Positioning methods, automated walking devices, and storage media

Abstract

This application relates to the field of walking devices, providing a positioning method, an automatic walking device, and a storage medium. The automatic walking device includes a driving module for driving the automatic walking device to move and an acquisition module for image acquisition. The method includes: responding to a start command, controlling the acquisition module to acquire images to obtain at least two first acquired images corresponding to different directions around the automatic walking device; determining a target movement direction based on the first acquired images and a boundary map atlas of the target working area where the automatic walking device is located, the boundary map atlas including multiple edge images corresponding to different edge positions of the target working area; controlling the driving module to drive the automatic walking device to perform a target driving operation in the target movement direction, and after the target driving operation is completed, controlling the acquisition module to acquire images in the target movement direction to obtain a second acquired image; and determining a first target pose of the automatic walking device based on the second acquired image and the boundary map atlas.

Description

Technical Field

[0001] This application relates to the field of automated walking equipment, and more particularly to a positioning method, an automated walking device, and a storage medium. Background Technology

[0002] To reduce the labor intensity and cost of lawn maintenance, automated walking equipment for cutting and mowing lawns, such as lawnmowers, has been developed. Currently, some lawnmowers can estimate their position in real time while moving and working on the lawn, for example, through VIO (visual-inertial odometry), and simultaneously build a map of the surrounding environment of the automated walking equipment to achieve synchronous positioning and mapping.

[0003] Existing VIO (Vehicle-Inertial Oscillator) driving solutions use visual acquisition results and inertial detection results to continuously locate the equipment during its movement. However, if the equipment restarts or is moved during its movement, the tracking of the equipment's position will be lost, making it difficult for the equipment to move and operate on the lawn. Summary of the Invention

[0004] The main purpose of this application is to provide a positioning method, an automatic walking device, and a storage medium, which are intended to determine the position and posture of the automatic walking device after it is started.

[0005] In a first aspect, this application provides a positioning method applied to an automated walking device, the automated walking device including a driving module for driving the automated walking device to move and an acquisition module for performing image acquisition, the positioning method including the following steps:

[0006] In response to the start command, the acquisition module is controlled to acquire at least two first acquired images corresponding to different directions around the automatic walking device;

[0007] The target movement direction of the automatic walking device is determined based on the boundary map set between the first acquired image and the target working area where the automatic walking device is located. The boundary map set includes multiple edge images corresponding to different edge positions of the target working area.

[0008] The driving module is controlled to drive the automatic walking device to perform a target driving operation in the target direction of movement, and after the target driving operation is completed, the acquisition module is controlled to acquire images in the target direction of movement to obtain a second acquired image;

[0009] The first target pose of the automated walking device is determined based on the second acquired image and the boundary map atlas.

[0010] Secondly, this application also provides a positioning method applied to an automated walking device, the automated walking device including a driving module for driving the automated walking device to move and an acquisition module for performing image acquisition, the positioning method including:

[0011] In response to the start command, the map attributes corresponding to each sub-map set in the boundary map set are obtained, and the map attributes include at least: a first direction attribute and a first location attribute;

[0012] Obtain the device attributes of the automated walking device, wherein the device attributes include at least: a second direction attribute and a second position attribute;

[0013] The device attributes are matched with each of the map attributes. If the first direction attribute matches the second direction attribute and the first location attribute matches the second location attribute, the sub-map set corresponding to the map attribute is determined as the target sub-map set.

[0014] The current second target pose of the automated walking device is determined based on the target sub-map set.

[0015] Thirdly, this application provides a positioning method applied to an automated walking device, the automated walking device including a driving module for driving the automated walking device to move and an acquisition module for image acquisition, the positioning method including:

[0016] The working state of the automatic walking device is obtained, and the working state includes a first working state and a second working state, wherein the first working state is the state when the automatic walking device fails to locate, and the second working state is the working state when the automatic walking device moves in the target working area.

[0017] In the first working state, in response to a start command, the acquisition module is controlled to acquire at least two first acquired images corresponding to different directions around the autonomous walking device; the target movement direction of the autonomous walking device is determined based on the first acquired images and the boundary map atlas of the target working area, the boundary map atlas including multiple edge images corresponding to different edge positions of the target working area; the driving module is controlled to drive the autonomous walking device to perform a target driving operation in the target movement direction, and after the target driving operation is completed, the acquisition module is controlled to acquire images in the target movement direction to obtain a second acquired image; the first target pose of the autonomous walking device is determined based on the second acquired image and the boundary map atlas.

[0018] In the second working state, in response to the start command, the map attributes corresponding to each sub-map set in the boundary map set are obtained, and the map attributes include at least: a first direction attribute and a first position attribute; the device attributes of the automated walking device are obtained, and the device attributes include at least: a second direction attribute and a second position attribute; the device attributes are matched with each of the map attributes, and if the first direction attribute matches the second direction attribute and the first position attribute matches the second position attribute, the sub-map set corresponding to the map attribute is determined as the target sub-map set; the current second target pose of the automated walking device is determined based on the target sub-map set.

[0019] Fourthly, this application also provides an automated walking device, the device comprising:

[0020] ontology;

[0021] A driving module is used to drive the main body to move;

[0022] A working module is set on the main body and is used to perform preset operations at the location of the automatic walking device;

[0023] The acquisition module is used for image acquisition.

[0024] A controller, connected to the driving module and the data acquisition module, is used to execute the positioning method and driving control method as described in any one of the embodiments of this application.

[0025] Fifthly, a computer-readable storage medium storing a computer program, wherein when executed by a processor, the computer program implements the steps of the positioning method as described in any one of the embodiments of this application.

[0026] This application provides a positioning method, an automated walking device, and a storage medium. In response to a start command, the method controls a data acquisition module to acquire at least two first acquired images corresponding to different directions around the automated walking device. Based on the first acquired images and a boundary map of the target working area where the automated walking device is located, the method determines the target movement direction of the automated walking device. The boundary map includes multiple edge images corresponding to different edge positions of the target working area. The method controls a driving module to drive the automated walking device to perform a target driving operation in the target movement direction. After the target driving operation is completed, the method controls the data acquisition module to acquire images in the target movement direction to obtain a second acquired image. Based on the second acquired image and the boundary map, the method determines the first target pose of the automated walking device. By acquiring first acquired images from different directions around the automated walking device, comparing the first acquired images with the edge images in the boundary map to determine the target movement direction, and further acquiring a second acquired image in the target movement direction based on the comparison results, the pose of the automated walking device can be determined based on the second acquired image and the boundary map. Even if the automated walking device experiences positioning failure (e.g., being moved manually or suddenly restarted), the pose of the automated walking device can still be accurately determined. Attached Figure Description

[0027] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 A schematic flowchart illustrating a positioning method provided in an embodiment of this application;

[0029] Figure 2 A schematic diagram of a first acquired image provided in an embodiment of this application;

[0030] Figure 3 A schematic diagram of the boundary atlas in the target working area provided in an embodiment of this application;

[0031] Figure 4 A schematic diagram illustrating the target movement direction according to an embodiment of this application;

[0032] Figure 5 A schematic flowchart illustrating a positioning method provided in another embodiment of this application;

[0033] Figure 6 A schematic flowchart illustrating a positioning method provided in another embodiment of this application;

[0034] Figure 7 This is a schematic block diagram of the structure of a self-moving robot provided in an embodiment of this application;

[0035] Figure 8 This is a schematic diagram of the structure of a self-moving robot provided in an embodiment of this application;

[0036] Figure 9 This is a schematic block diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0037] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0038] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the order described. For example, some operations / steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.

[0039] This application provides a positioning method, an automatic walking device, and a storage medium.

[0040] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0041] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating a positioning method provided in an embodiment of this application. This positioning method can be used in a terminal or server to determine the pose of an automated walking device in a target working area. The terminal can be a self-moving robot, such as a lawnmower or a sweeping robot; the server can be a standalone server, a server cluster, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0042] like Figure 1 As shown, the positioning method includes steps S101 to S104.

[0043] Step S101: In response to the start command, control the acquisition module to acquire at least two first acquisition images corresponding to different directions around the automatic walking device.

[0044] Please refer to Figure 2 , Figure 2 This is a schematic diagram of a first acquired image provided in an embodiment of this application.

[0045] like Figure 2 As shown, Figure 2 Each triangle in the diagram represents a frame of the first acquired image, with the apex of each triangle pointing in the direction of acquisition. Optionally, when the automatic walking device receives a start command, if its acquisition module is fixedly installed, it can rotate 360 ​​degrees in place and capture the first acquired image in each of its surrounding directions. Optionally, if its acquisition module is a rotatable structure, images in different directions can be acquired by rotating the image acquisition device. Optionally, a fixed camera array can be set in each direction of the automatic walking device, and the cameras in each direction can be controlled to simultaneously capture surrounding images. Optionally, the number of acquisition modules on the automatic walking device can be one or more. When only one acquisition module is set on the automatic moving device, the driving module is controlled to drive the automatic walking device to rotate one full circle and acquire the first acquired image in each of its surrounding directions. When two acquisition modules facing opposite directions are set on the automatic moving device, the driving module can be controlled to drive the automatic walking device to rotate half a circle and acquire the first acquired image in each of its surrounding directions.

[0046] In some embodiments, controlling the acquisition module to acquire images to obtain at least two first acquired images corresponding to different directions around the automated walking device includes:

[0047] The driving module is controlled to drive the automatic walking device to rotate so that the acquisition module faces different orientation directions in turn, and the acquisition module is controlled to acquire images when facing each orientation direction to obtain the first acquired image corresponding to each orientation direction.

[0048] Optionally, the control module drives the automatic walking device to rotate in place, so that the acquisition module faces multiple different orientations at once. Whenever the acquisition module faces a specific direction, the control module controls the acquisition module to perform an image acquisition, thereby obtaining a first acquired image corresponding to that orientation. Optionally, this rotation can be clockwise or counterclockwise, and the rotation layout can be set according to actual needs. Figure 2For example, the automated walking device captures first images in eight directions around its perimeter. For instance, it captures an image every 45 degrees of rotation, sequentially acquiring eight images within a 360-degree range. During this process, the acquisition module can be a single, fixed camera structure, which acquires multi-directional image information through the rotation of the automated walking device itself. However, this is not limited to this; this application does not limit the number of directions or the angle interval for image acquisition. In practical applications, the number of directions (such as 4, 6, 12, or 16 directions) can be adjusted according to the device's computing power and the accuracy requirements of the recognition algorithm. The first acquired image can include images from more or fewer directions, which is not limited here.

[0049] In some implementations, the activation command is generated when the positioning of the automated walking device fails.

[0050] For example, positioning failure of automated walking equipment includes, but is not limited to, restarting of the automated walking equipment or being moved by external force.

[0051] Understandably, when an automated walking device is moved by an external force, because its body is artificially moved from its original position to a new one without undergoing the movement process recorded by its own control system, its posture information undergoes abrupt changes and cannot be accurately perceived by the device's internal inertial navigation system or wheeled odometer positioning module. When the automated walking device is artificially moved, a significant deviation occurs between its original posture estimation information and its actual posture, causing the positioning system to fail. In this situation, the automated walking device is like being "kidnapped," forcibly taken to an unknown location; this is called a kidnapping state.

[0052] Optionally, the automated walking device also cannot detect whether it has been moved by an external force during the restart process. Therefore, after the automated walking device restarts or is moved by an external force, its position needs to be re-determined using the positioning method provided in this application embodiment.

[0053] Optionally, when the automated walking device continuously detects abnormalities in its own positioning information during operation (such as sudden position changes, orientation drift, invalid positioning module data, etc.), it can be determined that the current positioning system may have failed. The control system can then generate a start command to perform a repositioning operation. If the automated walking device has been stored without power for an extended period or is in transport mode, its original pose information may have become invalid. After the device recovers from such a state, the system can automatically generate a start command to perform repositioning to ensure the safety and reliability of subsequent tasks.

[0054] Therefore, in any of the above situations, in order to ensure that the automatic walking device can regain accurate self-position information, the start command in step S101 is generated when the automatic walking device fails to position.

[0055] Step S102: Determine the target movement direction of the automatic walking device based on the boundary map atlas of the first acquired image and the target working area where the automatic walking device is located. The boundary map atlas includes multiple edge images corresponding to different edge positions of the target working area.

[0056] Please refer to Figure 3 , Figure 3 This is a schematic diagram of the boundary atlas of the target working area provided in an embodiment of this application.

[0057] A boundary map atlas is constructed, comprising multiple edge images corresponding to different edge locations of the target working area. These edge images are constructed by collecting image data along the edges of the working area during the pre-calibration phase before equipment deployment. The boundary map atlas can be divided into several sub-map atlases, such as… Figure 3 As shown, the boundary map set of the target working area includes sub-map set 1 and sub-map set 2. Each sub-map set corresponds to a different edge position in the target working area. Sub-map set 1 and sub-map set 2 correspond to different edge segments of the target working area. Each sub-map set includes multiple edge images acquired in a fixed direction.

[0058] For example, by comparing the first acquired image with the edge images in each sub-map set of the boundary map set, the target movement direction of the automated walking device is determined, so as to control the automated walking device to move in the target movement direction and take a second acquired image for further comparison.

[0059] In some embodiments, determining the target movement direction of the automated walking device based on the boundary map atlas of the first acquired image and the target working area where the automated walking device is located includes:

[0060] The first acquired image is compared with the boundary map set to obtain the similarity between the first acquired image and each of the edge images; the similarity can be the Euclidean distance, Hamming distance, cosine similarity between image features, or a similarity score based on the output of a deep neural network, which is not specifically limited in this application.

[0061] Based on the similarity between the first acquired image and the edge image, a target direction image is selected from the first acquired image, and the direction corresponding to the target direction image is used as the target movement direction.

[0062] For example, the first acquired image is compared with the boundary map atlas. For instance, the first acquired image is compared with the edge images in each sub-map atlas of the boundary map atlas to obtain the similarity between the first acquired image and each edge image. The similarity can be calculated based on the feature vector of the first acquired image and the feature vector of each edge image, and can be Euclidean distance, cosine similarity, etc., which is not limited here.

[0063] For example, after obtaining the similarity, edge images with similarity higher than a set threshold are used as candidate images, edge images with greater similarity to the first acquired image are used as target direction images, and the acquisition direction of the edge image with greater similarity to the first acquired image is used as the target movement direction, so as to control the automatic walking device to move towards the target movement direction and capture a second acquired image for further comparison.

[0064] In some implementations, the step of filtering the target direction image from the first acquired image based on the similarity between the first acquired image and the edge image includes:

[0065] The similarity between each of the first acquired images and each of the edge images is sorted.

[0066] Based on the sorting results, N pairs of the first acquired image and the edge image with the highest similarity are obtained, and the corresponding first acquired image is used as the image to be determined in the direction, where N is an integer.

[0067] The target direction image is selected from the images of the unknown direction based on the boundary map atlas.

[0068] For example, to improve the accuracy of the target's movement direction, a target direction image is determined based on multiple images of the undetermined direction. Specifically, the similarity between each first acquired image and its edge image is sorted, and the first acquired image among the top N first acquired images and their edge images in the sorted results is used as the image of the undetermined direction. The size of N can be set according to actual needs, for example, it can be the top 10, and is not limited here.

[0069] Please refer to Figure 4 , Figure 4 This is a schematic diagram illustrating the target movement direction according to an embodiment of this application.

[0070] like Figure 4As shown, assuming that similarity matching is performed between first-captured images acquired from multiple directions and edge images in the boundary map set, and all comparison results are sorted according to similarity scores, several pairs of "first-captured image-edge image" pairings with the top N similarity rankings are selected for subsequent judgment. If, among the top N first-captured image-edge images in the similarity ranking, there are multiple frames (e.g., 3 frames) of first-captured images from different directions, and these images all have high similarity, then the directions corresponding to these 3 frames of first-captured images are taken as images of undetermined directions. Figure 4 The first acquired image, displayed in bold, is the image with the direction to be determined.

[0071] For example, images of a desired orientation can be fused to obtain a target orientation image. This can be achieved by adding the direction vectors of the images of the desired orientation to obtain the target direction vector, and then using the image of the desired orientation whose direction vector is closest to the target direction vector as the target orientation image. Figure 4 For example, after fusing the images of undetermined direction 1, undetermined direction 2 and undetermined direction 3, the undetermined direction image 2 is used as the target direction image.

[0072] Specifically, for each frame of the image with the unknown orientation, the device orientation angle (e.g., the yaw angle provided by the IMU) corresponding to its acquisition time is obtained and converted into a two-dimensional unit direction vector form, with the angle θ. i Can be converted into vector V i =(cosθ i, sinθ i ); sum the direction vectors of all images with undetermined directions to obtain the fused direction vector V. target Calculate the direction vector V corresponding to each image in the unknown direction. i With fusion direction vector V target The angle or Euclidean distance between the two values ​​is used to select the one with the smallest difference as the final target orientation image.

[0073] by Figure 4 For example, assuming the directions of image 1, image 2, and image 3 to be determined are 0°, 45°, and 90° respectively, then the direction vector corresponding to image 1 to be determined is: = (cos0°,sin0°) = (1,0), and the direction vector corresponding to the undetermined direction image 2 is: = (cos45°,sin45°) ≈ (0.707,0.707), and the direction vector corresponding to the undetermined direction image 3 is: = (cos90°,sin90°) = (0,1); Adding these three values ​​together yields the fusion direction vector: = + + = (1+0.707+0,0+0.707+1) = (1.707,1.707). This will fuse the direction vectors. The direction vectors of the images in each unknown direction are respectively , , By comparing, we can obtain and The cosine similarity is 0.707. and The cosine similarity is 0.707. and The cosine similarity is 0.707. At this point, the similarity between the three frames and the fused direction vector is close, and they are theoretically equivalent. However, if we take the image of the unknown direction whose direction vector is closest to the fused direction vector as the target direction image according to the principle of closest vector direction, then... =(1.707,1.707) is the direction vector corresponding to the direction of 45°. The closest approach is to use the undetermined orientation image 2 at 45° as the final target orientation image.

[0074] Step S103: Control the driving module to drive the automatic walking device to perform the target driving operation in the target direction of movement, and after the target driving operation is completed, control the acquisition module to acquire images in the target direction of movement to obtain a second acquired image.

[0075] For example, the driving module of the automated walking device moves a certain distance in the target movement direction corresponding to the target direction image, where the target movement direction is the shooting direction of the target direction image. The automated walking device is brought closer to the edge position corresponding to one of the sub-maps in the boundary map set, and after moving a certain distance, a second acquired image is captured. This second acquired image is then further compared with the edge image in the boundary map set. If the second acquired image also matches the edge image, the first target pose of the automated walking device is determined based on the sub-map set described in the edge image.

[0076] like Figure 4 As shown, after the automated walking device moves a certain distance in the direction of the target movement, it captures a second image in that direction. The acquisition direction of the second image may also include directions adjacent to the target movement direction, such as... Figure 4 The second acquisition consists of three frames captured in the direction of the target's movement and in two adjacent directions. However, this is not a limitation; the second acquisition can have more or fewer frames and different shooting directions.

[0077] In some embodiments, controlling the driving module to drive the autonomous walking device to perform a target driving operation in the target direction of movement includes:

[0078] The driving module is controlled to drive the automatic walking device to travel in the target direction for a preset time; or,

[0079] The driving module is controlled to drive the automatic walking device to travel a preset distance in the direction of the target movement.

[0080] For example, the distance the automated walking device moves in the target direction can be determined according to actual needs. Specifically, the duration of the automated walking device's movement in the target direction can be preset to obtain a preset duration, thereby controlling the driving module to drive the automated walking device to travel in the target direction at a certain speed for the preset duration; or, the distance the automated walking device moves in the target direction can be preset to obtain a preset travel distance, thereby controlling the driving module to drive the automated walking device to travel the preset distance in the target direction.

[0081] Step S104: Determine the first target pose of the automatic walking device based on the second acquired image and the boundary map atlas.

[0082] For example, the first target pose of the autonomous walking device is determined by comparing the second acquired image with the edge image in the boundary map set. Specifically, the feature points in the second acquired image can be matched with the feature points in the edge image using the SLAM (Simultaneous Localization and Mapping) algorithm to determine the 6-DOF pose of the autonomous walking device in the target working area, that is, the position and orientation of the autonomous walking device in three-dimensional space, specifically including three translational degrees of freedom and three rotational degrees of freedom.

[0083] In some embodiments, the boundary atlas includes at least two sub-atlases corresponding to different edge images, each sub-atlas including at least one edge image;

[0084] Determining the first target pose of the automated walking device based on the second acquired image and the boundary map atlas includes:

[0085] Select a target sub-map set from the boundary map set according to the target's direction of movement;

[0086] The pose of the first target is determined based on the edge image in the target sub-map set and the second acquired image.

[0087] For example, the boundary atlas includes two or more sub-atlases, each sub-atlas corresponding to different edge locations of the target working area, and contains at least one edge image taken near the edge location. Therefore, the target sub-atlas needs to be determined from the sub-atlases based on the second acquired image, and then the first target pose is determined by comparing the second acquired image with the edge image in the target sub-atlas.

[0088] The target sub-map set can be determined based on the acquisition location and direction of the second acquired image, as well as the acquisition location and direction of the edge images within each sub-map set. Understandably, each sub-map set has its own location and direction attributes. The number of location attributes can be multiple, representing the acquisition location of each edge image within the sub-map set. Since the acquisition directions of edge images within the same sub-map set are roughly the same, the direction attribute of the sub-map set can be one, representing the acquisition direction of each edge image within the sub-map set. Specifically, the acquisition direction and location of the second acquired image are determined by combining the location and direction attributes of the second acquired image.

[0089] For example, if the acquisition location of the second acquired image matches the location attribute of the sub-map set, and the acquisition direction of the second acquired image matches the direction attribute of the sub-map set, the sub-map set is determined as the target sub-map set.

[0090] For example, the first target pose can be determined based on a combination of the Random Sample Consensus (RANSAC) algorithm and the Perspective-n-Point (PnP) algorithm. For instance, feature points can be randomly extracted from the second acquired image using the RANSAC algorithm, and then the first target pose can be solved based on the correspondence between feature points in the second acquired image and feature points in the edge image using the PnP algorithm. Alternatively, each feature point in the edge image can be stored as a descriptor, and when the second acquired image is obtained, the descriptor can be calculated based on the feature points in the second acquired image. The descriptor corresponding to the edge image can then be compared with the descriptor of the second acquired image to obtain the first target pose.

[0091] In some implementations, the target sub-map set includes the sub-map set corresponding to the target's direction of movement; or,

[0092] The target sub-map set includes the sub-map set corresponding to the target's movement direction and the sub-map set corresponding to the approximate movement direction adjacent to the target's movement direction.

[0093] like Figure 4As shown, since the second acquired image includes images taken towards the target's movement direction and images taken towards an approximate movement direction adjacent to the target's movement direction, the target sub-map set can be a sub-map set with the same direction attribute as the target's movement direction, or a sub-map set with the same direction attribute as the approximate movement direction; no limitation is made here.

[0094] The positioning method provided in this application, in response to a start command, controls the acquisition module to acquire at least two first acquired images corresponding to different directions around the automated walking device; determines the target movement direction of the automated walking device based on the first acquired images and a boundary map atlas of the target working area where the automated walking device is located, wherein the boundary map atlas includes multiple edge images corresponding to different edge positions of the target working area; controls the driving module to drive the automated walking device to perform a target driving operation in the target movement direction, and after the target driving operation is completed, controls the acquisition module to acquire images in the target movement direction to obtain a second acquired image; and determines the first target pose of the automated walking device based on the second acquired image and the boundary map atlas. Because by acquiring first acquired images in different directions around the automated walking device, comparing the first acquired images with the edge images in the boundary map atlas to determine the target movement direction, and further acquiring a second acquired image in the target movement direction based on the comparison results, the pose of the automated walking device can be determined based on the second acquired image and the boundary map atlas. Even if the automated walking device experiences positioning failure (e.g., being moved manually or suddenly restarted), the pose of the automated walking device can still be accurately determined.

[0095] Please refer to Figure 5 , Figure 5 This is a flowchart illustrating a positioning method provided in another embodiment of this application.

[0096] This application also provides a positioning method for use in an automated walking device. The automated walking device is described in the embodiments of this application and will not be repeated here.

[0097] like Figure 5 As shown, the method includes steps S201-S204:

[0098] Step S201: In response to the start command, obtain the map attributes corresponding to each sub-map set in the boundary map set, wherein the map attributes include at least: a first direction attribute and a first location attribute;

[0099] Step S202: Obtain the device attributes of the automatic walking device, wherein the device attributes include at least: a second direction attribute and a second position attribute;

[0100] Step S203: Match the device attributes with each of the map attributes. If the first direction attribute matches the second direction attribute and the first location attribute matches the second location attribute, determine the sub-map set corresponding to the map attribute as the target sub-map set.

[0101] Step S204: Determine the current second target pose of the automated walking device based on the target sub-map atlas.

[0102] For example, when the automated walking device is started normally, the target sub-map corresponding to the automated walking device can be determined by comparing the map attributes of the existing sub-map set with the device attributes of the automated walking device, and then the automated walking device can be located based on the target sub-map.

[0103] The map attributes of a sub-map set may include, for example, a first direction attribute and multiple first location attributes. The first direction attribute is the acquisition direction of each edge image in the sub-map set, and the multiple first location attributes are the acquisition locations of each edge image.

[0104] The device attributes of an automated walking device may include a second direction attribute and a second position attribute. The second direction attribute is the direction that the automated walking device is facing, and the second position attribute is the location of the automated walking device.

[0105] For example, matching the first direction attribute with the second direction attribute can be achieved by the angle between the angles of the first direction attribute and the second direction attribute being less than a preset angle. Matching the first position attribute with the second position attribute can be achieved by the distance between the position coordinates of the first position attribute and the position coordinates of the second position attribute being less than a preset distance.

[0106] For example, the method for determining the pose of the second target based on the target sub-map atlas can be referred to the description in the embodiments of this application, and will not be repeated here.

[0107] Please refer to Figure 6 , Figure 6 This is a flowchart illustrating a positioning method provided in another embodiment of this application.

[0108] This application also provides a positioning method for use in an automated walking device. The automated walking device is described in the embodiments of this application and will not be repeated here.

[0109] like Figure 6 As shown, the method includes steps S301-S303:

[0110] Step S301: Obtain the working state of the automatic walking device. The working state includes a first working state and a second working state. The first working state is the state when the automatic walking device fails to locate, and the second working state is the working state when the automatic walking device moves in the target working area.

[0111] Step S302: In the first working state, in response to the start command, control the acquisition module to acquire at least two first acquisition images corresponding to different directions around the automatic walking device; determine the target movement direction of the automatic walking device based on the first acquisition images and the boundary map atlas of the target working area, wherein the boundary map atlas includes multiple edge images corresponding to different edge positions of the target working area; control the driving module to drive the automatic walking device to perform a target driving operation in the target movement direction, and after the target driving operation is completed, control the acquisition module to acquire images in the target movement direction to obtain a second acquisition image; determine the first target pose of the automatic walking device based on the second acquisition image and the boundary map atlas.

[0112] Step S303: In the second working state, in response to the start command, obtain the map attributes corresponding to each sub-map set in the boundary map set, the map attributes including at least: a first direction attribute and a first position attribute; obtain the device attributes of the automated walking device, the device attributes including at least: a second direction attribute and a second position attribute; match the device attributes with each of the map attributes, and if the first direction attribute matches the second direction attribute and the first position attribute matches the second position attribute, determine the sub-map set corresponding to the map attribute as the target sub-map set; determine the current second target pose of the automated walking device based on the target sub-map set.

[0113] For example, the first working state is the working state when the automatic walking equipment is restarted or moved, i.e., the "kidnapped state"; the second working state is the working state when the automatic walking equipment is started normally and performing operations.

[0114] Understandably, in the second working state, the automated walking device can directly (e.g., through IMU, GPS, RTK modules) determine its own second orientation attribute and second position attribute, such as the direction the automated walking device is facing and its current position. By comparing the second orientation attribute and second position attribute with the first orientation attribute and first position attribute of each sub-map set, the target sub-map set corresponding to the automated walking device at that position and angle is determined, thus obtaining the second target pose. However, in the first working state, since the automated walking device's positioning fails, it is difficult to determine the accurate position and angle. Therefore, it is necessary to compare the first acquired image with the edge image to determine the sub-map set that can be used for the automated walking device's positioning, thus obtaining the first target pose.

[0115] For example, the positioning method provided in the embodiments of this application can be referred to the positioning method provided in other embodiments of this application, and will not be described in detail here.

[0116] Please refer to Figure 7 , Figure 8 , Figure 7 This is a schematic block diagram of the structure of a self-moving robot provided in an embodiment of this application; Figure 8 This is a schematic diagram of the structure of a self-moving robot provided in an embodiment of this application.

[0117] like Figure 7 , Figure 8 As shown in the illustration, this application also provides a self-moving robot, which includes:

[0118] Ontology 10;

[0119] The driving module 20 is used to drive the main body.

[0120] The working module 30 is set on the main body and is used to perform grass mowing operations at the location of the self-moving robot;

[0121] The acquisition module 40 is used at least to acquire images of the environment in which the self-moving robot is located and to acquire the pose of the self-moving robot.

[0122] A controller (not shown) is connected to the driving module and the data acquisition module, and is used to execute the positioning method and driving control method as described in any one of the embodiments of this application.

[0123] For example, the self-moving robot provided in this application embodiment can be used to perform lawn mowing operations during movement. Of course, it is not limited to this. The self-moving robot provided in this application embodiment can also perform cleaning, snow sweeping, leaf blowing and other operations, which are not limited here.

[0124] The acquisition module 40 of the self-moving robot is used to acquire image data and pose data of the robot's environment. For example, it may include: a visible light camera or infrared camera for acquiring image data, an inertial measurement module for obtaining the acquisition direction, and a real-time dynamic positioning module for obtaining the acquisition position. However, it is not limited to these; the acquisition module 40 can be replaced with other devices or include more components, which is not limited here.

[0125] For example, the controller is at least used to implement the positioning method provided in the embodiments of this application to determine a first target pose of the automated walking device.

[0126] For example, the above method can be implemented as a computer program, which can be used in, for example... Figure 9 It runs on the computer device shown.

[0127] Please see Figure 9 , Figure 9 This is a schematic block diagram illustrating the structure of a computer device provided in an embodiment of this application. This computer device can be configured within a self-moving robot for running the computer-readable storage medium provided in this embodiment.

[0128] like Figure 9 As shown, the computer device includes a processor, a memory, and a network interface connected via a system bus, wherein the memory may include a storage medium and internal memory.

[0129] The storage medium may store the operating system and computer programs. The computer programs include program instructions that, when executed, cause the processor to perform any positioning method.

[0130] The processor provides computing and control capabilities, supporting the operation of the entire computer device.

[0131] Internal memory provides an environment for the execution of computer programs stored in the storage medium. When the computer program is executed by the processor, it enables the processor to perform any positioning method.

[0132] This network interface is used for network communication, such as sending assigned tasks. Those skilled in the art will understand that... Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0133] This application also provides a computer-readable storage medium storing a computer program, the computer program including program instructions, and the method implemented when the program instructions are executed can be referred to various embodiments of the positioning method of this application.

[0134] The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiments, such as the hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, SmartMedia Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the computer device.

[0135] In one embodiment, the processor is configured to run a computer program stored in memory to perform the following steps:

[0136] In response to the start command, the acquisition module is controlled to acquire at least two first acquired images corresponding to different directions around the automatic walking device;

[0137] The target movement direction of the automatic walking device is determined based on the boundary map set between the first acquired image and the target working area where the automatic walking device is located. The boundary map set includes multiple edge images corresponding to different edge positions of the target working area.

[0138] The driving module is controlled to drive the automatic walking device to perform a target driving operation in the target direction of movement, and after the target driving operation is completed, the acquisition module is controlled to acquire images in the target direction of movement to obtain a second acquired image;

[0139] The first target pose of the automated walking device is determined based on the second acquired image and the boundary map atlas.

[0140] In one embodiment, the processor is configured to run a computer program stored in memory to perform the following steps:

[0141] In response to the start command, the map attributes corresponding to each sub-map set in the boundary map set are obtained, and the map attributes include at least: a first direction attribute and a first location attribute;

[0142] Obtain the device attributes of the automated walking device, wherein the device attributes include at least: a second direction attribute and a second position attribute;

[0143] The device attributes are matched with each of the map attributes. If the first direction attribute matches the second direction attribute and the first location attribute matches the second location attribute, the sub-map set corresponding to the map attribute is determined as the target sub-map set.

[0144] The current second target pose of the automated walking device is determined based on the target sub-map set.

[0145] In one embodiment, the processor is configured to run a computer program stored in memory to perform the following steps:

[0146] The working state of the automatic walking device is obtained, and the working state includes at least a first working state and a second working state, wherein the first working state is the state when the automatic walking device fails to locate, and the second working state is the working state when the automatic walking device moves in the target working area.

[0147] In the first working state, in response to a start command, the acquisition module is controlled to acquire at least two first acquired images corresponding to different directions around the autonomous walking device; the target movement direction of the autonomous walking device is determined based on the first acquired images and the boundary map atlas of the target working area, the boundary map atlas including multiple edge images corresponding to different edge positions of the target working area; the driving module is controlled to drive the autonomous walking device to perform a target driving operation in the target movement direction, and after the target driving operation is completed, the acquisition module is controlled to acquire images in the target movement direction to obtain a second acquired image; the first target pose of the autonomous walking device is determined based on the second acquired image and the boundary map atlas.

[0148] In the second working state, in response to the start command, the map attributes corresponding to each sub-map set in the boundary map set are obtained, and the map attributes include at least: a first direction attribute and a first position attribute; the device attributes of the automated walking device are obtained, and the device attributes include at least: a second direction attribute and a second position attribute; the device attributes are matched with each of the map attributes, and if the first direction attribute matches the second direction attribute and the first position attribute matches the second position attribute, the sub-map set corresponding to the map attribute is determined as the target sub-map set; the current second target pose of the automated walking device is determined based on the target sub-map set.

[0149] It should be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the scope of the application. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0150] It should also be understood that the term "and / or" as used in this specification and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations. It should be noted that, herein, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0151] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments. The above descriptions are merely specific implementations of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A positioning method applied to an automated walking device, the automated walking device comprising a driving module for driving the automated walking device to move and an acquisition module for image acquisition, characterized in that, The method includes: In response to the start command, the acquisition module is controlled to acquire at least two first acquired images corresponding to different directions around the automatic walking device; The target movement direction of the automatic walking device is determined based on the boundary map atlas between the first acquired image and the target working area where the automatic walking device is located. The boundary map atlas includes multiple edge images corresponding to different edge positions of the target working area. The driving module is controlled to drive the automatic walking device to perform a target driving operation in the target direction of movement, so that the automatic walking device gets closer to the edge position of one of the sub-maps in the boundary map set. After the target driving operation is completed, the acquisition module is controlled to acquire images in the target direction of movement to obtain a second acquired image. The first target pose of the automated walking device is determined based on the second acquired image and the boundary map atlas.

2. The positioning method as described in claim 1, characterized in that, Determining the target movement direction of the automated walking device based on the boundary map atlas of the first acquired image and the target working area where the automated walking device is located includes: The first acquired image is compared with the boundary map set to obtain the similarity between the first acquired image and each of the edge images; Based on the similarity between the first acquired image and the edge image, a target direction image is selected from the first acquired image, and the direction corresponding to the target direction image is used as the target movement direction.

3. The positioning method according to claim 2, characterized in that, The step of filtering the target direction image from the first acquired image based on the similarity between the first acquired image and the edge image includes: The similarity between each of the first acquired images and each of the edge images is sorted. Based on the sorting results, N pairs of the first acquired image and the edge image with the highest similarity are obtained, and the corresponding first acquired image is used as the image to be determined in the direction, where N is an integer. The target direction image is selected from the images of the unknown direction based on the boundary map atlas.

4. The positioning method as described in claim 1, characterized in that, The control of the driving module to drive the automatic walking device to perform target driving operations in the target movement direction includes: The driving module is controlled to drive the automatic walking device to travel in the target direction for a preset time; or, The driving module is controlled to drive the automatic walking device to travel a preset distance in the direction of the target movement.

5. The positioning method as described in claim 1, characterized in that, The boundary map set includes at least two sub-map sets corresponding to different edge images, and each sub-map set includes at least one edge image; Determining the first target pose of the automated walking device based on the second acquired image and the boundary map atlas includes: Select a target sub-map set from the boundary map set according to the target's direction of movement; The pose of the first target is determined based on the edge image in the target sub-map set and the second acquired image.

6. The positioning method as described in claim 5, characterized in that, The target sub-map set includes the sub-map set corresponding to the target's direction of movement; or... The target sub-map set includes the sub-map set corresponding to the target's movement direction and the sub-map set corresponding to the approximate movement direction adjacent to the target's movement direction.

7. The positioning method according to any one of claims 1-6, characterized in that, The control of the acquisition module to acquire images to obtain at least two first acquired images corresponding to different directions around the automatic walking device includes: The driving module is controlled to drive the automatic walking device to rotate so that the acquisition module faces different orientation directions in turn, and the acquisition module is controlled to acquire images when facing each orientation direction to obtain the first acquired image corresponding to each orientation direction.

8. The positioning method according to any one of claims 1-6, characterized in that, The start command is generated when the positioning of the automatic walking device fails.

9. A positioning method applied to an automated walking device, the automated walking device comprising a driving module for driving the automated walking device to move and an acquisition module for image acquisition, characterized in that, The method includes: In response to the start command, the map attributes corresponding to each sub-map set in the boundary map set are obtained, and the map attributes include at least: a first direction attribute and a first location attribute; Obtain the device attributes of the automated walking device, wherein the device attributes include at least: a second direction attribute and a second position attribute; The device attributes are matched with each of the map attributes. If the first direction attribute matches the second direction attribute and the first location attribute matches the second location attribute, the sub-map set corresponding to the map attribute is determined as the target sub-map set. The current second target pose of the automated walking device is determined based on the target sub-map set; The first direction attribute is the acquisition direction of each edge image in the sub-map set, and the first position attribute is the acquisition position of each edge image.

10. A positioning method applied to an automated walking device, the automated walking device comprising a driving module for driving the automated walking device to move and an acquisition module for image acquisition, characterized in that, The method includes: The working state of the automatic walking device is obtained, and the working state includes at least a first working state and a second working state, wherein the first working state is the state when the automatic walking device fails to locate, and the second working state is the working state when the automatic walking device moves in the target working area. In the first working state, in response to a start command, the acquisition module is controlled to acquire at least two first acquired images corresponding to different directions around the autonomous walking device; the target movement direction of the autonomous walking device is determined based on the first acquired images and the boundary map atlas of the target working area, the boundary map atlas including multiple edge images corresponding to different edge positions of the target working area; the driving module is controlled to drive the autonomous walking device to perform a target driving operation in the target movement direction, and after the target driving operation is completed, the acquisition module is controlled to acquire images in the target movement direction to obtain a second acquired image; the first target pose of the autonomous walking device is determined based on the second acquired image and the boundary map atlas. In the second working state, in response to the start command, the map attributes corresponding to each sub-map set in the boundary map set are obtained, and the map attributes include at least: a first direction attribute and a first position attribute; the device attributes of the automated walking device are obtained, and the device attributes include at least: a second direction attribute and a second position attribute; the device attributes are matched with each of the map attributes, and if the first direction attribute matches the second direction attribute and the first position attribute matches the second position attribute, the sub-map set corresponding to the map attribute is determined as the target sub-map set; the current second target pose of the automated walking device is determined based on the target sub-map set.

11. An automatic walking device, characterized in that, The device includes: ontology; A driving module is used to drive the main body to move; A working module is set on the main body and is used to perform preset operations at the location of the automatic walking device; The acquisition module is used for image acquisition. A controller, connected to the driving module and the acquisition module, is used to execute the positioning method and driving control method as described in any one of claims 1-10.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, it implements the steps of the positioning method as described in any one of claims 1 to 10.

Images