to capture an image of the cleaning position; based on the image, identifying whether there is any residual object to be cleaned at the cleaning position; if so, controlling the sweeping robot to repeatedly clean the object to be cleaned at the cleaning position. In this embodiment, for objects to be cleaned that are difficult to be thoroughly cleaned in one cleaning, a reciprocating cleaning strategy can be used for repeated cleaning, thereby effectively improving the cleaning ability of the sweeping robot.

[0133] For example, when the sweeping robot cleans the object to be cleaned at any cleaning position according to the reciprocating cleaning strategy, in order to reduce the number of reciprocating cleaning times, the cleaning intensity adopted by the sweeping robot in the non-first cleaning process can be higher than the cleaning intensity adopted in the previous cleaning process, thereby improving the cleaning efficiency.

[0134] Exemplarily, the sweeping robot is provided with at least two visual sensors. The field of view directions of the at least two visual sensors satisfy: the field of view direction of one visual sensor is the same as the cleaning direction of the sweeping robot, and the field of view direction of the other visual sensor is opposite to the cleaning direction. Wherein, when the sweeping robot cleans the object to be cleaned at any cleaning position according to the reciprocating cleaning strategy, the cleaning directions of two adjacent cleaning processes are opposite, and after cleaning is completed, the visual sensor with the field of view direction opposite to the cleaning direction is used to collect the image, so that whether there is any residual object to be cleaned at the same cleaning position can be detected without turning the head direction of the body, thereby improving the detection efficiency and cleaning efficiency.

[0135] For example, please refer to Figure 8. The sweeping robot is equipped with a forward-looking sensor and a rear-looking sensor. When the sweeping robot cleans the object to be cleaned at any cleaning position according to the reciprocating cleaning strategy, for example, the first time it cleans according to the first cleaning direction, and after cleaning is completed, the rear-looking sensor is used to collect images. When it is determined based on the image collected by the rear-looking sensor that there are residual objects to be cleaned at the cleaning position, cleaning is performed in the second cleaning direction, which is opposite to the first cleaning direction. After cleaning is completed, the forward-looking sensor is used to collect images. Similarly, when it is determined based on the image collected by the forward-looking sensor that there are residual objects to be cleaned at the cleaning position, cleaning is performed in the first cleaning direction, and so on. The sweeping robot cannot turn its head during the reciprocating cleaning process, thereby improving the detection efficiency and cleaning efficiency.

[0136] Of course, the robot vacuum cleaner is not limited to using a visual sensor to detect whether there are any remaining objects to be cleaned when a reciprocating cleaning strategy is used for cleaning. The visual sensor can also be used to detect whether there are any remaining objects to be cleaned when other cleaning strategies are used for cleaning.

[0137] In one possible implementation, after determining the cleaning strategy for the object to be cleaned at a certain cleaning position, the sweeping robot cleans the object to be cleaned at the cleaning position according to the cleaning intensity indicated by the determined cleaning strategy, and uses a visual sensor to collect an image of the cleaning position after cleaning is completed; based on the image, it identifies whether there are any residual objects to be cleaned at the cleaning position; if so, the cleaning strategy corresponding to the object to be cleaned is modified to a cleaning strategy with higher cleaning intensity, and the object to be cleaned at the cleaning position is repeatedly cleaned according to the modified cleaning strategy, and the mapping relationship between the semantic information of the object to be cleaned and the new cleaning strategy is saved, so that the object to be cleaned can be cleaned according to the new cleaning strategy when the cleaning task is performed next time, thereby reducing the number of cleaning times and improving cleaning efficiency.

[0138] In some embodiments, the different cleaning strategies indicate different cleaning intensities. The different cleaning intensities indicate that at least one of the following is different for the sweeping robot: the cleaning power of the sweeping robot, the execution parameters of the execution system of the sweeping robot. For example, the execution parameters of the execution system of the sweeping robot include at least one of the following: the area of ​​the suction port of the sweeping robot, the cleaning frequency of the brush of the sweeping robot, the scrubbing frequency of the mop of the sweeping robot, the downward pressure of the brush or mop of the sweeping robot, and the wetness of the mop of the sweeping robot, etc. This embodiment adjusts at least one of the above factors of the sweeping robot so that the sweeping robot can clean different objects with different cleaning strategies, thereby improving the cleaning flexibility and intelligence of the sweeping robot.

[0139] Regarding vacuuming methods, given a fixed suction port area, a robot vacuum's cleaning power and cleaning intensity are positively correlated; higher cleaning power translates to stronger cleaning intensity. For a fixed cleaning power, there's a negative correlation between the suction port area and the robot vacuum's cleaning intensity; the smaller the suction port area, the stronger the cleaning intensity.

[0140] For brush cleaning, the robot's cleaning power, brush frequency, and brush pressure are positively correlated with cleaning intensity. With other factors remaining constant, higher cleaning power translates to stronger cleaning intensity; higher brush frequency translates to stronger cleaning intensity; and greater brush pressure translates to stronger cleaning intensity, and vice versa.

[0141] For mopping, the robot's cleaning power, mop frequency, mop pressure, and mop wetness all have positive correlations with cleaning intensity. With other factors remaining constant, higher cleaning power translates to stronger cleaning intensity; higher mop frequency translates to stronger cleaning intensity; greater mop pressure translates to stronger cleaning intensity; and higher mop wetness translates to stronger cleaning intensity.

[0142] Here, a schematic illustration of the change in the area of ​​the suction port is provided: in one possible implementation, the suction assembly of the robot vacuum includes a suction port and a movable baffle engaged with the suction port; an execution parameter of the suction assembly is related to the movement of the movable baffle, wherein the execution parameter is the area of ​​the suction port. The movement of the movable baffle blocks the suction port, thereby changing the area of ​​the suction port.

[0143] Exemplarily, the movable baffle can be manually moved. For example, the movable baffle has texture, and the movable baffle can be moved by friction between the hand and the texture; for another example, the movable baffle has a notch, and the movable baffle can be moved by pressing the notch.

[0144] Exemplarily, the sweeping robot further includes a driving device for driving the movable baffle to move.

[0145] In one example, the driving device can be a manual driving device, for example, the driving device includes a mechanical switch 101 for driving the movable baffle to move to different positions; for example, please refer to Figure 9, which shows a mechanical switch 101 that can drive the movable baffle to move to three different positions. The three different positions correspond to the three gears of the mechanical switch 101. By toggling the mechanical switch 101 to different gears, the movable baffle can be driven up and down to the position of the corresponding gear, thereby adjusting the size of the suction port. The three gears of the mechanical switch 101 include a minimum suction gear mechanical switch, a standard suction gear mechanical switch, and a maximum suction gear mechanical switch. Among them, the minimum suction gear mechanical switch indicates the largest suction port area and the lowest corresponding suction port wind speed. This gear is suitable for light daily dust cleaning (corresponding to the light cleaning strategy). The standard suction gear mechanical switch indicates a smaller suction port area than the minimum suction gear mechanical switch, and the corresponding suction port wind speed is moderate, suitable for general daily household cleaning (corresponding to the moderate cleaning strategy). The suction port area indicated by the maximum suction gear mechanical switch is the smallest among the three, smaller than the suction port area indicated by the standard suction gear mechanical switch. The corresponding suction port wind speed is the largest. This gear is suitable for daily cleaning of heavily dirty floors (corresponding to the heavy cleaning strategy).

[0146] In another example, the drive device may be an electric drive device. The drive device includes a motor and a transmission mechanism; wherein the motor drives the movable baffle to move via the transmission mechanism. The sweeping robot may control the rotation of the motor based on a determined cleaning strategy for the object to be cleaned, thereby driving the movable baffle to a corresponding position via the transmission mechanism, so that the sweeping robot can clean the object to be cleaned using the corresponding cleaning strategy.

[0147] In another possible implementation, the vacuum cleaner assembly of the robot vacuum includes a vacuum port and multiple removable baffles configured to cooperate with the vacuum port. The multiple removable baffles have different execution parameters for the vacuum port. The execution parameters of the vacuum port are associated with the different removable baffles, wherein the execution parameter is an area covered by the vacuum port. The area of ​​the vacuum port changes as the different removable baffles are replaced.

[0148] In some embodiments, referring to FIG. 10 , the robot vacuum cleaner further includes a wind speed sensor 102 positioned near the suction port. During the cleaning process, the robot vacuum cleaner can obtain the actual wind speed at the suction port, as detected by the wind speed sensor 102. If the actual wind speed is lower than the reference wind speed indicated by the current cleaning strategy, the robot vacuum cleaner's cleaning power is adjusted to increase the wind speed to the reference wind speed. This embodiment dynamically adjusts the robot vacuum cleaner's cleaning power by using wind speed as a control target, thereby ensuring no loss of suction power during operation and ensuring effective cleaning.

[0149] The various technical features in the above embodiments can be arbitrarily combined as long as there is no conflict or contradiction between the combinations of features. Therefore, the arbitrary combination of the various technical features in the above embodiments also falls within the scope of disclosure of this specification.

[0150] Correspondingly, referring to FIG11 , an embodiment of the present application further provides a control device 121 of a sweeping robot, comprising one or more processors 1211 ; a memory 1212 for storing instructions executable by the processors;

[0151] The one or more processors 1211 execute the executable instructions individually or collectively to:

[0152] Determine the semantic information of different objects located on the movement path;

[0153] determining different safe execution distances for the different objects based on semantic information of the different objects;

[0154] The sweeping robot is controlled to perform cleaning tasks and / or obstacle avoidance tasks according to the different safe execution distances of the different objects.

[0155] The processor 1211 executes the executable instructions included in the memory 1212. The processor 1211 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0156] The memory 1212 stores executable instructions for the control method. The memory 1212 may include at least one type of storage medium, including flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, a magnetic disk, an optical disk, etc. Moreover, the device may cooperate with a network storage device that performs the storage function of the memory via a network connection. The memory 1212 may be an internal storage unit of the control device 121, such as a hard disk or memory of the control device 121. The memory 1212 may also be an external storage device of the control device 121, such as a plug-in hard disk equipped on the control device 121, a smart memory card (SMC), a secure digital (SD) card, a flash card, etc. Furthermore, the memory 1212 may include both an internal storage unit of the control device 121 and an external storage device. The memory 1212 is used to store the computer program 55 and other programs and data required by the device. The memory 1212 can also be used to temporarily store data that has been output or is to be output.

[0157] In some embodiments, the different objects include different obstacles; the different obstacles are obtained based on semantic information of the different objects. The processor 1211 is specifically configured to execute the obstacle avoidance task according to different obstacle avoidance strategies for different obstacles.

[0158] In some embodiments, the different obstacle avoidance strategies indicate different obstacle avoidance methods and / or different obstacle avoidance speeds.

[0159] In some embodiments, the different obstacle avoidance modes are determined based on semantic information and / or physical parameters of the different obstacles; and the different obstacle avoidance speeds are determined based on semantic information of the different obstacles.

[0160] In some embodiments, the different obstacle avoidance methods include a first obstacle avoidance method; the first obstacle avoidance method indicates to go around the side of the obstacle; if the physical parameters of the obstacle do not meet the preset climbing conditions of the sweeping robot, the obstacle avoidance method corresponding to the obstacle is the first obstacle avoidance method; the different obstacle avoidance methods include a second obstacle avoidance method, and the second obstacle avoidance strategy indicates to climb over the obstacle; if the physical parameters of the obstacle meet the preset climbing conditions of the sweeping robot, the obstacle avoidance method corresponding to the obstacle is the second obstacle avoidance method.

[0161] In some embodiments, the different safe execution distances of the different objects are determined from a pre-stored first mapping relationship according to semantic information of the different objects, where the first mapping relationship indicates different safe execution distances corresponding to objects with different semantic information.

[0162] In some embodiments, the different objects include obstacles and objects to be cleaned; the obstacles and objects to be cleaned are divided based on semantic information of the different objects; the safe execution distance of the objects to be cleaned is 0; and the safe execution distance of the obstacles is greater than or equal to 0.

[0163] In some embodiments, different obstacles include obstacles made of soft materials, obstacles made of ordinary materials, and obstacles made of fragile materials; the different materials of the different obstacles are divided based on the semantic information of the different obstacles; the safe execution distance of obstacles made of soft materials is smaller than the safe execution distance of obstacles made of ordinary materials, and the safe execution distance of obstacles made of ordinary materials is smaller than the safe execution distance of obstacles made of fragile materials.

[0164] In some embodiments, the processor 1211 is specifically configured to execute the cleaning task according to different cleaning strategies; wherein the different cleaning strategies are determined based on semantic information of the different objects.

[0165] In some embodiments, the different cleaning strategies indicate different cleaning intensities.

[0166] In some embodiments, the different cleaning intensities indicate that the cleaning powers of the cleaning robot and / or the areas of the suction ports of the cleaning robot are different.

[0167] In some embodiments, the sweeping robot further includes a movable baffle cooperating with the dust suction port; the area of ​​the dust suction port is related to the movement of the movable baffle; or the sweeping robot further includes multiple detachable baffles cooperating with the dust suction port, and the multiple detachable baffles have different blocking areas for the dust suction port; the area of ​​the dust suction port is related to different detachable baffles.

[0168] In some embodiments, the sweeping robot further includes a driving device for driving the movable baffle to move.

[0169] In some embodiments, the driving device includes a mechanical switch for driving the movable baffle to move to different positions; or the driving device includes a motor and a transmission mechanism; wherein the motor drives the movable baffle to move through the transmission structure.

[0170] In some embodiments, the sweeping robot also includes a wind speed sensor arranged near the suction port; the processor 1211 is also used to obtain the actual wind speed of the suction port collected by the wind speed sensor during the execution of the cleaning task; when the actual wind speed is lower than the reference wind speed indicated by the current cleaning strategy, the cleaning power of the sweeping robot is adjusted with the goal of increasing the wind speed to the reference wind speed.

[0171] In some embodiments, the sweeping robot is provided with a visual sensor; the different cleaning strategies include at least a reciprocating cleaning strategy; the object includes an object to be cleaned; the processor 1211 is specifically used to repeat the following steps until there is no object to be cleaned at any cleaning position when cleaning the object to be cleaned at the cleaning position according to the reciprocating cleaning strategy: after cleaning the object to be cleaned at the cleaning position, using the visual sensor to collect an image of the cleaning position; based on the image, identify whether there is any residual object to be cleaned at the cleaning position; if so, control the sweeping robot to repeatedly clean the object to be cleaned at the cleaning position.

[0172] In some embodiments, when the sweeping robot cleans the object to be cleaned at any cleaning position according to the reciprocating cleaning strategy, the cleaning intensity adopted by the sweeping robot in a non-first cleaning process is higher than the cleaning intensity adopted in the previous cleaning process.

[0173] In some embodiments, the sweeping robot is provided with at least two visual sensors; the field of view directions of the at least two visual sensors satisfy: the field of view direction of one visual sensor is the same as the cleaning direction of the sweeping robot, and the field of view direction of the other visual sensor is opposite to the cleaning direction; wherein, when the sweeping robot cleans the object to be cleaned at any cleaning position according to the reciprocating cleaning strategy, the cleaning directions of two adjacent cleaning processes are opposite, and after cleaning is completed, the visual sensor with the field of view direction opposite to the cleaning direction is used to collect the image.

[0174] In some embodiments, before determining the semantic information of different objects located on the moving path, the processor 1211 is also used to receive information to be cleaned; and plan the moving path of the sweeping robot according to the area to be cleaned indicated by the information to be cleaned; wherein, the area to be cleaned is determined based on the received first touch trajectory, and the first touch trajectory includes at least one of the following: a smear trajectory, a pressing trajectory, or a sliding operation trajectory in the form of a closed sliding trajectory.

[0175] Various embodiments described herein can be implemented using a computer-readable medium such as computer software, hardware, or any combination thereof. For hardware implementation, the embodiments described herein can be implemented by using at least one of an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a processor, a controller, a microcontroller, a microprocessor, an electronic unit designed to perform the functions described herein. For software implementation, embodiments such as processes or functions can be implemented with a separate software module that allows execution of at least one function or operation. Software code can be implemented by a software application (or program) written in any appropriate programming language, and the software code can be stored in a memory and executed by a controller.

[0176] The implementation process of the functions and effects of each unit in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here.

[0177] Accordingly, an embodiment of the present application further provides a sweeping robot, comprising:

[0178] body;

[0179] a power system, disposed in the body, for providing power to the sweeping robot; and

[0180] The above-mentioned control device is arranged in the body.

[0181] For the relevant description of the sweeping robot, please refer to the description of the embodiment in FIG3 , which will not be repeated here.

[0182] Correspondingly, referring to FIG1 , an embodiment of the present application further provides a control system, including a sweeping robot and a terminal.

[0183] Exemplarily, the terminal is used to display an environment map in an interactive interface; in response to a first touch operation received on the interactive interface, a first touch trajectory is generated; wherein the first touch trajectory may include at least one of the following: a smear trajectory, a pressing trajectory, or a sliding operation trajectory in the form of a closed sliding trajectory; based on the first touch trajectory and the environment map, an area to be cleaned in the environment is determined; and based on the area to be cleaned, a sweeping robot is controlled to perform a cleaning task in the environment.

[0184] The terminal is also used to determine the area to be cleaned in the environment based on the area covered by several circles with the first touch track (for example, the smear track) as the center in the environment map; wherein the radius of the circle is determined based on the first instruction.

[0185] The terminal is further used to obtain a plurality of circles with the smear trajectory as the center, and to fit the plurality of circles to obtain a closed figure; and to determine the area to be cleaned in the environment according to the area covered by the closed figure in the environment map.

[0186] The terminal is further configured to obtain the current position of the robot vacuum cleaner, determine a movement path based on the current position of the robot vacuum cleaner and the area to be cleaned, and control the robot vacuum cleaner to move along the movement path. The movement path includes at least: a first movement path representing the path from the current position of the robot vacuum cleaner to the area to be cleaned; and / or a second movement path representing the path of the robot vacuum cleaner while performing a cleaning task within the area to be cleaned.

[0187] The terminal is used to control the sweeping robot to move on the moving path, specifically for: when the sweeping robot receives the area to be cleaned, under a first condition, controlling the sweeping robot to move from the current position via the first moving path to the area to be cleaned, or under a second condition, prioritizing the control of the sweeping robot to move from the current position via the first moving path to the area to be cleaned, or under a third condition, prioritizing the control of the sweeping robot to continue to perform the current basic task.

[0188] The terminal is also used to determine the semantic information of different objects located on the moving path; determine the different safe execution distances of the different objects based on the semantic information of the different objects; and control the sweeping robot to perform cleaning tasks and / or obstacle avoidance tasks according to the different safe execution distances of the different objects.

[0189] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions, such as a memory including instructions, is also provided. The instructions are executable by a processor of a device to perform the above method. For example, the non-transitory computer-readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, or the like.

[0190] A non-transitory computer-readable storage medium enables the terminal to perform the above method when instructions in the storage medium are executed by a processor of the terminal.

[0191] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device that includes a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements that are inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a..." does not exclude the presence of other identical elements in the process, method, article or device that includes the element.

[0192] The above is a detailed introduction to the methods and devices provided in the embodiments of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the methods and core ideas of the present application. At the same time, for those skilled in the art, based on the ideas of the present application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A control method for a sweeping robot, characterized in that: Applied to sweeping robots, including: Determine the semantic information of different objects located on the moving path; Determining different safe execution distances of the different objects according to the semantic information of the different objects; The cleaning robot is controlled to perform cleaning tasks and / or obstacle avoidance tasks according to the different safe execution distances of the different objects.

2. The method according to claim 1, characterized in that The different objects include different obstacles; the different obstacles are obtained based on the semantic information of the different objects; Perform obstacle avoidance tasks, including: For different obstacles, the obstacle avoidance task is performed according to different obstacle avoidance strategies.

3. The method according to claim 2, characterized in that The different obstacle avoidance strategies indicate different obstacle avoidance modes and / or different obstacle avoidance speeds.

4. The method according to claim 3, characterized in that The different obstacle avoidance modes are determined according to the semantic information and / or physical parameters of the different obstacles; The different obstacle avoidance speeds are determined according to semantic information of the different obstacles.

5. The method according to claim 4, characterized in that The different obstacle avoidance modes include a first obstacle avoidance mode; the first obstacle avoidance mode indicates to go around the obstacle from the side; If the physical parameters of the obstacle do not meet the preset climbing conditions of the sweeping robot, the obstacle avoidance method corresponding to the obstacle is the first obstacle avoidance method.

6. The method according to claim 4, characterized in that The different obstacle avoidance modes include a second obstacle avoidance mode; the second obstacle avoidance strategy indicates climbing over an obstacle; If the physical parameters of the obstacle meet the preset climbing conditions of the sweeping robot, the obstacle avoidance method corresponding to the obstacle is the second obstacle avoidance method.

7. The method according to any one of claims 1 to 6, characterized in that: The different safe execution distances of different objects are determined from a pre-stored first mapping relationship according to the semantic information of the different objects, and the first mapping relationship indicates different safe execution distances corresponding to objects with different semantic information.

8. The method according to any one of claims 1 to 7, characterized in that: The different objects include obstacles and objects to be cleaned; the obstacles and objects to be cleaned are obtained by dividing the different objects based on semantic information; The safe execution distance of the object to be cleaned is 0; The safe enforcement distance of the obstacle is greater than or equal to 0.

9. The method according to claim 8, characterized in that The different obstacles include obstacles made of soft materials, obstacles made of ordinary materials, and obstacles made of fragile materials; the different materials of the different obstacles are obtained based on the semantic information of the different obstacles; The safe execution distance of obstacles made of soft materials is shorter than that of obstacles made of ordinary materials, and the safe execution distance of obstacles made of ordinary materials is shorter than that of obstacles made of fragile materials.

10. The method according to any one of claims 1 to 9, characterized in that: Perform cleaning tasks including: The cleaning task is performed according to different cleaning strategies; wherein the different cleaning strategies are determined according to the semantic information of the different objects.

11. The method according to claim 10, characterized in that The different cleaning strategies indicate different cleaning intensities.

12. The method according to claim 11, characterized in that The different cleaning intensities indicate that the cleaning powers of the cleaning robot and / or the execution parameters of the execution system of the cleaning robot are different.

13. The method according to claim 12, characterized in that The execution system includes at least one of the following: a dry cleaning component, a dust collection component, and a wet cleaning component.

14. The method according to claim 13, characterized in that The dust suction component comprises a dust suction port and a movable baffle matched with the dust suction port; an execution parameter of the dust suction component is related to the movement of the movable baffle, wherein the execution parameter is the area of ​​the dust suction port; or The dust suction component includes a dust suction port and a plurality of detachable baffles cooperating with the dust suction port, wherein the plurality of detachable baffles have different execution parameters for the dust suction component; the execution parameters of the dust suction component are related to different detachable baffles, wherein the execution parameters are the blocking area of ​​the dust suction port.

15. The method according to claim 14, characterized in that The cleaning robot further comprises a driving device for driving the movable baffle to move.

16. The method according to claim 15, characterized in that The driving device includes a mechanical switch for driving the movable baffle to move to different positions; or The driving device includes a motor and a transmission mechanism; wherein the motor drives the movable baffle to move through the transmission structure.

17. The method according to any one of claims 10 to 16, characterized in that: The sweeping robot further includes a wind speed sensor disposed near the suction port; The method further comprises: In the process of performing the cleaning task, obtaining the actual wind speed of the suction port collected by the wind speed sensor; When the actual wind speed is lower than the reference wind speed indicated by the current cleaning strategy, the cleaning power of the sweeping robot is adjusted with the goal of increasing the wind speed to the reference wind speed.

18. The method according to any one of claims 10 to 17, characterized in that: The sweeping robot is provided with a visual sensor; the different cleaning strategies include at least a reciprocating cleaning strategy; the object includes an object to be cleaned; The performing of the cleaning task according to different cleaning strategies comprises: When cleaning an object to be cleaned at any cleaning position according to the reciprocating cleaning strategy, the following steps are repeatedly performed until there is no object to be cleaned at the cleaning position: After cleaning the object to be cleaned at the cleaning position, collecting an image of the cleaning position using the visual sensor; Identify whether there is any residual object to be cleaned at the cleaning position based on the image; If so, the cleaning robot is controlled to repeatedly clean the object to be cleaned at the cleaning position.

19. The method according to claim 18, characterized in that When the cleaning robot cleans the object to be cleaned at any cleaning position according to the reciprocating cleaning strategy, the cleaning intensity adopted by the cleaning robot in a non-first cleaning process is higher than the cleaning intensity adopted in the last cleaning process.

20. The method according to claim 19, characterized in that The sweeping robot is provided with at least two visual sensors; The field of view directions of the at least two visual sensors satisfy: the field of view direction of one of the visual sensors is the same as the cleaning direction of the cleaning robot, and the field of view direction of the other visual sensor is opposite to the cleaning direction; When the sweeping robot cleans the object to be cleaned at any cleaning position according to the reciprocating cleaning strategy, the cleaning directions of two adjacent cleaning processes are opposite, and after cleaning is completed, a visual sensor with a field of view direction opposite to the cleaning direction is used to collect the image.

21. The method according to any one of claims 1 to 20, characterized in that Before determining the semantic information of different objects on the moving path, the method further includes: Receive information to be cleaned; The moving path of the sweeping robot is planned according to the area to be cleaned indicated by the information to be cleaned; wherein the area to be cleaned is determined according to a received first touch trajectory, and the first touch trajectory includes at least one of the following: a smearing trajectory, a pressing trajectory, or a sliding operation trajectory in the form of a closed sliding trajectory.

22. A control method for a sweeping robot, characterized in that: Applied to a terminal, the method comprises: Display the environment map in the interactive interface; In response to a first touch operation received on the interactive interface, generating a first touch track; Determining an area to be cleaned in the environment according to the first touch track and the environment map; The sweeping robot is controlled to perform a cleaning task in the environment according to the area to be cleaned.

23. The method according to claim 22, characterized in that The step of determining the area to be cleaned in the environment according to the first trajectory and the environment map includes: The area to be cleaned in the environment is determined according to the area covered by a plurality of circles with the first touch track as the center in the environment map; wherein the radius of the circle is determined based on the first instruction.

24. The method according to claim 23, characterized in that The determining of the area to be cleaned in the environment includes: Acquire a plurality of circles with the first touch track as the center, and fit the plurality of circles to obtain a closed figure; The area to be cleaned in the environment is determined according to the area covered by the closed graphic in the environment map.

25. The method according to claim 22, characterized in that The controlling the sweeping robot to perform a cleaning task in the environment according to the area to be cleaned comprises: Obtaining the current position of the sweeping robot; Determining a moving path according to the current position of the sweeping robot and the area to be cleaned; The cleaning robot is controlled to move along the moving path.

26. The method according to claim 25, characterized in that The moving path at least includes: A first moving path, used to indicate a path from the current position of the mobile robot to the area to be cleaned; and / or The second moving path is used to represent the path of the mobile robot when performing the cleaning task in the area to be cleaned.

27. The method according to claim 26, characterized in that The controlling the sweeping robot to move along the moving path includes: When the cleaning robot receives the area to be cleaned, Under the first condition, the cleaning robot is controlled to move from the current position to the area to be cleaned via the first moving path, or Under the second condition, the cleaning robot is preferentially controlled to move from the current position to the area to be cleaned via the first moving path, or Under the third condition, the cleaning robot is preferentially controlled to continue to perform the current basic task.

28. The method according to any one of claims 25 to 27, characterized in that Also includes: Determine the semantic information of different objects located on the moving path; Determining different safe execution distances of the different objects according to the semantic information of the different objects; The cleaning robot is controlled to perform cleaning tasks and / or obstacle avoidance tasks according to the different safe execution distances of the different objects.

29. A control device for a sweeping robot, characterized in that: include: one or more processors; a memory for storing instructions executable by the processor; The one or more processors execute the executable instructions individually or collectively to perform the method according to any one of claims 1 to 21.

30. A sweeping robot, characterized in that: include: Body; A power system, disposed in the body, for providing power to the sweeping robot; as well as A control device as claimed in claim 29 disposed in the body.

31. A control system, characterized in that: Comprising the cleaning robot and the terminal as claimed in claim 30; The terminal is used to execute the method described in any one of claims 22 to 28.

32. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores executable instructions, and when the executable instructions are executed by a processor, the method according to any one of claims 1 to 28 is implemented.

Images