Map construction method, self-moving device, and storage medium

Abstract

The application provides a map construction method, a self-moving device and a storage medium. The method comprises: acquiring an image obtained by photographing a user; determining a foot position of the user according to the image; controlling the self-moving device to move from a current position following the foot position and recording a device position of the self-moving device; and constructing a boundary map based on the recorded multiple device positions, wherein the boundary map comprises a boundary of a working area or a boundary of an obstacle. By using the above method, the risk of losing a tracking target or positional deviation can be reduced, the complexity of visual recognition can be reduced, and the movement safety of the self-moving device can be ensured.

Description

Technical Field

[0001] This application relates to the field of self-moving device technology, and in particular to a map building method, a self-moving device, and a storage medium. Background Technology

[0002] In the field of self-moving equipment technology, boundary planning of the work area, as a crucial step in mapping, is a necessary prerequisite for achieving efficient equipment operation. Related technologies employ a method where the self-moving equipment follows a feature object and records its coordinate information during the movement to complete the boundary planning of the work area. However, this method of boundary planning by following the movement of the feature object has certain limitations.

[0003] Taking the human body as a feature as an example, the self-moving device completes the human body tracking action based on sensors. As the user walks along the boundary, the self-moving device follows the user's movement and records the boundary coordinate information to complete boundary planning. However, in practical applications, this method of boundary planning by following human body movement has several problems: due to the low height of the device's camera, it is difficult to capture the entire human body, which may lead to the loss of the tracking target or positioning deviation; human body shape (such as height, weight), clothing (such as long skirts / loose clothing) or posture changes (such as turning around, waving) may affect the stability of visual recognition; when tracking the upper body, the user may deviate from the actual walking path due to line of sight observation or habitual side turning, thus guiding the self-moving device into dangerous areas such as ditches and walls. Summary of the Invention

[0004] In view of the above, it is necessary to provide a map building method, a self-moving device, and a storage medium that can solve the technical problem of poor boundary planning effect of the work area.

[0005] On one hand, this application provides a map construction method, the method comprising: acquiring an image of a user taken by a photograph, determining the user's foot position based on the image, controlling a self-moving device to move from its current position to follow the foot position, recording the device position of the self-moving device, and constructing a boundary map based on the recorded multiple device positions, the boundary map including the boundary of a work area or the boundary of an obstacle.

[0006] On the other hand, this application provides a self-moving device, which includes: a moving component for driving the self-moving device to move; an image acquisition module for capturing images; and a storage module for storing a tracking program. The tracking program includes the following steps: acquiring an image captured of a user; determining the user's foot position based on the image; controlling the self-moving device to move from its current position following the foot position; and recording the device position of the self-moving device. A control module is used to control the image acquisition module to capture images in real time, execute the tracking program after each image capture, and construct a boundary map based on multiple recorded device positions. The boundary map includes the boundary of the work area or the boundary of obstacles.

[0007] On the other hand, this application provides a self-moving device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the self-moving device implements the map building method described above. On the other hand, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor in a self-moving device, implements the map building method described above.

[0008] In the map construction scheme provided in this application embodiment, the boundary planning of the work area is completed by using a self-moving device to follow the user's foot position. Since the feet are always near the ground, they are highly compatible with the observation range of the low-angle image acquisition module (such as a camera) installed on the self-moving device. This avoids missing key information due to limited viewing angle, thereby reducing the risk of target loss or positioning deviation. Compared to the complex body shape differences and clothing variations of the upper body, the shape and movement patterns of the feet are relatively fixed, especially when wearing shoes, where color and outline are more obvious. This reduces the complexity of visual recognition and improves its stability. Since the position of the feet directly reflects the safe path actually traversed by the user, it effectively avoids the risk of being misled by upper body posture deviations, thereby avoiding obstacles and dangerous areas and ensuring the movement safety of the self-moving device. Attached Figure Description

[0009] Figure 1 This is a flowchart of a map construction method provided in an embodiment of this application.

[0010] Figure 2 This is a schematic diagram of a local cost map provided in an embodiment of this application.

[0011] Figure 3 This is a schematic diagram of a local cost map provided in another embodiment of this application.

[0012] Figure 4 This is a schematic diagram of the structure of a self-moving device provided in an embodiment of this application.

[0013] Figure 5 This is a schematic diagram of the structure of a self-moving device provided in another embodiment of this application. Detailed Implementation

[0014] To make the objectives, technical solutions, and advantages of this application clearer, the application will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0015] It should be noted that in this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and drawings of this application are used to distinguish similar objects, not to describe a specific order or sequence.

[0016] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0017] In the field of self-moving equipment technology, boundary planning of the work area, as a crucial step in mapping, is a necessary prerequisite for achieving efficient equipment operation. Related technologies employ a method where the self-moving equipment follows a feature object and records its coordinate information during the movement to complete the boundary planning of the work area. However, this method of boundary planning by following the movement of the feature object has certain limitations.

[0018] Taking the human body as a feature as an example, the self-moving device completes the human body tracking action based on sensors. As the user walks along the boundary, the self-moving device follows the user's movement and records the boundary coordinate information to complete boundary planning. However, in practical applications, this method of boundary planning by following human body movement has several problems: due to the low height of the device's camera, it is difficult to capture the entire human body, which may lead to the loss of the tracking target or positioning deviation; human body shape (such as height, weight), clothing (such as long skirts / loose clothing) or posture changes (such as turning around, waving) may affect the stability of visual recognition; when tracking the upper body, the user may deviate from the actual walking path due to line of sight observation or habitual side turning, thus guiding the self-moving device into dangerous areas such as ditches and walls.

[0019] To address the aforementioned technical problems, this application provides a map construction method that can reduce the risk of target loss or positioning deviation, reduce the complexity of visual recognition, and ensure the mobile safety of self-moving devices.

[0020] The map construction method provided in this application can be applied to one or more self-moving devices, which can be lawn mowing robots, cleaning robots, de-icing robots, and cruise robots, etc. This application does not limit the specific type of self-moving device.

[0021] To more clearly illustrate the map construction method provided in the embodiments of this application, the following will provide examples in conjunction with the accompanying drawings.

[0022] like Figure 1 The diagram shown is a flowchart of a map construction method provided in one embodiment of this application. Depending on different needs, the order of the steps in this flowchart can be adjusted according to actual requirements, and some steps can be omitted. The method is applied to self-moving devices.

[0023] S11, acquire the image taken of the user.

[0024] In some embodiments, the self-moving device may include an image acquisition module, which can capture images at preset intervals.

[0025] The captured images may include the user's entire body or only the user's lower body. This application does not limit the type of image acquisition module. For example, the image acquisition module can be a sensor such as a camera or a webcam; the camera can be a monocular camera, a multi-view camera, or a color-depth (RGB-D, RGB-D) camera. The preset time can be customized, and this application does not limit this. For example, the preset time could be 0.2 seconds.

[0026] S12, determine the user's foot position based on the image.

[0027] In some embodiments, the foot position can be the three-dimensional coordinates of the user's foot in a world coordinate system, rather than the user's footprint. The self-moving device can determine a foot position based on each image captured.

[0028] For example, a self-moving device can use a segmentation algorithm to perform semantic segmentation on an image, obtain a semantic segmentation result, and determine the foot position based on the semantic segmentation result.

[0029] This application does not limit the type of segmentation algorithm. For example, semantic segmentation algorithms can be Fully Convolutional Networks (FCNs), SegNet, U-Net, etc. The semantic segmentation result can include the category of each pixel in the image. Based on the category of each pixel, the mobile device can determine the set of pixels belonging to the same object.

[0030] The self-moving device can determine the pixel corresponding to the user's foot in the image based on the category of each pixel. Based on the position of the pixel corresponding to the user's foot, it can determine the pixel position of the user's foot in the image. The pixel position can be the two-dimensional coordinates of the user's foot in the pixel coordinate system of the image. The pixel position is transformed according to the parameters of the image acquisition module to obtain the three-dimensional coordinates of the user's foot in the world coordinate system as the foot position.

[0031] The parameters of the image acquisition module can include intrinsic and extrinsic parameters. Intrinsic parameters represent the transformation between the pixel coordinate system of the image and the camera coordinate system of the image acquisition module, while extrinsic parameters represent the transformation between the camera coordinate system of the image acquisition module and the world coordinate system. By using the intrinsic and extrinsic parameters of the image acquisition module, the self-moving device can transform the pixel position corresponding to the user's foot from the pixel coordinate system to the world coordinate system, thereby obtaining the three-dimensional coordinates of the user's foot as its location.

[0032] In this embodiment, since the semantic segmentation result of the image includes the category of each pixel in the image, the pixel position of the user's foot in the image can be quickly determined through the semantic segmentation result. Thus, the pixel position can be quickly converted according to the intrinsic and extrinsic parameters of the image acquisition module to obtain the three-dimensional coordinates of the user's foot as the user's foot position.

[0033] In some embodiments, for the Nth image acquired by the camera, if N equals 1, the mobile device can generate an initial local cost map based on the semantic segmentation result corresponding to the first image. If N is an integer greater than 1, the mobile device can update the local cost map generated or updated based on the semantic segmentation result of the (N-1)th image based on the semantic segmentation result of the Nth image. For example, the mobile device can update the initial local cost map using the semantic segmentation result of the second image, and update the local cost map updated from the semantic segmentation result of the second image using the semantic segmentation result of the third image, and so on, thus enabling continuous updating of the local cost map.

[0034] The local cost map can be a 3D map centered on the mobile device. Methods for generating the local cost map based on semantic segmentation results can refer to relevant technologies. The mobile device can mark the user's foot position, as well as the positions of grassy and non-grassy areas, on the local cost map. For example, non-grassy areas can include obstacle areas and road areas.

[0035] The self-moving device can identify passable areas (e.g., grass areas) and impassable areas (e.g., obstacle areas) based on the cost value of each area in the local cost map. The cost value of each area represents the difficulty or risk of passage. For example, areas with higher cost values ​​may have higher passage difficulties than areas with lower cost values. For instance, in the local cost map of this application embodiment, the cost value of a grass area may be lower than that of non-grass areas such as obstacle areas. This differentiated cost value setting can guide the self-moving device to prioritize passage through grass areas and reduce or avoid entering impassable areas such as obstacle areas.

[0036] For example, such as Figure 2 The image shown is a schematic diagram of a local cost map provided in an embodiment of this application. Figure 2 In the image, the mobile device is located at the center of the local cost map, and the grass area, non-grass area, and the user's foot position are marked.

[0037] In this embodiment, a local cost map is generated based on the semantic segmentation results, enabling the self-moving device to accurately understand the surrounding environment, thereby accurately following the user's foot position, reducing movement risks, and improving movement efficiency.

[0038] S13, control the self-moving device to move from the current position to follow the foot position, and record the device position of the self-moving device.

[0039] In some embodiments, the current location includes the starting position of the self-moving device, which is the starting position when the self-moving device first begins to follow the user's foot position. During the movement following the user's foot position, the self-moving device can use a real-time kinematic positioning (RTK) algorithm to locate itself and record its own device position.

[0040] In some embodiments, the self-moving device moves in real time following the user's foot position.

[0041] For example, after obtaining each foot position of the user, the self-moving device can move from the current position to that foot position.

[0042] During the movement from the current position to the foot position, the self-moving device can perform collision detection to avoid colliding with the user.

[0043] In this embodiment, by following the user's foot position in real time, the tracking efficiency of the user's foot position can be improved.

[0044] For example, the self-moving device can determine the distance between itself and the user based on its current location and the latest foot location. If the distance between the self-moving device and the user is greater than a preset threshold, the self-moving device is controlled to move from its current location to follow the foot location. If the distance between the self-moving device and the user is less than or equal to the preset threshold, the self-moving device is controlled to maintain its current location.

[0045] The preset threshold can be customized, and this application does not impose any restrictions on it. For example, the preset threshold could be 1 meter.

[0046] If the distance between the self-moving device and the user is greater than a preset threshold, and the self-moving device obtains multiple foot positions at the current location, the self-moving device can determine the target location from the multiple foot positions based on the time point corresponding to each foot position, and control the self-moving device to move from the current location to the target location.

[0047] For example, a self-moving device can select the earliest foot position from multiple foot positions as the target position.

[0048] like Figure 3 The image shown is a schematic diagram of a local cost map provided in another embodiment of this application. Figure 3 Of the multiple foot positions shown, the latest foot position is furthest from the user, while the foot position corresponding to the earliest time point (referred to as the "earliest foot position") is closest to the user.

[0049] In this embodiment, if the distance between the self-moving device and the user is greater than a preset threshold, the self-moving device is controlled to move from its current position to follow the foot position. If the distance between the self-moving device and the user is less than or equal to the preset threshold, the self-moving device is controlled to maintain its current position. This allows the self-moving device to maintain a certain distance from the user, thereby reducing the risk of collision between the self-moving device and the user.

[0050] For example, if a preset number of foot positions are obtained at the current location, the self-moving device can select a target position from the preset number of foot positions and move from the current location to the target position.

[0051] The preset number can be customized, and this application does not impose any restrictions on it. For example, the preset number could be 5, 6, etc. The self-moving device can flexibly select the target location from the preset number of foot locations based on the time point corresponding to each foot location. The method for selecting the target location can be found in the description above.

[0052] In this embodiment, by obtaining a preset number of foot positions at the current location, selecting a target position from the preset number of foot positions, and moving from the current location to the target position, the distance between the self-moving device and the user can be controlled, thereby reducing the risk of collision between the self-moving device and the user.

[0053] In other embodiments, the self-moving device can plan a movement path based on a local cost map and a path planning algorithm, and move from its current position to the corresponding foot position or target position according to the movement path.

[0054] Among them, the path planning algorithm can be A Algorithms, Dijkstra's algorithm, etc.

[0055] For example, after determining the foot position based on the semantic segmentation result of the image, if the self-moving device obtains multiple foot positions at the current position, the self-moving device can determine the target position from the multiple foot positions. Based on the local cost map updated using the semantic segmentation result, a path planning algorithm is used to plan the movement path of the self-moving device from the current position to the target position, and the self-moving device moves from the current position to the target position according to the movement path.

[0056] In this embodiment, a path planning algorithm is used to plan a movement path based on a local cost map, and the movement is made from the current position to the corresponding foot position or target position according to the movement path, which can improve the movement efficiency of the self-moving device.

[0057] In other embodiments, the self-moving device determines a first moving speed of the user based on multiple foot positions and corresponding time points, determines a second moving speed of the self-moving device based on the first moving speed, and controls the self-moving device to move from the current position to follow the foot position based on the second moving speed.

[0058] Based on multiple foot positions and corresponding time points, the self-moving device can determine the user's movement distance and corresponding movement duration, and then determine a first movement speed based on the movement distance and movement duration. The second movement speed can be positively correlated with the first movement speed. For example, when the user walks at a lower first movement speed, the self-moving device can follow the user's foot positions at a lower second movement speed; conversely, when the user walks at a higher first movement speed, the self-moving device can follow the user's foot positions at a higher second movement speed.

[0059] In this embodiment, when the user walks at a lower first moving speed, the self-moving device can follow the user's foot position at a lower second moving speed. When the user walks at a higher first moving speed, the self-moving device can follow the user's foot position at a higher second moving speed. This allows the self-moving device to maintain a certain distance from the user, thereby reducing the risk of collision between the self-moving device and the user.

[0060] In other embodiments, the self-moving device can be communicatively connected to a control device, and the self-moving device can receive remote control commands sent from the control device and control the self-moving device to move according to the remote control commands. After detecting a trigger event, the self-moving device can be controlled to continue moving following the foot position.

[0061] The control devices include, but are not limited to, mobile phones and remote controls. Triggering events include, but are not limited to, the user being photographed again by the image acquisition module, and failure to receive remote control commands from the control devices.

[0062] For scenarios where users cannot pass through, such as under low trees or in doorways, it is difficult to move by tracking the user's foot position. Therefore, in this embodiment, by receiving remote control commands sent from the control device and moving according to the remote control commands, the flexibility and environmental adaptability of mapping can be improved, thereby improving mapping efficiency.

[0063] S14, Construct a boundary map based on the recorded locations of multiple devices. In some embodiments, the self-moving device can construct a boundary map based on multiple recorded device locations when it returns to its starting position.

[0064] For example, the self-moving device can compare the recorded device position with the starting position. If the recorded device position is the same as or differs from the starting position within a preset range, it can be determined that the self-moving device has returned to the starting position.

[0065] In some embodiments, the self-moving device can determine the boundary consisting of multiple recorded device locations in the finally updated local cost map, thereby obtaining a boundary map.

[0066] The boundaries formed by multiple device locations include, but are not limited to: work area boundaries and obstacle boundaries. Work area boundaries can be used to indicate that the area within the boundary is a work area, and obstacle boundaries can be used to indicate that the area within the boundary is an obstacle. Correspondingly, the boundary map can be the boundary of a work area or the boundary of obstacles.

[0067] In this embodiment, the boundary formed by the recorded locations of multiple devices is determined in the final updated local cost map, thereby obtaining a boundary map and improving the accuracy of the boundary map.

[0068] In other embodiments, before constructing a boundary map based on the recorded multiple device locations, the self-moving device may use a smoothing algorithm to smooth the recorded multiple device locations in order to filter out noisy and abnormal data in the multiple device locations.

[0069] This application does not limit the type of smoothing algorithm. For example, the smoothing algorithm can be a Bézier curve function or a B-spline curve function.

[0070] In this embodiment, a smoothing algorithm is used to smooth the recorded locations of multiple devices, which can improve the smoothness of the generated boundary and make the location of the work area and obstacles within the boundary map more accurate.

[0071] In the map construction scheme provided in this application embodiment, the boundary planning of the work area is completed by using a self-moving device to follow the user's foot position. Since the user's feet are always near the ground, they are highly compatible with the observation range of the low-angle image acquisition module (such as a camera) installed on the self-moving device. This avoids missing key information due to limited viewing angle, thereby reducing the risk of target loss or positioning deviation. Compared to the complex body shape differences and clothing variations of the upper body, the shape and movement patterns of the feet are relatively fixed, especially when wearing shoes, where color and outline are more obvious. This reduces the complexity of visual recognition and improves its stability. Since the position of the feet directly reflects the safe path actually traversed by the user, it effectively avoids the risk of being misled by upper body posture deviations, thereby avoiding obstacles and dangerous areas and ensuring the movement safety of the self-moving device.

[0072] like Figure 4 The diagram shown is a structural schematic of a self-moving device provided in an embodiment of this application. Figure 4 As shown, the self-moving device 40 includes a moving component 401, an image acquisition module 402, a storage module 403, and a control module 404. The self-moving device implements the above-described map construction method through the moving component 401, image acquisition module 402, storage module 403, and control module 404, for example: The moving component 401 can be used to drive the self-moving device. The moving component 401 can be a drive wheel or track wheels, etc.

[0073] The image acquisition module 402 can be used to capture images. The image acquisition module 402 can be a sensor such as a camera or a sensor camera.

[0074] Storage module 403 can be used to store a tracking program, which includes the following steps: acquiring an image of the user taken by camera, determining the user's foot position based on the image, controlling the self-moving device to move from the current position to follow the foot position, and recording the device position of the self-moving device. Storage module 403 can be a memory; for a description of storage module 403, please refer to the description of memory 501 below.

[0075] The control module 404 can be used to control the image acquisition module to capture images in real time, execute a tracking program after each image capture, and build a boundary map based on the recorded locations of multiple devices. The boundary map includes the boundary of the work area or the boundary of obstacles.

[0076] The control module 404 can construct a boundary map based on multiple recorded device positions when the self-moving device returns to the starting position. For example, the control module 404 can compare the recorded device positions with the starting position of the self-moving device. If the recorded device positions are the same as or differ from the starting position within a preset range, it can be determined that the self-moving device has returned to the starting position.

[0077] In some embodiments, the control module 404 may be a processor, and a description of the control module 404 may be given in reference to the following description of the processor 502.

[0078] For example, such as Figure 5 The diagram shown is a structural schematic of a self-moving device provided in another embodiment of this application. Figure 5 In this system, the self-moving device 50 includes a main body and a memory 501, a processor 502, a power supply 503, a sensor 504, a working mechanism 505, a communication module 506, a positioning module 507, a drive wheel 508, and a bus 509 disposed on the main body. The processor 502 is coupled to the memory 501, the power supply 503, the sensor 504, the working mechanism 505, the communication module 506, the positioning module 507, and the drive wheel 508 via the bus 509.

[0079] Memory 501 may include one or more random access memory (RAM) and one or more non-volatile memory (NVM). The RAM can be directly read and written by the processor 502 and can be used to store executable programs (such as machine instructions) of the operating system or other running programs, as well as user and application data. The RAM may include static random-access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), etc.

[0080] Non-volatile memory can also store executable programs and user and application data, and can be pre-loaded into random access memory for direct reading and writing by the processor 502. Non-volatile memory can include disk storage devices and flash memory.

[0081] Memory 501 is used to store one or more computer programs. The one or more computer programs are configured to be executed by processor 502. The one or more computer programs include multiple instructions that, when executed by processor 5003, implement a map building method that is executed on self-moving device 50.

[0082] In other embodiments, the self-moving device 50 further includes an external memory interface for connecting to an external memory to expand the storage capacity of the self-moving device 50.

[0083] Processor 502 may include one or more processing units, such as application processors (APs), modem processors, graphics processing units (GPUs), image signal processors (ISPs), controllers, video codecs, digital signal processors (DSPs), baseband processors, and / or neural network processing units (NPUs). These different processing units may be independent devices or integrated into one or more processors.

[0084] The processor 502 provides computing and control capabilities. For example, the processor 502 is used to execute computer programs stored in the memory 501 to implement the map building method described above.

[0085] Power supply 503 is used to power self-moving devices. In one embodiment of this application, power supply 503 may include any one or more power supply devices such as batteries, fuel generators, solar power modules, and wind power modules.

[0086] Sensor 504 is used to acquire information for the self-moving device 50, such as environmental information and movement information of the self-moving device 50. In one embodiment of this application, sensor 504 may include one or more sensors of the type such as lidar, camera, infrared sensor, encoder, etc.

[0087] The working mechanism 505 is used to perform corresponding work tasks, such as mowing, de-icing, patrolling, sweeping, and spraying pesticides. In some embodiments, the working mechanism 505 may include a motor, a transmission mechanism, and a blade disc. When the self-moving device is a lawnmower, the motor can drive the blade disc to rotate through the transmission mechanism to achieve the mowing function. The motor can also control the movement of the blades to adjust the mowing height and the mowing area.

[0088] The communication module 506 is used to enable communication between the self-moving device and other devices. In one embodiment of this application, the communication module 506 can interact with other devices via wired and / or wireless communication. The aforementioned wireless communication may include one or more combinations of communication methods such as Bluetooth communication, Wi-Fi communication, and Near Field Communication (NFC).

[0089] The positioning module 507 is used to determine the location of the self-moving device. In some embodiments, the positioning module 507 may include one or more positioning modules of the type such as Global Positioning System (GPS), inertial navigation system, and real-time kinematic (RTK) carrier phase differential system.

[0090] The drive wheel 508 is used to enable movement of the self-moving device. In some embodiments, the drive wheel 508 can realize the movement function of the self-moving device according to the control of the processor 502. In some embodiments, the drive wheel 508 may include a left drive wheel and a right drive wheel.

[0091] Bus 509 is used at least to provide a channel for communication between the memory 501, processor 502, power supply 503, sensor 504, working mechanism 505, communication module 506, positioning module 507, and drive wheel 508 in the self-moving device 50.

[0092] In other embodiments, the self-moving device 50 may further include an image acquisition module, a collision avoidance unit, and a steering assembly. The image acquisition module may be a visual sensor such as a camera or a video camera. The collision avoidance unit can be used to prevent the drive wheels 508 from colliding with obstacles or other objects in front of the self-moving device. The steering assembly can be used to adjust the driving direction of the drive wheels 508.

[0093] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the self-moving device 50. In other embodiments of this application, the self-moving device 50 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0094] This application also provides a computer-readable storage medium storing a computer program, which includes program instructions. When the program instructions are executed, the method implemented can refer to the methods in the above embodiments of this application.

[0095] The computer-readable storage medium can be the internal storage of the self-moving device described in the above embodiments, such as the hard disk or memory of the self-moving device. The computer-readable storage medium can also be an external storage device of the self-moving device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the self-moving device.

[0096] In some embodiments, a computer-readable storage medium may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; and the data storage area may store data created based on the use of the mobile device, etc.

[0097] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0098] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0099] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A map construction method, characterized in that, The method includes: Acquire images taken of the user; The location of the user's feet is determined based on the image; Control the self-moving device to move from its current position to follow the foot position, and record the device position of the self-moving device; A boundary map is constructed based on the recorded locations of multiple devices, and the boundary map includes the boundaries of the work area or the boundaries of obstacles.

2. The map construction method as described in claim 1, characterized in that, An image is taken at preset intervals, and a foot position is determined based on each captured image.

3. The map construction method as described in claim 1 or 2, characterized in that, The method for determining the foot position includes: Perform semantic segmentation on the image to obtain semantic segmentation results; The location of the foot is determined based on the semantic segmentation results.

4. The map construction method as described in claim 1, characterized in that, The method further includes: If the distance between the self-moving device and the user is greater than a preset threshold, the self-moving device is controlled to move from the current position to follow the foot position; If the distance is less than or equal to the preset threshold, the self-moving device is controlled to maintain its current position.

5. The map construction method as described in claim 1 or 4, characterized in that, If there are multiple foot positions, and each foot position has a corresponding time point, controlling the self-moving device to move from the current position to follow the foot position includes: Based on the stated time point, the target location is determined from multiple foot positions; Control the self-moving device to move from the current location to the target location.

6. The map construction method as described in claim 5, characterized in that, Determining the target location from multiple foot positions based on the time point includes: The target position is determined based on the earliest foot position among the plurality of foot positions.

7. The map construction method as described in claim 1 or 4, characterized in that, The method further includes: The user's first moving speed is determined based on the multiple foot positions and corresponding time points; Based on the first moving speed, the second moving speed of the self-moving device is determined; Based on the second moving speed, the self-moving device is controlled to move from the current position to follow the foot position.

8. The map construction method as described in claim 1, characterized in that, The self-moving device is communicatively connected to the control device, and the method further includes: Receive remote control commands sent from the control device, and control the self-moving device to move according to the remote control commands; Upon detecting a trigger event, the self-moving device is controlled to continue moving following the foot's position.

9. A self-moving device, characterized in that, The self-moving device includes: A mobile component for moving the self-moving device; Image acquisition module, used to capture images; A storage module is used to store a tracking program, which includes the following steps: acquiring an image of a user taken by camera, determining the user's foot position based on the image, controlling a self-moving device to move from its current position to follow the foot position, and recording the device position of the self-moving device; The control module is used to control the image acquisition module to capture images in real time, execute the tracking program after each image capture, and construct a boundary map based on the recorded locations of multiple devices. The boundary map includes the boundaries of the working area or the boundaries of obstacles.

10. A self-moving device, characterized in that, The self-moving device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the self-moving device implements the map building method as described in any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor in a self-moving device, implements the map construction method as described in any one of claims 1 to 8.

Images