Control method and control unit for self-moving device, and self-moving device

Abstract

A control method and control unit for a self-moving device, and a self-moving device. The control method for a self-moving device comprises: acquiring device position information collected by a positioning apparatus and a region boundary of at least two working regions (step 102); determining a position attribute of the region boundary, the position attribute being used for indicating access and working restriction conditions at the region boundary (step 104); and, determining a working route of the self-moving device at the region boundary on the basis of the position attribute, and controlling the self-moving device to work along the working route, the working route being adapted to the restriction conditions (step 106). In this way, on the basis of the access and working restriction conditions at the region boundary, the present application dynamically adjusts the working route to adapt to the restriction conditions, so as to prevent omitted regions at the region boundary, thereby improving the working region coverage rate of the self-moving device, and ensuring safety of the self-moving device during advancing.

Description

Self-moving device control method, control unit, and self-moving device

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on November 23, 2023, with application number 202311567907.1 and invention name “Control method, control unit and self-moving device for self-mobile device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The embodiments of this specification relate to the field of artificial intelligence technology, and in particular to a control method, a control unit, and a self-moving device. Background Art

[0003] With the rapid development of computer technology, the internet, and artificial intelligence, autonomous devices are increasingly being used in all aspects of life and work, such as service robots, lawn mowers, and other robots. To enable autonomous mobility in real-world scenarios (i.e., physical spaces), it is necessary to use a positioning device on the autonomous device to locate and control its movement.

[0004] In the prior art, the working area environment of the self-mobile device is relatively complex. The user will divide the working area into multiple areas manually or automatically through an algorithm. Since the positioning device of the self-mobile device has positioning deviations in local areas and the navigation control has control deviations, there may be missed areas at the junction of adjacent areas. The coverage rate of the working area of ​​the self-mobile device is poor, and a more accurate method is needed to control or process the self-mobile device.

[0005] SUMMARY OF THE INVENTION In view of this, embodiments of this specification provide a method for controlling a self-moving device. One or more embodiments of this specification also relate to a control unit of a self-moving device, a self-moving device, a computer-readable storage medium, and a computer program to address technical deficiencies in the prior art.

[0006] According to a first aspect of an embodiment of this specification, a method for controlling a self-moving device is provided, wherein the self-moving device is provided with a positioning device, the method comprising:

[0007] Acquire device location information collected by the positioning device and the boundary of at least two working areas;

[0008] Determining a location attribute of the area boundary, wherein the location attribute is used to indicate a restriction on passage and work at the area boundary;

[0009] A working route of the self-moving device at the boundary of the area is determined according to the location attribute, and the self-moving device is controlled to work along the working route, wherein the working route is adapted to the restriction condition.

[0010] According to a second aspect of an embodiment of this specification, a control unit of a self-moving device is provided, wherein the self-moving device is provided with a positioning device, and the control unit includes:

[0011] an acquisition module configured to acquire device location information collected by the positioning device and a boundary between at least two working areas;

[0012] A first determining module is configured to determine a location attribute of the area boundary, wherein the location attribute is used to indicate a restriction on passage and work at the area boundary;

[0013] The second determining module is configured to determine a working route of the self-moving device at the boundary of the area according to the location attribute, and control the self-moving device to work along the working route, wherein the working route is adapted to the restriction condition.

[0014] According to a third aspect of the embodiments of this specification, a self-moving device is provided, including:

[0015] ontology,

[0016] A driving module, provided on the body, for driving the body to move forward;

[0017] An execution module, provided in the main body, for executing work tasks;

[0018] A positioning device, disposed on the body;

[0019] memory for storing computer programs;

[0020] A processor is coupled to the memory, and the program includes instructions. When the instructions are executed by the processor, the processor performs operations, including the operations of the above-mentioned control method for the mobile device.

[0021] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the above-mentioned control method of the mobile device are implemented.

[0022] According to a fifth aspect of the embodiments of this specification, a computer program is provided, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned method for controlling a self-mobile device.

[0023] One embodiment of the present specification provides a method for controlling a self-moving device, wherein a positioning device is provided on the self-moving device, and the method includes: obtaining device location information collected by the positioning device, and the regional boundary of at least two working areas; determining the location attributes of the regional boundary, wherein the location attributes are used to indicate the restrictions on passage and work at the regional boundary; determining the working route of the self-moving device at the regional boundary based on the location attributes, and controlling the self-moving device to work along the working route, wherein the working route is adapted to the restrictions.

[0024] One embodiment of this specification implements the determination of location attributes at regional boundaries. These location attributes can indicate restrictions on access and operation at these boundaries. Based on these location attributes, a working route for a mobile device at the regional boundary can be determined, and the mobile device can be controlled to operate along the determined working route, with the working route adapted to these restrictions. In this way, the corresponding working route can be dynamically adjusted to adapt to the restrictions on access and operation at the boundary of adjacent areas, avoiding missed areas at the boundary of adjacent areas, improving the coverage of the mobile device's working area, and ensuring the safety of the mobile device during travel. Furthermore, dynamically adjusting the corresponding working route at the boundary of adjacent areas can make the mobile device more intelligent and interactive. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] FIG1 is a flow chart of a method for controlling a self-moving device provided by one embodiment of this specification;

[0026] FIG2a is a schematic diagram of a mapping process of a mobile device provided by one embodiment of this specification;

[0027] FIG2 b is a schematic diagram of a first object type recognition process provided by an embodiment of this specification;

[0028] FIG2c is a schematic diagram of a second object type recognition process provided by an embodiment of this specification;

[0029] FIG2 d is a schematic diagram of a third object type recognition process provided by an embodiment of this specification;

[0030] FIG2e is a flow chart of a method for dynamically controlling a zigzag route provided in one embodiment of this specification;

[0031] FIG2f is a flow chart of a dynamic control method for a Yanbian route provided in an embodiment of this specification;

[0032] FIG2g is a schematic diagram of a bow-shaped route provided in an embodiment of this specification;

[0033] FIG2h is a schematic diagram of a Yanbian route provided in an embodiment of this specification;

[0034] FIG3 is a flowchart of a process of controlling a self-mobile device according to an embodiment of the present invention;

[0035] FIG4 is a schematic structural diagram of a control unit of a self-moving device provided by one embodiment of this specification;

[0036] FIG5 is a structural block diagram of a self-moving device provided by an embodiment of this specification. DETAILED DESCRIPTION

[0037] The following description sets forth many specific details to facilitate a thorough understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the scope of this specification. Therefore, this specification is not limited to the specific implementations disclosed below.

[0038] The terms used in one or more embodiments of this specification are for the purpose of describing specific embodiments only and are not intended to limit one or more embodiments of this specification. The singular forms "a," "an," and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0039] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0040] In an embodiment of this specification, a control method for a self-moving device is provided. This specification also relates to a control unit of a self-moving device, a self-moving device, and a computer-readable storage medium, which are described in detail one by one in the following embodiments.

[0041] 1 , which shows a flow chart of a method for controlling a self-moving device according to an embodiment of the present specification. The self-moving device is provided with a positioning device, and specifically includes the following steps 102 - 106 .

[0042] Step 102: Obtain the device location information collected by the positioning device, as well as the boundary of at least two working areas. Specifically, the positioning device refers to a component module set on the mobile device that can determine the current position of the mobile device. For example, the positioning module can be a positioning sensor, such as GPS or ultrasonic positioning, etc.; or, the positioning module can include an ordinary camera or fisheye camera, IMU module, panoramic camera, UWB tag, encoder, etc. Under this solution, UWB base stations need to be arranged around the area where the mobile device performs work tasks. The UWB base stations can be manually arranged around the area by users or manufacturer technicians, and can be reasonably arranged through the UWB base station layout recommendation algorithm. Of course, in actual applications, the positioning device can also refer to other component modules that can determine the current position of the mobile device, and the embodiments of this specification are not limited to this.

[0043] In addition, the self-moving device may be a service robot, a lawn mowing robot, etc.

[0044] It should be noted that the control unit on the mobile device can obtain the device location information collected by the positioning device to monitor the movement of the mobile device and determine the current location of the mobile device, thereby facilitating subsequent control of the travel route.

[0045] In addition, the regional boundaries of at least two working areas can also be obtained. The regional boundaries refer to the locations in the work map where regional boundaries exist, so as to combine the device location information of the self-mobile device and the regional boundaries to determine the location attributes of the regional boundaries and control the working route of the self-mobile device.

[0046] In an optional implementation of this embodiment, before monitoring the movement of the self-moving device, a map of the working area of ​​the self-moving device may be constructed, that is, before obtaining the device location information collected by the positioning device, the following steps may be further included:

[0047] Build a work map;

[0048] Divide the work map into at least two work areas and mark the boundaries between adjacent areas.

[0049] In practice, when a mobile device is used for the first time, it is necessary to map the work area. Specifically, the mobile device can be manually controlled to traverse each location where work tasks need to be performed, or the mobile device can automatically traverse each location where work tasks need to be performed to build a work map.

[0050] It should be noted that, because the working environment of a self-moving device is generally complex, the user can manually divide the work map into at least two work areas, or the algorithm can be used to automatically divide the work map into at least two work areas. In addition, to improve the work coverage rate of two adjacent work areas, the boundary between adjacent areas can be marked so that the self-moving device can be monitored to determine whether it moves near the boundary. Based on the traffic and work restrictions at the boundary, the working route of the self-moving device at the boundary can be dynamically adjusted to ensure that the working route of the self-moving device at the boundary adapts to the actual situation at the boundary, thereby improving the work coverage rate.

[0051] For example, Figure 2a is a schematic diagram of a mapping process of a self-mobile device provided by an embodiment of this specification. As shown in Figure 2a, mapping begins, and then the user remotely controls the self-mobile device / the self-mobile device automatically builds a working map; after the working map is built, it is automatically partitioned or manually partitioned by the user to obtain a contour map (the outer boundary map of the working map) and a partition map, and mapping is completed.

[0052] In an optional implementation of this embodiment, in addition to marking the boundary of adjacent areas, the location attribute of the boundary may be further marked. That is, after marking the boundary of adjacent areas, the following steps may be further included:

[0053] Mark location attributes at the intersection of regions between adjacent regions.

[0054] It should be noted that the location attributes are used to indicate the restrictions on access and work at the junction of adjacent areas. For example, the location attributes may include inaccessible and inoperable, passable and inoperable, operable, etc., so as to adjust the working route of the mobile device at the junction of areas based on the restrictions, so that the working route adapts to the restrictions on access and work at the junction of areas.

[0055] In a specific implementation, a marking operation of a user at a boundary of adjacent areas may be received, the marking operation carries a location attribute of the boundary, and the location attribute and the boundary are stored in correspondence.

[0056] In actual implementation, the boundary between adjacent areas is usually a boundary line with a certain length. Different points of the boundary may have different location attributes. Therefore, when marking the location attributes of the boundary between adjacent areas, if the entire boundary has the same attribute, the entire boundary can be marked with the location attribute; if the entire boundary has different attributes, the location attributes of each point of the boundary can be marked separately.

[0057] In the embodiments of the present specification, after marking the area boundaries of adjacent areas, the location attributes of the area boundaries can be further marked. Subsequently, the location attributes of the area boundaries can be directly obtained, and then the corresponding work routes can be adapted without further additional analysis of the traffic and work restrictions at the area boundaries, thereby improving the control efficiency of the self-moving equipment.

[0058] Step 104: Determine the location attributes of the area boundary, wherein the location attributes are used to indicate the restrictions on travel and work at the area boundary.

[0059] It should be noted that since the boundaries between adjacent areas often present complex environments and different restrictions, the environment at these boundaries can be analyzed and a corresponding work route can be adapted as the self-moving device moves. Specifically, the control unit can obtain the device's location information and the boundaries of at least two work areas during the self-moving device's movement. The control unit can then determine the location attributes of these boundaries, using these location attributes to indicate the restrictions on access and work at the boundary, thereby controlling the work route near the boundary.

[0060] In an optional implementation of this embodiment, when the mobile device moves near the area boundary, the location attribute of the area boundary may be determined. That is, determining the location attribute of the area boundary includes:

[0061] According to the device location information and the area boundaries of at least two working areas, it is determined whether there is an area boundary around the self-moving device; if so, a location attribute of the area boundary around the self-moving device is determined.

[0062] It should be noted that the control unit can obtain the device location information of the mobile device during the movement of the mobile device, and obtain the regional boundaries of at least two working areas, monitor the movement of the mobile device, and determine whether there is a regional boundary around the mobile device. If so, it means that the mobile device has moved to the vicinity of a certain regional boundary. At this time, the position attributes of the regional boundary around the mobile device can be determined.

[0063] In actual implementation, after dividing the working map into at least two working areas, the regional boundaries of each adjacent area can be marked. After receiving the device location information collected by the positioning device, the distance between the device location indicated by the device location information and the boundaries of each area can be calculated. If there is a position less than the distance threshold from a certain regional boundary, it means that the self-mobile device is currently close to the regional boundary, that is, there is a regional boundary around the self-mobile device, and the identifier of the regional boundary is obtained. Alternatively, after dividing the working map into at least two working areas, the regional boundaries of adjacent areas can be omitted. Instead, a partition map can be saved. After obtaining the device location information collected by the positioning device, the location information can be matched with the partition map to determine whether the current distance between the self-mobile device and a certain regional boundary is less than the distance threshold, thereby determining whether there is a regional boundary around the self-mobile device.

[0064] In specific implementation, when it is monitored that there is a regional boundary around the self-moving device, it means that the self-moving device is moving near the regional boundary. In order to adapt to the complex environment of the regional boundary, the position attribute of the regional boundary around the self-moving device can be determined. The position attribute is used to indicate the restrictions on passage and work at the regional boundary, thereby adapting the corresponding work route.

[0065] In one possible implementation, if the location attributes of the area boundaries are pre-marked, after determining that there is an area boundary around the mobile device, the identifier of the area boundary around the mobile device can be obtained, and the corresponding location attributes can be read directly based on the identifier of the area boundary.

[0066] In another possible implementation, if the location attributes of the region boundaries are not marked in advance, the location attributes of the region boundaries may be analyzed and identified.

[0067] In an optional implementation of this embodiment, the position attributes of the region boundary can be identified based on the object type analysis at the region boundary, that is, the position attributes of the region boundary are determined, including:

[0068] Determine the object type at the region boundary, and determine the location attribute of the region boundary based on the object type;

[0069] Among them, the object type includes restricted access type, unrestricted access type and work object type; the location attribute includes inaccessible and non-workable attribute, accessible and non-workable attribute and workable attribute.

[0070] In actual implementation, the object type at the intersection of the area can be analyzed and determined, and then based on the object type at the intersection of the area, whether the intersection of the area is passable and whether it is workable and other restrictions can be determined. The location attributes of the intersection of the area are determined, which makes it easier to adapt the corresponding work route based on the restrictions of passage and work, improve the coverage of the working area of ​​the self-moving equipment, and make the self-moving equipment more intelligent.

[0071] It should be noted that object types at the intersection of areas can be divided into restricted access types, unrestricted access types, and work object types. Restricted access types refer to inaccessible areas, such as obstacles and restricted areas. These restricted areas can include swimming pools, pits, cliffs, and other areas where self-moving devices cannot travel. Unrestricted access types refer to areas that are accessible but where self-moving devices cannot operate, such as cobblestone roads and cobblestones. Work object types refer to the objects that self-moving devices work on. For example, if the self-moving device is a lawn mower robot, the work object type is grass. In specific implementations, the object type of each object can be pre-configured, that is, each object can be divided into different types, such as restricted access types, unrestricted access types, and work object types.

[0072] In addition, different object types may correspond to different location attributes, including an inaccessible and inoperable attribute, a traversable and inoperable attribute, and a workable attribute.

[0073] In actual implementation, the location attributes corresponding to various object types can be pre-configured. After determining the object type at the intersection of the areas, the corresponding relationship can be queried to determine the location attributes of the area intersection. For example, the location attributes corresponding to the restricted access type can be pre-configured as inaccessible and non-operational, the location attributes corresponding to the unrestricted access type can be pre-configured as accessible and non-operational, and the location attributes corresponding to the work object type can be pre-configured as operable. In this way, the location attributes can be used to indicate the access and work restrictions at the area intersection, making it easier to subsequently adapt the corresponding work routes based on the access and work restrictions, improve the coverage rate of the working area of ​​the self-moving equipment, and make the self-moving equipment more intelligent.

[0074] It should be noted that an image acquisition device may be provided in the mobile device to acquire image information at the region boundary, analyze and identify the image information, and determine the type of object at the region boundary.

[0075] In an optional implementation of this embodiment, the mobile device is further provided with an image acquisition device; determining the type of object at the boundary of the area includes:

[0076] Acquiring image information of the region boundary captured by the image acquisition device;

[0077] Identify image information at the region junction and determine the object type at the region junction.

[0078] In an optional implementation of this embodiment, the image acquisition device includes a camera and / or a 3D sensor; identifying image information at the region boundary and determining the type of object at the region boundary includes:

[0079] Based on the image information collected by the camera and / or 3D sensor, the deep learning model is used to determine the type of object at the intersection of the area.

[0080] Specifically, the image acquisition device refers to a component module set on a mobile device that can acquire image information of the current position of the mobile device. For example, the image acquisition device can be a camera and / or a 3D sensor. The 3D sensor can be a sensor that can acquire three-dimensional point cloud information within a set distance in front. The 3D sensor is a TOF (Time of Flight) camera. The TOF camera continuously sends light pulses to the target and then receives the light returned from the target. By detecting the flight (round-trip) time of the light pulses, it obtains the three-dimensional point cloud information of the target. It can acquire a high-precision depth point cloud, thereby ensuring the accuracy of the acquired three-dimensional point cloud information of the channel. Of course, in actual applications, the 3D sensor can also be other sensors that can acquire three-dimensional point cloud information of the channel, such as a lidar, etc., and the embodiments of this specification are not limited to this.

[0081] In actual implementation, the image information of the area junction collected by the image acquisition device can be obtained, and then the image information can be identified and analyzed to determine the type of object at the area junction, so as to determine whether the area junction is passable and whether it can be worked according to the type of object at the area junction, and determine the location attributes of the area junction, so as to adapt the corresponding work route based on the restrictions of passage and work, improve the coverage rate of the working area of ​​the self-moving equipment, and make the self-moving equipment more intelligent.

[0082] In an optional implementation of this embodiment, determining the type of object at the boundary of regions using a deep learning model based on image information collected by a camera and / or a 3D sensor includes:

[0083] If the image acquisition device is a camera, the two-dimensional position image acquired by the camera is input into the image recognition model to obtain the target object at the junction of the regions;

[0084] If the image acquisition device is a 3D sensor, the three-dimensional point cloud information collected by the 3D sensor is input into the point cloud learning model to obtain the target object at the intersection of the area;

[0085] If the image acquisition device is a camera and a 3D sensor, the three-dimensional point cloud information acquired by the 3D sensor is mapped to the two-dimensional position image acquired by the camera to obtain combined point cloud information; the combined point cloud information is input into the point cloud learning model to obtain the target object at the junction of the regions;

[0086] Query the target type of the target object and use the target type as the object type at the region boundary.

[0087] Specifically, the image recognition model is a deep learning model for identifying objects within an image. It is pre-trained based on a large number of training samples, which can be images carrying corresponding object labels. This allows the trained image recognition model to accurately identify objects within the input image. Separately, the point cloud learning model is a deep learning model for identifying objects corresponding to three-dimensional point cloud information. It is pre-trained based on a large number of training samples, which can be three-dimensional point cloud information carrying corresponding object labels. This allows the trained point cloud learning model to accurately identify objects corresponding to the input three-dimensional point cloud information. In actual implementation, if a camera is provided on the mobile device, the camera can be used to capture a two-dimensional position image of the junction of the areas, and the two-dimensional position image can be input into a pre-trained image recognition model, and the target object at the junction of the areas can be identified through the image deep learning method; if a 3D sensor is provided on the mobile device, the 3D point cloud information at the junction of the areas can be collected through the 3D sensor, and the three-dimensional point cloud information can be input into a pre-trained point cloud learning model, and the target object at the junction of the areas can be identified through the point cloud deep learning method; if a camera and a 3D sensor are provided on the mobile device, the camera can be used to capture a two-dimensional position image of the junction of the areas, and the 3D point cloud information at the junction of the areas can be collected through the 3D sensor, and the three-dimensional point cloud information collected by the 3D sensor can be mapped to the two-dimensional position image collected by the camera to obtain combined point cloud information, and the combined point cloud information can be input into the pre-trained point cloud learning model, and the target object at the junction of the areas can be identified through the point cloud deep learning method. For example, Figure 2b is a schematic diagram of the recognition process of the first object type provided by an embodiment of this specification. As shown in Figure 2b, a two-dimensional position image of the intersection position is captured by a camera, and the two-dimensional position image is input into a pre-trained image recognition model. The object at the intersection position is identified through an image deep learning method. The object may include people, small animals, trees, flowers, hedges, landscape lights, swimming pools, pits, cliffs, stone roads, pebbles, ..., grass, etc., among which people, small animals, trees, flowers, hedges, landscape lights, swimming pools, pits, cliffs, stone roads, pebbles, ... all belong to restricted access types, people, small animals, trees, flowers, hedges, landscape lights, etc. belong to obstacles, swimming pools, pits, cliffs belong to restricted access areas, stone roads, pebbles, ... belong to non-restricted access types, and grass belongs to work object types.

[0088] As another example, Figure 2c is a schematic diagram of the recognition process of the second object type provided by an embodiment of this specification. As shown in Figure 2c, three-dimensional point cloud information at the intersection position is collected by a 3D sensor, and the 3D sensor is TOF. The three-dimensional point cloud information is input into a pre-trained point cloud learning model, and the object at the intersection position is identified through the point cloud deep learning method. The object may include people, small animals, trees, flowers, hedges, landscape lights, swimming pools, pits, cliffs, stone roads, pebbles, ..., grass, etc., among which people, small animals, trees, flowers, hedges, landscape lights, swimming pools, pits, cliffs, stone roads, pebbles, ... all belong to restricted access types, people, small animals, trees, flowers, hedges, landscape lights, etc. belong to obstacles, swimming pools, pits, cliffs belong to restricted access areas, stone roads, pebbles, ... belong to non-restricted access types, and grass belongs to work object types.

[0089] As another example, FIG2d is a schematic diagram of the recognition process of the third object type provided by an embodiment of the present specification. As shown in FIG2d, a two-dimensional position image of the intersection position is captured by a camera, and three-dimensional point cloud information of the intersection position is collected by a 3D sensor. The three-dimensional point cloud information collected by the 3D sensor is mapped to the two-dimensional position image collected by the camera to obtain combined point cloud information. The combined point cloud information is input into a pre-trained point cloud learning model, that is, the camera and the 3D sensor are combined to recognize the object through a point cloud deep learning method. Objects at the intersection may include people, small animals, trees, flowers, hedges, landscape lights, swimming pools, pits, cliffs, stone roads, pebbles, ..., grass, etc. Among them, people, small animals, trees, flowers, hedges, landscape lights, swimming pools, pits, cliffs, stone roads, pebbles, ... are all restricted access types, people, small animals, trees, flowers, hedges, landscape lights, etc. are obstacles, swimming pools, pits, cliffs are restricted access areas, stone roads, pebbles, ... are non-restricted access types, and grass is a work object type.

[0090] It should be noted that by collecting image information at the junction of regions through a camera and / or a 3D sensor, and using a deep learning method, i.e., a target detection method, the target object in the image information is identified, and the object type at the junction of regions can be obtained. The object type at the junction of regions is determined by a deep learning method, with high recognition accuracy and high recognition efficiency. In an optional implementation of this embodiment, the position attribute of the junction of regions is determined based on the object type, including: when the object type is a restricted access type, determining the position attribute of the junction of regions as an inaccessible and non-operational attribute;

[0091] When the object type is a non-restricted access type, the location attribute of the area boundary is determined to be passable and non-operational;

[0092] In the case where the object type is a work object type, the position attribute of the region boundary is determined to be a workable attribute.

[0093] It should be noted that, when the object type is a restricted access type, it means that the area junction is restricted, and the self-moving device cannot move at the area junction, otherwise it will hit an obstacle or enter an inaccessible restricted area, causing damage to the self-moving device, and the restricted access self-moving device will not be able to work. At this time, the position attribute of the area junction can be determined as an inaccessible and non-workable attribute. When the object type is a non-restricted access type, it means that the self-moving device can enter the area junction, but cannot perform work tasks at the area junction. At this time, the position attribute of the area junction can be determined as a passable and non-workable attribute. When the object type is a work object type, it means that the area junction is still an object where the self-moving device can perform work tasks. At this time, the position attribute of the area junction can be determined as a workable attribute.

[0094] In actual implementation, the correspondence between object type and position attribute can be pre-configured, as shown in Table 1 below.

[0095] Table 1 Correspondence between object type and location attributes

[0096] In the embodiments of the present specification, the object type at the area junction can be determined first, and then the corresponding location attributes can be determined based on the object type to indicate the restrictions on passage and work at the area junction. In this way, when a mobile device is monitored to be near the area junction, the restrictions on passage and work at the area junction can be monitored, so that the corresponding work route can be dynamically adjusted to adapt to the restrictions.

[0097] Step 106: Determine a working route of the mobile device at the boundary of the area according to the location attribute, and control the mobile device to work along the working route, wherein the working route is adapted to the restriction condition.

[0098] It should be noted that the location attributes can indicate the restrictions on passage and work at the intersection of areas. Therefore, it is necessary to determine the working route of the self-moving device at the intersection of areas based on the location attributes, so that the working route of the self-moving device at the intersection of areas can adapt to the restrictions of the intersection of the areas, achieve full work, ensure the coverage of the working area, and ensure the safety of the self-moving device.

[0099] In an optional implementation of this embodiment, determining the working route of the mobile device at the boundary of the area based on the location attribute includes:

[0100] When the location attribute is passable and non-workable, the initial travel route at the regional boundary is used as the work route at the regional boundary;

[0101] When the location attribute is other working attributes, the initial travel route of the area boundary is shrunk or expanded to determine the working route of the mobile device at the area boundary.

[0102] It should be noted that the initial route is a pre-configured route for the mobile device to travel through various areas. During configuration, this initial route often skips the boundaries between adjacent areas and does not perform work tasks. This may result in missing boundaries between adjacent areas, leading to low coverage of the work area. In actual implementation, for the passable but non-operational attribute, which indicates that the mobile device can travel through the boundary but cannot perform work tasks, there is no need to adjust the initial route. The initial route at the boundary can still be used as the work route at the boundary. The mobile device can directly cross the boundary according to the initial route and then continue working in the adjacent area without any special route changes.

[0103] In addition, for other working attributes besides the passable and non-workable attributes, it indicates that there are special passage or work restrictions at the junction of the area. The initial travel route needs to be retracted or expanded to adapt to the characteristics of the area junction and improve the coverage of the working area.

[0104] In an optional implementation of this embodiment, when the location attribute is other working attributes, the initial travel route at the regional intersection is contracted or expanded to determine the working route of the mobile device at the regional intersection, including: when the location attribute is inaccessible and non-working attributes, the initial travel route at the regional intersection is contracted to determine the working route of the mobile device at the regional intersection;

[0105] When the location attribute is a workable attribute, the initial travel route at the area boundary is expanded to determine the working route of the mobile device at the area boundary.

[0106] In actual implementation, the attributes of "inaccessible and non-operational" indicate that there are obstacles at the intersection of the areas or restricted areas that the self-moving equipment cannot enter. If the self-moving equipment continues to move along the initial route, it may collide with the obstacle or enter the restricted area, damaging the self-moving equipment. Therefore, the initial route at the intersection of the areas needs to be retracted to determine the working route of the self-moving equipment at the intersection of the areas, so that the working route can avoid obstacles or restricted areas that the self-moving equipment cannot enter, thereby ensuring the safety of the self-moving equipment.

[0107] In addition, for the workable attribute, it indicates that the area intersection is the working object of the self-moving device, that is, the self-moving device can pass through the area intersection and can also perform work tasks. If it moves according to the initial travel route, the area intersection will be skipped, resulting in area omission. Therefore, at this time, the initial travel route of the area intersection can be expanded outward to determine the working route of the self-moving device at the area intersection, so that the self-moving device can work on a part of the area from the area intersection to the outside, thereby improving the coverage rate of the working area.

[0108] In the embodiments of this specification, when the location attribute is impassable and non-operable, the device can be retracted a certain distance to bypass obstacles or restricted areas to ensure the safety of the self-moving device. Furthermore, when the location attribute is operable, the device can be expanded a certain distance to cover a larger area and improve the coverage of the working area. This allows the identification of object types at the boundaries of adjacent areas, and the algorithm can dynamically determine whether to expand or contract the boundaries to achieve greater or complete coverage of the working area.

[0109] It should be noted that the adaptation parameters for dynamic shrinking and dynamic expansion, such as the retraction distance and the expansion distance, can be pre-configured. In actual implementation, if it is determined that retraction or expansion is required, the pre-configured adaptation parameters can be obtained for dynamic adaptation to obtain the working route. In addition, in addition to being manually pre-configured, the adaptation parameters such as the retraction distance and the expansion distance can also be automatically calculated based on AI recognition according to the objects at the intersection of the identified areas, and the adaptation parameters such as the retraction distance and the expansion distance can be dynamically adjusted.

[0110] In an optional implementation of this embodiment, the initial route of the area boundary is contracted or expanded to determine the working route of the mobile device at the area boundary, including:

[0111] Obtaining a pre-configured adaptation parameter, wherein the adaptation parameter is a shrinking distance or an expanding distance;

[0112] An updated travel route having an adaptation parameter distance from the initial travel route in the direction of the first area is determined, and the updated travel route is used as a working route of the self-moving device at the intersection of the areas. In the case of inward contraction, the first area is the current working area of ​​the self-moving device; in the case of outward expansion, the first area is an adjacent area to the current working area of ​​the self-moving device.

[0113] It should be noted that pre-configured adaptation parameters can be obtained. For the case of inward contraction, an updated travel route with a contraction distance from the initial travel route in the direction of the current working area can be determined, and the updated travel route is used as the working route of the self-mobile device at the intersection of the areas, so that when the self-mobile device moves at the intersection of the areas, it retracts the set distance in the direction close to the current working area, bypassing obstacles or restricted areas. For the case of outward expansion, an updated travel route with a contraction distance from the initial travel route in the adjacent area of ​​the current working area of ​​the self-mobile device can be determined, and the updated travel route is used as the working route of the self-mobile device at the intersection of the areas, so that when the self-mobile device moves at the intersection of the areas, it expands the set distance in the direction close to the adjacent area of ​​the current working area, thereby allowing the self-mobile device to work in more areas outside the area intersection.

[0114] In actual applications, after determining the working route of the mobile device at the regional intersection based on the location attributes and controlling the mobile device to work along the working route, it is possible to return to the operation steps of obtaining the device location information collected by the positioning device and the regional intersection of at least two working areas, continue to monitor whether there is a regional intersection around the mobile device, and monitor the location attributes of the regional intersection if it exists, so as to dynamically adjust the working route of the mobile device until the work is completed.

[0115] During specific implementation, the initial travel route of the mobile device may be pre-configured, and the initial travel route may include multiple types, such as a bow-shaped route or an extended route.

[0116] FIG2e is a flow chart of a method for dynamically controlling a bow-shaped route provided in an embodiment of the present specification. As shown in FIG2e, the self-mobile device can first load a work map, traverse the various work areas included in the work map, select an unworked area as the current work area, and then start to move in a bow shape. The positioning sensor identifies that when it is determined that there is a boundary between areas around the self-mobile device, the image acquisition device determines the type of object at the boundary between the areas, and based on the object type, determines the location attribute of the boundary between the areas, and determines whether the location attribute is a workable attribute. If so, the bow-shaped route is expanded to a certain distance adjacent to the current work area. If not, it is determined whether the location attribute is an inaccessible and non-workable attribute. If so, the bow-shaped route is retracted to a certain distance from the current work area to prevent the self-mobile device from entering a restricted area or colliding with an obstacle. If not, the self-mobile device continues to move along the bow-shaped route. The work continues until the work in the area is completed, and then the work continues in the next area.

[0117] FIG2f is a flowchart of a dynamic control method for an extension route provided in an embodiment of the present specification. As shown in FIG2f , the self-mobile device can first load a work map, traverse the various work areas included in the work map, select an unused area as the current work area, and start to extend the route. The positioning sensor identifies that when it is determined that there is a boundary between areas around the self-mobile device, the image acquisition device determines the type of object at the boundary, and based on the object type, determines the location attribute of the boundary, and determines whether the location attribute is a workable attribute. If so, the extension route is expanded to a certain distance adjacent to the current work area. If not, it is determined whether the location attribute is an inaccessible and non-workable attribute. If so, the extension route is retracted to a certain distance from the current work area to prevent the self-mobile device from entering a restricted area or colliding with an obstacle. If not, it continues to move along the extension route. The work continues until the work in the area is completed, and then the work continues in the next area.

[0118] For example, FIG2g is a schematic diagram of a bow-shaped route provided in an embodiment of this specification. As shown in FIG2g, the entire work map includes two work areas, namely work area 1 and work area 2. There is an elliptical restricted access area / obstacle in the middle of the area intersection of work area 1 and work area 2. The bow-shaped route is the initial route of the mobile device, that is, the normal working trajectory. The mobile device starts from point A in work area 1 and moves along the bow-shaped route. When it reaches point B, it is detected that the mobile device is currently located near the area intersection of work area 1 and work area 2, that is, there is an area intersection around the mobile device. At this time, it is determined by identification that the object type at the area intersection is the working object of the mobile device, that is, the position attribute of the area intersection is a workable attribute. At this time, the bow-shaped route is expanded outward to work area 2 by a certain distance. The distance can be adaptively adjusted according to the distribution of the working objects of the mobile device. Assuming that it is expanded outward to point C, an outward-expanded working route is obtained. The self-mobile device continues to move along the outward-expanding work route. When it reaches point D, it still monitors the area near the intersection of work area 1 and work area 2. However, through identification, it is determined that the object type at the intersection of the areas is a restricted access restricted area / obstacle, that is, the position attribute of the intersection of the areas is a different access and non-workable attribute. At this time, the bow-shaped route is retracted a certain distance into work area 1. The distance can be adaptively adjusted according to the distribution of the restricted area / obstacle. It is assumed that it is retracted to point E, bypassing the obstacle, and obtaining the retracted work route. After that, monitoring is continued. When the self-mobile device moves to point F, it can be detected that the position attribute of the area intersection is restored to the workable attribute. The bow-shaped route continues to be expanded a certain distance outward to work area 2. It is assumed that it is expanded to point G, and an outward-expanding work route is obtained. The self-mobile device continues to move along the outward-expanding work route to perform work tasks until the work in area 1 is completed.

[0119] For example, Figure 2h is a schematic diagram of the movement of a Yanbian route provided in an embodiment of this specification. As shown in Figure 2h, the entire work map includes two work areas, namely work area 1 and work area 2. There is an elliptical restricted access area / obstacle in the middle of the area intersection of work area 1 and work area 2. The Yanbian route is the initial movement route of the self-mobile device, that is, the normal working trajectory. The self-mobile device starts from point A in work area 1 and moves along the Yanbian route. When it moves to point B, it is detected that the self-mobile device is currently located near the area intersection of work area 1 and work area 2, that is, there is an area intersection around the self-mobile device. At this time, it is determined by identification that the object type at the area intersection is the working object of the self-mobile device, that is, the position attribute of the area intersection is a workable attribute. At this time, the Yanbian route is expanded to a certain distance to work area 2. The distance can be adaptively adjusted according to the distribution of the working objects of the self-mobile device. Assuming that it is expanded to point C, an expanded working route is obtained. The self-mobile device continues to move along the outward-expanding work route. When it reaches point D, it is still near the boundary between work area 1 and work area 2. However, through identification, it is determined that the object type at the boundary of the areas is a restricted access restricted area / obstacle, that is, the position attribute of the boundary of the areas is a different access and non-workable attribute. At this time, the extended route is retracted to work area 1 by a certain distance. The distance can be adaptively adjusted according to the distribution of the restricted area / obstacle. It is assumed that it is retracted to point E, bypassing the obstacle, and obtaining the retracted work route. After that, monitoring is continued. When the self-mobile device moves to point F, it can be detected that the position attribute of the boundary of the areas is restored to the workable attribute. The extended route continues to be expanded to work area 2 by a certain distance. It is assumed that it is expanded to point G, and an outward-expanding work route is obtained. The self-mobile device continues to move along the outward-expanding work route to perform work tasks until it returns to point A, and the work in area 1 is completed.

[0120] One embodiment of this specification provides a method for controlling a self-moving device, which can determine the location attributes of a zone boundary. This location attribute can indicate the restrictions on access and operation at the zone boundary. Based on this location attribute, the self-moving device's operating route at the zone boundary can be determined, and the self-moving device can be controlled to operate along the determined operating route, with the operating route adapted to the restrictions. In this way, based on the restrictions on access and operation at the zone boundary of adjacent zones, the corresponding operating route can be dynamically adjusted to adapt to the restrictions, avoiding missed areas at the zone boundary of adjacent zones, improving the coverage of the self-moving device's operating area, and ensuring the safety of the self-moving device during travel. In addition, dynamically adjusting the corresponding operating route at the zone boundary of adjacent zones can make the self-moving device more intelligent and interactive.

[0121] The following further describes the control method for a self-propelled device provided in this specification, using the application of the control method for a lawn mower robot as an example, in conjunction with Figure 3. Figure 3 shows a flowchart of the process of controlling a self-propelled device provided in one embodiment of this specification, specifically including the following steps.

[0122] Step 302: Manually or automatically control the mowing robot to traverse various locations to be mowed, build a mowing map, and manually or automatically divide the working map into at least two working areas to obtain a partition map; download the partition map, control the mowing robot to select an unworked area as the current working area, move along an initial travel route, and perform the work task, where the initial travel route is a bow-shaped route or a side route.

[0123] Step 304: Obtain robot position information collected by the robot's positioning sensor, as well as the boundary of at least two working areas. If the robot position information and the boundary of at least two working areas indicate the presence of a boundary around the robot, obtain image information of the boundary collected by the robot's camera or time-of-flight (TOF) sensor, identify the target object included in the image information through deep learning, and determine the object type at the boundary. Step 306: If the object type is restricted access, determine that the location attribute of the boundary is inaccessible and non-operational, retract the initial route of the boundary based on a pre-configured retraction distance, and determine the working route of the robot at the boundary.

[0124] Step 308: When the object type is a non-restricted pass type, the location attribute of the area boundary is determined to be passable and non-workable, and the initial travel route of the area boundary is used as the work route at the area boundary.

[0125] Step 310: When the object type is grass, determine that the location attribute of the area intersection is a workable attribute, expand the initial travel route of the area intersection based on the pre-configured expansion distance, and determine the working route of the lawn mowing robot at the area intersection.

[0126] Step 312: Control the lawn mowing robot to work along the working route.

[0127] The process returns to step 304 until mowing the current working area is completed.

[0128] One embodiment of this specification provides a control method for a self-propelled device. When a boundary exists around a robotic lawn mower, that is, when the robotic lawn mower approaches the boundary, the method determines the location attributes of the boundary. The location attributes can indicate the restrictions on access and operation at the boundary. Based on the location attributes, the robotic lawn mower can determine a working route at the boundary, and the robotic lawn mower can be controlled to operate along the determined working route, with the working route adapted to the restrictions. In this manner, the working route can be dynamically adjusted to adapt to the restrictions on access and operation at the boundary of adjacent areas, thereby avoiding missed areas at the boundary of adjacent areas, improving the coverage of the robotic lawn mower's working area, and ensuring the safety of the robotic lawn mower during movement. Furthermore, dynamically adjusting the working route at the boundary of adjacent areas can make the robotic lawn mower more intelligent and interactive.

[0129] Corresponding to the above method embodiments, this specification also provides an embodiment of a control unit for a self-moving device. FIG4 shows a schematic diagram of the structure of a control unit for a self-moving device provided in one embodiment of this specification. As shown in FIG4 , a positioning device is provided on the self-moving device, and the control unit includes:

[0130] An acquisition module 402 is configured to acquire device location information collected by a positioning device and a boundary between at least two working areas;

[0131] A first determining module 404 is configured to determine a location attribute of a region boundary, wherein the location attribute is used to indicate a restriction on passage and work at the region boundary;

[0132] The second determining module 406 is configured to determine a working route of the mobile device at the boundary of the area according to the location attribute, and control the mobile device to work along the working route, wherein the working route is adapted to the restriction condition.

[0133] In an optional implementation of this embodiment, the first determining module 404 is further configured to:

[0134] According to the device location information and the area boundaries of at least two working areas, it is determined whether there is an area boundary around the self-moving device; if so, a location attribute of the area boundary around the self-moving device is determined.

[0135] In an optional implementation of this embodiment, the first determining module 404 is further configured to:

[0136] Determine the object type at the region boundary, and determine the location attribute of the region boundary based on the object type;

[0137] Among them, the object type includes restricted access type, unrestricted access type and work object type; the location attribute includes inaccessible and non-workable attribute, accessible and non-workable attribute and workable attribute.

[0138] In an optional implementation of this embodiment, the mobile device is further provided with an image acquisition device; the first determination module 404 is further configured to:

[0139] Acquiring image information of the region boundary captured by the image acquisition device;

[0140] Identify image information at the region junction and determine the object type at the region junction.

[0141] In an optional implementation of this embodiment, the image acquisition device includes a camera and / or a 3D sensor; the first determination module 404 is further configured to:

[0142] Based on the image information collected by the camera and / or 3D sensor, the deep learning model is used to determine the type of object at the intersection of the area.

[0143] In an optional implementation of this embodiment, the first determining module 404 is further configured to:

[0144] When the object type is restricted access type, the location attribute of the area boundary is determined to be impassable and non-operational;

[0145] When the object type is a non-restricted access type, the location attribute of the area boundary is determined to be passable and non-operational;

[0146] In the case where the object type is a work object type, the position attribute of the region boundary is determined to be a workable attribute.

[0147] In an optional implementation of this embodiment, the second determining module 406 is further configured to:

[0148] When the location attribute is passable and non-workable, the initial travel route at the regional boundary is used as the work route at the regional boundary;

[0149] When the location attribute is other working attributes, the initial travel route of the area boundary is shrunk or expanded to determine the working route of the mobile device at the area boundary.

[0150] In an optional implementation of this embodiment, the second determining module 406 is further configured to:

[0151] When the location attribute is inaccessible and non-operational, the initial route of the area boundary is retracted to determine the working route of the mobile device at the area boundary;

[0152] When the location attribute is a workable attribute, the initial travel route at the area boundary is expanded to determine the working route of the mobile device at the area boundary.

[0153] In an optional implementation of this embodiment, the second determining module 406 is further configured to:

[0154] Obtaining a pre-configured adaptation parameter, wherein the adaptation parameter is a shrinking distance or an expanding distance;

[0155] An updated travel route having an adaptation parameter distance from the initial travel route in the direction of the first area is determined, and the updated travel route is used as a working route of the self-moving device at the intersection of the areas. In the case of inward contraction, the first area is the current working area of ​​the self-moving device; in the case of outward expansion, the first area is an adjacent area to the current working area of ​​the self-moving device.

[0156] In an optional implementation of this embodiment, the first determining module 404 is further configured to:

[0157] If the image acquisition device is a camera, the two-dimensional position image acquired by the camera is input into the image recognition model to obtain the target object at the junction of the regions;

[0158] If the image acquisition device is a 3D sensor, the three-dimensional point cloud information collected by the 3D sensor is input into the point cloud learning model to obtain the target object at the intersection of the area;

[0159] If the image acquisition device is a camera and a 3D sensor, the three-dimensional point cloud information acquired by the 3D sensor is mapped to the two-dimensional position image acquired by the camera to obtain combined point cloud information; the combined point cloud information is input into the point cloud learning model to obtain the target object at the junction of the regions;

[0160] Query the target type of the target object and use the target type as the object type at the region boundary.

[0161] In an optional implementation of this embodiment, the control unit further includes a marking module configured to:

[0162] Build a work map;

[0163] Divide the work map into at least two work areas and mark the boundaries between adjacent areas.

[0164] In an optional implementation of this embodiment, the marking module is further configured to:

[0165] Mark location attributes at the intersection of regions between adjacent regions.

[0166] One embodiment of the present specification provides a control unit for a self-moving device that can determine location attributes at a zone boundary. These location attributes can indicate restrictions on access and operation at the zone boundary. Based on these location attributes, a working route for the self-moving device at the zone boundary can be determined, and the self-moving device can be controlled to operate along the determined working route, with the working route adapted to the restrictions. In this way, based on the restrictions on access and operation at the zone boundary of adjacent zones, the corresponding working route can be dynamically adjusted to adapt to the restrictions, avoiding missed areas at the zone boundary of adjacent zones, improving the coverage of the self-moving device's working area, and ensuring the safety of the self-moving device during travel. Furthermore, dynamically adjusting the corresponding working route at the zone boundary of adjacent zones can make the self-moving device more intelligent and interactive.

[0167] The above is a schematic diagram of a control unit for a self-moving device according to this embodiment. It should be noted that the technical solution of the control unit for the self-moving device and the technical solution of the control method for the self-moving device described above are based on the same concept. For details not described in detail in the technical solution of the control unit for the self-moving device, please refer to the description of the technical solution of the control method for the self-moving device described above.

[0168] Figure 5 shows a block diagram of a self-propelled device according to an embodiment of the present application. The components of the self-propelled device include, but are not limited to, a body 502; a drive module 504, disposed on the body 502 and configured to drive the body 502; an execution module 506, disposed on the body 502 and configured to execute a task; a positioning device 508, disposed on the body 502; a memory 510 for storing a computer program; and a processor 512, coupled to the memory 510. The program includes instructions that, when executed by the processor 512, cause the processor 512 to perform operations, including the operations described in the control method for the self-propelled device.

[0169] It should be noted that, when the self-moving device is a lawn mower, the execution module can be a cutting module in the lawn mower, which is arranged in the lawn mower body and is used to perform the cutting task; when the self-moving device is a sweeping robot, the execution module can be a cleaning module in the sweeping robot, which is arranged in the sweeping robot body and is used to perform the cleaning task; when the self-moving device is a food delivery machine, the execution module can be a mobile module in the food delivery machine, which is arranged in the food delivery machine body and is used to perform the food delivery task.

[0170] The self-moving device provided in the embodiments of the present application can determine the location attributes of the regional boundary, which can indicate the restrictions on access and operation at the regional boundary. Based on the location attributes, the working route of the self-moving device at the regional boundary can be determined, and the self-moving device can be controlled to operate along the determined working route, with the working route adapted to the restrictions. In this way, the corresponding working route can be dynamically adjusted to adapt to the restrictions on access and operation at the regional boundary of adjacent areas, avoiding missed areas at the regional boundary of adjacent areas, improving the coverage of the working area of ​​the self-moving device, and ensuring the safety of the self-moving device during travel. In addition, dynamically adjusting the corresponding working route at the regional boundary of adjacent areas can make the self-moving device more intelligent and more interactive.

[0171] The above is a schematic diagram of a self-moving device according to this embodiment. It should be noted that the technical solution of this self-moving device and the technical solution of the control method of the self-moving device described above are based on the same concept. For details not described in detail in the technical solution of the self-moving device, please refer to the description of the technical solution of the control method of the self-moving device described above.

[0172] An embodiment of the present specification further provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the above-mentioned method for controlling a mobile device.

[0173] The above is a schematic diagram of a computer-readable storage medium according to this embodiment. It should be noted that the technical solution of this storage medium and the technical solution of the aforementioned method for controlling a self-moving device are based on the same concept. For details not described in detail in the technical solution of the storage medium, please refer to the description of the technical solution of the aforementioned method for controlling a self-moving device.

[0174] An embodiment of the present specification further provides a computer program, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned method for controlling a mobile device.

[0175] The above is an illustrative embodiment of a computer program. It should be noted that the technical solution of this computer program and the technical solution of the aforementioned method for controlling a self-moving device are based on the same concept. For details not described in detail in the technical solution of the computer program, please refer to the description of the technical solution of the aforementioned method for controlling a self-moving device.

[0176] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0177] Computer-executable instructions include computer program code, which may be in source code form, object code form, executable files, or some intermediate form. Computer-readable media may include any entity or device capable of carrying computer program code, recording media, USB flash drives, mobile hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signals, telecommunications signals, and software distribution media. It should be noted that the content of computer-readable media may be appropriately increased or decreased based on the requirements of patent practice. For example, in some regions, according to patent practice, computer-readable media does not include electric carrier signals and telecommunications signals.

[0178] It should be noted that for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0179] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0180] The preferred embodiments disclosed above are intended only to help illustrate this specification. The optional embodiments do not exhaustively describe all details, nor do they limit the invention to specific embodiments. Obviously, many modifications and variations are possible based on the content of the embodiments described herein. These embodiments are selected and specifically described in this specification to better explain the principles and practical applications of the embodiments, thereby enabling those skilled in the art to better understand and utilize this specification. This specification is limited only by the claims and their full scope and equivalents.

Claims

1. A control method for a self-moving device, characterized in that: The self-mobile device is provided with a positioning device, and the method comprises: Acquire the device location information collected by the positioning device and the regional boundary of at least two working areas; Determining a location attribute of the area boundary, wherein the location attribute is used to indicate a restriction on passage and work at the area boundary; The working route of the self-moving device at the boundary of the area is determined according to the location attribute, and the self-moving device is controlled to work along the working route, wherein the working route is adapted to the restriction situation.

2. The control method of the self-moving device according to claim 1, characterized in that: The determining of the location attributes of the region boundaries includes: According to the device location information and the area boundaries of at least two working areas, it is determined whether there is an area boundary around the self-moving device, and if so, a location attribute of the area boundary around the self-moving device is determined.

3. The control method of the self-moving device according to claim 1, characterized in that: The determining of the location attributes of the region boundaries includes: Determining the type of object at the junction of the regions, and determining the position attribute of the junction of the regions according to the type of object; Among them, the object types include restricted access types, unrestricted access types and working object types; the location attributes include inaccessible and non-workable attributes, accessible and non-workable attributes and workable attributes.

4. The control method of the self-moving device according to claim 3, characterized in that: The self-mobile device is also provided with an image acquisition device; the determining of the type of object at the boundary of the area includes: Acquire image information of the region boundary collected by the image collection device; The image information at the junction of the regions is identified, and the type of the object at the junction of the regions is determined.

5. The control method of the self-moving device according to claim 4, characterized in that: The image acquisition device includes a camera and / or a 3D sensor; the identifying the image information at the junction of the regions and determining the type of the object at the junction of the regions includes: According to the image information collected by the camera and / or the 3D sensor, the type of object at the junction of the areas is determined using a deep learning model.

6. The control method of a self-moving device according to any one of claims 3 to 5, characterized in that: The determining the position attribute of the region boundary according to the object type includes: In the case where the object type is a restricted access type, determining the location attribute of the area boundary as an inaccessible and inoperable attribute; In the case where the object type is a non-restricted pass type, determining the location attribute of the area boundary as a passable and non-operational attribute; In the case where the object type is a work object type, the position attribute of the region boundary is determined as a workable attribute.

7. The control method of a self-moving device according to any one of claims 1 to 5, characterized in that: The step of determining the working route of the mobile device at the boundary of the area according to the location attribute includes: In the case where the location attribute is a passable and non-workable attribute, the initial travel route at the intersection of the areas is used as the work route at the intersection of the areas; When the location attribute is other working attributes, the initial travel route of the area boundary is shrunk or expanded to determine the working route of the self-moving device at the area boundary.

8. The control method of the self-moving device according to claim 7, characterized in that: When the location attribute is other working attributes, the initial route of the area boundary is contracted or expanded to determine the working route of the mobile device at the area boundary, including: When the location attribute is inaccessible and inoperable, the initial route of the area boundary is The line is retracted to determine the working route of the self-mobile device at the intersection of the area; When the location attribute is a workable attribute, the initial route of the area boundary is expanded to determine the working route of the self-moving device at the area boundary.

9. The control method of the self-moving device according to claim 7, characterized in that: The step of shrinking or expanding the initial route of the area boundary to determine the working route of the self-moving device at the area boundary includes: Acquire a pre-configured adaptation parameter, wherein the adaptation parameter is a shrinking distance or an expanding distance; Determine an updated travel route that is at a distance of the adaptation parameter from the initial travel route in the direction of the first area, and use the updated travel route as a working route of the self-moving device at the boundary of the area; Wherein, in the case of contraction, the first area is the current working area of ​​the self-moving device, and in the case of expansion, the first area is the adjacent area of ​​the current working area of ​​the self-moving device.

10. The control method of the self-moving device according to claim 5, characterized in that: Determining the type of object at the junction of the regions using a deep learning model based on the image information collected by the camera and / or the 3D sensor includes: If the image acquisition device is a camera, the two-dimensional position image acquired by the camera is input into the image recognition model to obtain the target object at the junction of the regions; If the image acquisition device is a 3D sensor, the three-dimensional point cloud information acquired by the 3D sensor is input into the point cloud learning model to obtain the target object at the junction of the regions; If the image acquisition device is a camera and a 3D sensor, the three-dimensional point cloud information acquired by the 3D sensor is mapped to the two-dimensional position image acquired by the camera to obtain combined point cloud information; the combined point cloud information is input into the point cloud learning model to obtain the target object at the junction of the regions; The target type of the target object is queried, and the target type is used as the object type at the boundary of the area.

11. The control method of a self-moving device according to any one of claims 1 to 5, characterized in that: Before acquiring the device location information collected by the positioning device, the method further includes: Build a work map; The working map is divided into at least two working areas, and the boundaries between adjacent areas are marked.

12. The control method of the self-moving device according to claim 11, characterized in that: After marking the boundary of adjacent areas, the method further includes: The location attributes of the area boundaries marked at the adjacent areas.

13. A control unit for a self-moving device, characterized in that: The self-mobile device is provided with a positioning device, and the control unit comprises: An acquisition module is configured to acquire the device location information collected by the positioning device and the regional boundary of at least two working areas; A first determination module is configured to determine a location attribute of the area boundary, wherein the location attribute is used to indicate a restriction on passage and work at the area boundary; The second determination module is configured to determine a working route of the self-moving device at the boundary of the area according to the location attribute, and control the self-moving device to work along the working route, wherein the working route is adapted to the restriction situation.

14. A method for controlling a self-moving device, characterized in that: The self-mobile device is provided with a positioning device, and the method comprises: During the movement of the self-moving device, obtaining device location information collected by the positioning device and the regional boundaries of at least two working areas; When the area boundary is impassable and inoperable, the initial travel route of the area boundary is retracted, the working route of the self-moving device at the area boundary is obtained, and the self-moving device is controlled to work along the working route.

15. The control method of the self-moving device according to claim 14, characterized in that: The step of retracting the initial route of the area boundary to obtain the working route of the mobile device at the area boundary includes: According to the device location information, the initial travel route at the boundary of the area is retracted to obtain the working route of the self-equipped device at the boundary of the area.

16. The control method of the self-moving device according to claim 14, characterized in that: The self-mobile device is also provided with an image acquisition device; after acquiring the device location information acquired by the positioning device and the boundary of at least two working areas, the method further includes: Acquire image information of the region boundary collected by the image collection device; Identify image information at the junction of the regions, and determine the type of object at the junction of the regions; In the case where the object type is a restricted access type, the area boundary is determined to be impassable and non-operable.

17. The control method of the self-moving device according to claim 16, characterized in that: The image acquisition device includes a camera and / or a 3D sensor; the identifying the image information at the junction of the regions and determining the type of the object at the junction of the regions includes: According to the image information collected by the camera and / or the 3D sensor, the type of object at the junction of the areas is determined using a deep learning model.

18. The control method of the self-moving device according to claim 14, characterized in that: The step of retracting the initial route of the area boundary to obtain the working route of the mobile device at the area boundary includes: Acquire a pre-configured adaptation parameter, wherein the adaptation parameter is a retraction distance; Determine an updated travel route that is at a distance of the adaptation parameter from the initial travel route in the direction of the first area, and use the updated travel route as a working route of the self-moving device at the boundary of the area; The first area is the current working area of ​​the mobile device.

19. The control method of a self-moving device according to any one of claims 14 to 18, characterized in that: Before acquiring the device location information collected by the positioning device, the method further includes: Build a work map; Dividing the working map into at least two working areas, and marking the boundaries between adjacent areas; Marking position attributes at the area boundary of the adjacent areas, wherein the position attributes are used to indicate restrictions on passage and work at the area boundary.

20. A method for controlling a self-moving device, characterized in that: The self-mobile device is provided with a positioning device, and the method comprises: During the movement of the self-moving device, obtaining device location information collected by the positioning device and the regional boundaries of at least two working areas; When the area boundary is operable, the initial travel route of the area boundary is expanded outward to obtain the working route of the self-moving device at the area boundary, and the self-moving device is controlled to work along the working route.

21. The control method of the self-moving device according to claim 20, characterized in that: The step of expanding the initial route of the area boundary to obtain the working route of the mobile device at the area boundary includes: According to the device location information, the initial travel route at the boundary of the area is expanded to obtain the working route of the self-equipped device at the boundary of the area.

22. The control method of the self-moving device according to claim 20, characterized in that: The self-mobile device is also provided with an image acquisition device; after acquiring the device location information acquired by the positioning device and the boundary of at least two working areas, the method further includes: Acquire image information of the region boundary collected by the image collection device; Identify image information at the junction of the regions, and determine the type of object at the junction of the regions; In the case where the object type is a work object type, the region boundary is determined to be a workable attribute.

23. The control method of the self-moving device according to claim 20, characterized in that: The step of expanding the initial route of the area boundary to obtain the working route of the mobile device at the area boundary includes: Acquire a pre-configured adaptation parameter, wherein the adaptation parameter is an outward expansion distance; Determine an updated travel route that is at a distance of the adaptation parameter from the initial travel route in the direction of the first area, and use the updated travel route as a working route of the self-moving device at the boundary of the area; The first area is an adjacent area of ​​the current working area of ​​the mobile device.

24. The control method of a self-moving device according to any one of claims 20 to 23, characterized in that: Before acquiring the device location information collected by the positioning device, the method further includes: Build a work map; Dividing the working map into at least two working areas, and marking the boundaries between adjacent areas; Marking position attributes at the area boundary of the adjacent areas, wherein the position attributes are used to indicate restrictions on passage and work at the area boundary.

25. A method for controlling a self-moving device, characterized in that: The self-mobile device is provided with a positioning device, and the method comprises: During the movement of the self-moving device, obtaining device location information collected by the positioning device and the regional boundaries of at least two working areas; In the case where the area boundary is passable but not workable, the initial travel route of the area boundary is used as the work route at the area boundary, and the self-moving device is controlled to work along the work route.

26. A self-propelled device, characterized in that: It includes: ontology, A driving module, disposed on the body, and used to drive the body to move forward; An execution module, disposed in the main body, for executing work tasks; A positioning device, arranged on the body; Memory for storing computer programs; A processor is coupled to the memory, the program includes instructions, and the instructions, when executed by the processor, cause the processor to perform operations, and the operations include the steps of the control method of the self-moving device described in any one of claims 1-12 or any one of claims 14-19 or any one of claims 20-24 or claim 25.

27. A computer-readable storage medium, characterized in that: It stores computer executable instructions, which, when executed by a processor, can implement the steps of the method for controlling a self-moving device as described in any one of claims 1 to 12, any one of claims 14 to 19, any one of claims 20 to 24, or claim 25.

Images