Pose correction method, automatic walking device and computer storage medium

Abstract

The application relates to the field of automatic walking equipment, and provides a driving control method, automatic walking equipment and a computer storage medium. The method comprises the following steps: in response to a control instruction of a user, starting a working mode of the automatic walking equipment; acquiring a boundary image corresponding to a boundary position of the automatic walking equipment in a target working area; constructing a boundary sub-map corresponding to at least two different boundary positions according to the boundary image; checking image data acquired by the automatic walking equipment according to the boundary sub-map, and obtaining a first image pose; and correcting an error of a historical pose of the automatic walking equipment according to the first image pose, and obtaining a target pose.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of automatic walking equipment, in particular to a pose correction method of automatic walking equipment, automatic walking equipment and computer storage medium. BACKGROUND

[0002] In order to reduce the labor intensity and cost of lawn maintenance, automatic walking equipment for cutting and trimming lawns, such as lawn mowers, has been born. At present, some lawn mowers mainly estimate the position of the vehicle in real time through a VIO (visual-inertial odometry) system when driving and working on the lawn, and at the same time construct a surrounding environment map of the automatic walking equipment to realize simultaneous localization and mapping. However, the existing VIO scheme requires a large amount of image data for mapping, and the automatic walking equipment needs to search in a large amount of image data when correcting the pose, which results in low correction efficiency and accuracy. SUMMARY

[0003] The main purpose of the present application is to provide a pose correction method of automatic walking equipment, automatic walking equipment and computer storage medium, which aims to improve the accuracy of pose correction of automatic walking equipment.

[0004] In a first aspect, the present application provides a pose correction method of automatic walking equipment, which comprises the following steps:

[0005] In response to a control instruction of a user, a working mode of the automatic walking equipment is started;

[0006] A boundary image corresponding to a boundary position of the automatic walking equipment in a target working area is obtained;

[0007] According to the boundary image, a boundary sub-map corresponding to at least two different boundary positions is constructed;

[0008] According to the boundary sub-map, the image data obtained by the automatic walking equipment is verified to obtain a first image pose;

[0009] According to the first image pose, the historical pose of the automatic walking equipment is error corrected to obtain a target pose.

[0010] In a second aspect, the present application further provides an automatic walking equipment, which comprises:

[0011] A body;

[0012] A driving module for driving the body to drive;

[0013] A working module is arranged in the body and is configured to perform a mowing operation on a position where the automatic walking device is located.

[0014] A collecting module is configured to collect an image of an environment where the automatic walking device is located and collect a pose of the automatic walking device.

[0015] A controller is connected to the driving module and the collecting module and is configured to execute a pose correction method of the automatic walking device according to any one of the embodiments of the present application.

[0016] In a third aspect, the present application provides a computer readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the pose correction method of the automatic walking device.

[0017] The present application provides a pose correction method of an automatic walking device, the automatic walking device and a computer storage medium. The present application starts a working mode of the automatic walking device in response to a control instruction of a user, acquires a boundary image corresponding to a boundary position of the automatic walking device in a target working area, constructs a boundary sub-map corresponding to at least two different boundary positions according to the boundary image, checks image data acquired by the automatic walking device according to the boundary sub-map to obtain a first image pose, and corrects an error of a historical pose of the automatic walking device according to the first image pose to obtain a target pose. Since the historical pose is corrected according to the first image pose checked by the boundary sub-map, the accuracy of pose correction of the automatic walking device is improved, and the accuracy of movement of the automatic walking device is improved. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0019] Figure 1 A flowchart of a pose correction method of an automatic walking device according to an embodiment of the present application is shown.

[0020] Figure 2 A schematic diagram of a boundary image in a boundary sub-map according to an embodiment of the present application is shown.

[0021] Figure 3 A schematic diagram of a first image pose according to an embodiment of the present application is shown.

[0022] Figure 4A schematic diagram of error correction of a historical pose according to a first image pose provided by an embodiment of the present application is shown in the following figure.

[0023] Figure 5 A schematic diagram of a motion trajectory of a first driving operation provided by an embodiment of the present application is shown in the following figure.

[0024] Figure 6 A schematic diagram of a motion trajectory of an automatic walking device provided by related technologies of the present application is shown in the following figure.

[0025] Figure 7 A schematic diagram of a structure of an automatic walking device provided by an embodiment of the present application is shown in the following figure. DETAILED DESCRIPTION

[0026] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0027] The flowchart shown in the accompanying drawings is only an example and does not necessarily include all the contents and operations / steps, nor does it necessarily be executed in the described order. For example, some operations / steps can be further decomposed, combined or partially merged, so the actual execution order may be changed according to the actual situation.

[0028] The embodiments of the present application provide a pose correction method of an automatic walking device, an automatic walking device and a computer storage medium.

[0029] Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. In the case of no conflict, the embodiments described below and the features in the embodiments can be combined with each other.

[0030] Please refer to Figure 1 , Figure 1 A flowchart of a pose correction method of an automatic walking device provided by an embodiment of the present application is shown in the following figure. The pose correction method of the automatic walking device can be used in a terminal or a server to correct the pose of the automatic walking device. The terminal can be an automatic walking device, such as a lawn mower robot, a sweeping robot or other electronic devices; the server can be an independent server, a server cluster, a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content distribution networks (CDN), and big data and artificial intelligence platforms, etc. basic cloud computing services.

[0031] AsFigure 1 As shown, the pose correction method of the automatic walking device includes steps S101 to S105.

[0032] Step S101, in response to the control instruction of the user, the working mode of the automatic walking device is started.

[0033] Exemplarily, the control instruction of the user can be remotely sent to the automatic walking device through wireless communication technology, or triggered through the button provided on the automatic walking device. Specifically, the user can operate the application program for controlling the automatic walking device through the smart phone, so that the server sends the control instruction to the automatic walking device. Of course, it is not limited to this, which is not limited herein.

[0034] Step S102, the boundary image corresponding to the boundary position of the automatic walking device in the target working area is acquired.

[0035] Exemplarily, unlike the automatic walking device in the related art which acquires images everywhere in the target working area without distinction and uses all the acquired images to construct the map, in the map construction method provided in the technical solution of the present application, only the boundary image acquired by the automatic walking device at the boundary position of the target working area is used to construct the boundary sub-map. Specifically, the boundary position is the position where the automatic walking device needs to turn around, and the pose of the automatic walking device at the boundary position is prone to deviation. Since the boundary position is the position where the automatic walking device is prone to deviation during movement, the boundary sub-map constructed by the boundary image has a small data volume and can effectively correct the automatic walking device, wherein the boundary position is not only the boundary of the working area, but also the image area range where the boundary feature can be acquired by the image acquisition device, which can be the boundary position, and it can also be the region segment of the position point where the automatic walking device needs to turn around or the time segment of the time point corresponding to the turning position, the boundary image is not only the image when the automatic walking device is exactly at the edge, but also a plurality of frames of images continuously acquired when approaching the boundary (such as less than a certain threshold value from the boundary).

[0036] Step S103, according to the boundary image, the boundary sub-map corresponding to at least two different boundary positions is constructed.

[0037] For example, a boundary sub-map is set for each boundary position to reduce the calculation amount of subsequent deviation correction of the automatic walking device. Taking solving a bundle adjustment (BA) problem based on a Levenberg-Marquardt (LM) algorithm as an example, the calculation complexity of the LM algorithm is O(N^3), where N represents the number of images in the map. Assuming that there are 100 images in the map of the target working area, the calculation complexity is 100^3 = 1000000; if the 100 images are divided into two sub-maps, the calculation complexity is (100 / 2)^3 * 2 = 250000, and the calculation speed is increased by 4 times; if the 100 images are divided into four sub-maps, the calculation complexity is (100 / 4)^3 * 4 = 62500, and the calculation speed is increased by 16 times. As can be seen, compared with maintaining one map, dividing one map into multiple boundary sub-maps can greatly reduce the calculation complexity and improve the calculation efficiency.

[0038] In some embodiments, the boundary sub-maps corresponding to the at least two different boundary positions are constructed according to the boundary images, comprising:

[0039] The acquisition poses of the automatic walking device when acquiring each boundary image are obtained; specifically, the device pose when acquiring each boundary image can be obtained by a odometer, an IMU, a GPS / RTK module, or a visual SLAM system, and the device pose at least includes position information and orientation information of the automatic walking device.

[0040] The boundary images are classified according to the acquisition poses to obtain the boundary sub-maps corresponding to the at least two different boundary positions.

[0041] For example, the boundary images acquired near different boundary positions correspond to different boundary sub-maps, so that the boundary images are divided into multiple boundary sub-maps. All boundary images are clustered according to their acquisition poses to divide them into multiple "boundary image sets", which can assign a unique ID to each boundary sub-map, such as Map_A, Map_B, etc. It can be understood that the automatic walking device has different poses near different boundary positions. For example, the automatic walking device is located at different positions near different boundary positions, and the automatic walking device faces different directions when moving towards different boundary positions. Therefore, the boundary sub-map to which the boundary image belongs can be determined according to the pose of the automatic walking device when acquiring the boundary image, and the boundary image is updated to the boundary sub-map.

[0042] As Figure 2 shown, Figure 2 a schematic diagram of boundary images in a boundary sub-map provided by an embodiment of the present application.

[0043] As Figure 2 shown, assuming that the target working area is a 100m*100m working area, the automatic walking device collects images in the process of walking, Figure 2 the vertices of the top angles of the triangles represent the positions of the collected images, and the directions of the top angles represent the angles of the collected images. If the Map_A in the dashed box is a north boundary map, when the automatic walking device collects the boundary images in Map_A, the position is close to the north boundary of the working area, that is, the Y coordinate is close to the maximum value, for example, the boundary image in Map_A is collected near the position of Y≈99m, and the angle of orientation is θ90°. It can be understood that, since the orientation of the automatic walking device may deviate by a certain angle during walking, as long as the angle of orientation is within the deviation range of the preset angle, the collected image can be used as the boundary image in the boundary sub-map corresponding to the boundary. Assuming that the collection pose of the boundary image is represented by (X, Y, θ), the collection pose of the boundary image in Map_A may be, for example: (5, 99, 90°), (25, 99, 90°), (50, 99, 92°), (75, 99, 88°), (95, 99, 90°), etc. Of course, it is not limited thereto, and there can also be boundary images corresponding to positions of Y≈98m and Y≈97m in Map_A, which are not limited herein. In some embodiments, the collection pose includes a collection position and a collection direction, and the classification of the boundary image according to the collection pose to obtain the boundary sub-map corresponding to at least two different boundary positions comprises:

[0044] obtaining a feature direction and a feature position of each boundary sub-map;

[0045] in a case where the collection direction of the boundary image matches the feature direction and the collection position matches the feature position, determining that the boundary image corresponds to the boundary sub-map.

[0046] Exemplarily, the collection direction of the boundary image is matched with the feature direction of the boundary sub-map, that is, the collection direction is compared with the feature direction, and in a case where the included angle formed by the two is less than a preset included angle threshold, it is determined that the collection direction matches the feature direction.

[0047] Exemplarily, the collection position of the boundary image is matched with the feature position of the boundary sub-map, that is, the collection position is compared with the feature position, and in a case where the distance between the two is less than a preset distance threshold, it is determined that the collection position matches the feature position.

[0048] wherein the feature direction of the boundary sub-map can be the collection direction of the existing boundary image in the boundary sub-map, and the feature position of the boundary sub-map can be the collection position of the existing boundary image in the boundary sub-map.

[0049] Step S104, according to the boundary sub-map, verifying the image data acquired by the automatic walking device to obtain a first image pose.

[0050] For example, the boundary image in the boundary sub-map is an image collected by the automatic walking device at a position adjacent to the boundary position in the process of constructing the boundary sub-map. The automatic walking device moves based on the indication of the visual-inertial odometry (VIO) during the operation, and collects image data during the movement. According to the output result of the VIO, the automatic walking device can determine the boundary position where the current image is located, and in the corresponding boundary sub-map, select a set of boundary images closest to the current pose in spatial distance and directional distance as a comparison image set.

[0051] It can be understood that, in an ideal case, when the automatic walking device moves to a position adjacent to the boundary position during the operation, the image data collected by the automatic walking device should be consistent with the boundary image in the boundary sub-map. However, due to the error of the VIO, there will be a certain degree of deviation between the pose of the automatic walking device when actually capturing the image data and the pose when capturing the boundary image, and therefore, there will also be a certain difference between the image data acquired by the automatic walking device and the boundary image in the boundary sub-map. At this time, the image data can be verified by comparing the difference between the boundary image and the image data, and the actual first image pose of the automatic walking device when collecting the image data during the movement can be obtained.

[0052] In some embodiments, the verifying the image data acquired by the automatic walking device according to the boundary sub-map to obtain a first image pose comprises:

[0053] The image data comprises a sub-image collected by the automatic walking device within a preset time window;

[0054] Extracting feature points of the boundary sub-map, and performing position verification on the feature points in the sub-image to obtain a first image pose.

[0055] Please refer to Figure 3 , Figure 3 a schematic diagram of the first image pose provided by an embodiment of the present application.

[0056] As Figure 3 shown, Figure 3 the circle in the figure represents a 3D point, and the triangle represents the pose when the image is captured, wherein the position of the vertex of the triangle represents the position of the image capture, and the orientation of the vertex angle represents the direction of the image capture. Figure 3The solid line in the figure forms a triangle, which is the boundary image pose, i.e., the pose when the boundary image in the boundary submap is collected; the dashed line forms a triangle, which is the first image pose, i.e., the actual pose when the image data is collected. In an ideal case, the first image pose should be the same as the boundary image pose, however, there is actually a certain deviation between the first image pose and the boundary image pose, i.e. Figure 3 The gap between the first image pose and the boundary image pose is shown.

[0057] Exemplarily, the actual pose of the image data, i.e., the first image pose, can be determined by comparing the feature points in the subimage obtained by the automatic walking device and the boundary image.

[0058] Specifically, the first image pose can be determined by optimizing the following objective function:

[0059]

[0060] wherein MapPose represents the first image pose, VioPose represents the boundary image pose, represents a function of projecting a 3D point into a pixel using a camera model, given the camera intrinsic and extrinsic parameters of the automatic walking device and the given 3D point; represents the covariance matrix of the corresponding residual term, the Mahalanobis distance is in the form of. The first term is a position constraint, which is ensured to be in a real scale by a position-prior in the optimization process; the second term is in a common bundle adjustment (BA) form.

[0061] Figure 3 The thick line between the first image pose and the boundary image pose in the figure represents the position constraint therebetween, and the line between the first image pose and the plurality of 3D points represents the constraint of the back-projection error, i.e., the bundle constraint. By comparing the feature points of the actually collected image data and the image in the boundary submap (image pose verification), and optimizing the objective function to obtain a more real image pose (the first image pose), the rough historical pose information obtained based on the VIO is effectively corrected.

[0062] In step S105, the historical pose of the automatic walking device is error-corrected according to the first image pose to obtain a target pose.

[0063] Exemplarily, after the image data is verified to obtain the first image pose, since the first image pose can more accurately represent the actual pose of the automatic walking device in the movement process than the pose of the image data before verification, the historical pose recorded based on VIO is corrected through the first image pose to obtain a more accurate target pose, so as to take the more accurate target pose as the basis for the next movement of the automatic walking device.

[0064] In some embodiments, according to the first image pose, the historical pose of the automatic walking device is error-corrected to obtain a target pose, including:

[0065] A first time point matched with the first image pose is obtained, and first pose information of the first time point is obtained;

[0066] The first pose information of the first time point is error-corrected based on the first image pose to obtain a first target pose.

[0067] It can be understood that the first pose information is the historical pose recorded by VIO at the first time point, and the first image pose is the pose obtained by verifying the image data at the first time point, therefore, the accuracy of the first image pose is higher than that of the first pose information, and the first pose information is error-corrected based on the first image pose to obtain a more accurate first target pose.

[0068] Please refer to Figure 4 , Figure 4 The error correction of the historical pose according to the first image pose provided by an embodiment of the present application is shown in the schematic diagram.

[0069] Figure 4 The solid circle in the middle represents the historical pose, and the dashed circle represents the first image pose obtained in step S103.

[0070] In some embodiments, the historical pose is error-corrected gradually through the following process to obtain the target pose: based on the pose information set within the preset time window, second pose information of a second time point adjacent to the first time point is obtained, the second pose information is corrected based on the first target pose to obtain a second target pose, and the historical pose is gradually corrected through this process to obtain the target pose.

[0071] As Figure 4 shown, the historical pose includes a series of pose information arranged in time sequence, for example, the first pose information and the second pose information are adjacent. It can be understood that, due to the continuity of movement, each historical pose except the first historical pose is related to the historical pose at the last time point, therefore, each pose information in the historical pose is corrected in time sequence one by one to obtain the target pose.

[0072] In some embodiments, the step-by-step correction of the historical poses to obtain the target pose comprises:

[0073] establishing a first constraint condition between the first pose information matched at the first time point and the first image pose;

[0074] establishing a second constraint condition between the first pose information and the second pose information adjacent at the first time point;

[0075] error correction of the historical poses according to the first constraint condition and the second constraint condition to obtain the target pose.

[0076] As shown in Figure 4 , the constraint of the first pose information includes the constraint of the second pose information adjacent to the first pose information, i.e., the first constraint condition, and the constraint of the first image information verified in step S103, i.e., the second constraint condition. Among them, Figure 4 the connection between each historical pose represents the first constraint condition, and the connection between each historical pose and the first image pose represents the second constraint condition.

[0077] For example, the error correction of the historical poses can be achieved by optimizing the following objective function:

[0078]

[0079] Among them, the meaning of is the inverse of , the meaning of which is , and the formula is the same as the similar meaning; represents the first pose information, represents the second pose information adjacent to the first pose information, represents the first image pose. The first term in the objective function represents the constraint of the second pose information on the first pose information, i.e., the second constraint condition; the second term represents the constraint of the first image pose on the first pose information, i.e., the first constraint condition.

[0080] In some embodiments, the automatic walking device enters the same boundary region at least twice during the first driving operation in the working mode, and the positions of the at least two times entering the same boundary region do not coincide in the extension direction of the boundary region.

[0081] Please refer to Figure 5 , Figure 5 for the first driving operation motion trajectory diagram provided by an embodiment of the present application.

[0082] As shown in Figure 5As shown, the pose correction provided by the embodiments of the present application is based on the boundary sub-maps corresponding to the boundary positions, and the boundary region corresponding to the boundary sub-maps should be a region that the automatic walking device needs to repeatedly enter during the first driving operation, for example Figure 5 Since the automatic walking device enters the same boundary region at least twice, one boundary sub-map can be used for pose correction at least twice during the movement of the automatic walking device, thereby improving the utilization rate of the boundary sub-map.

[0083] It can be understood that the boundary position is a position where the automatic walking device needs to turn around during movement, and is a position where the pose is prone to error. The pose error can be effectively reduced by performing correction in the boundary region near the boundary position.

[0084] The path through which the automatic walking device enters the same boundary region at least twice is different, and thus the positions through which the automatic walking device enters the same boundary region at least twice do not coincide in the extension direction of the boundary region.

[0085] It can be understood that the movement trajectory of the automatic walking device during the first driving operation in the working mode is not limited to Figure 5 the movement path shown in Figure 5 the movement trajectory shown in is only an example, and the target working region can have other shapes in actual operation. The movement trajectory of the automatic walking device is adapted to the shape of the target working region. For example, when the target working region has a circular or elliptical shape, the path in the movement trajectory of the automatic walking device can be arc-shaped.

[0086] In some embodiments, the driving path of the first driving operation is arc-shaped.

[0087] As shown in Figure 5 , the automatic walking device reciprocally moves along the arc-shaped path in the target working region, so that the movement trajectory covers the target working region as much as possible. Specifically, the automatic walking device moves northward to one of the boundary positions of the target working region, turns around to change the direction, moves southward to another boundary position of the target working region, and repeats this process until the movement trajectory covers the entire target working region.

[0088] Please refer to Figure 6 , Figure 6 for the movement trajectory of the automatic walking device provided in the related art of the present application.

[0089] The actual movement trajectory of the automatic walking device can be as shown in Figure 4The offset, for example, due to the cumulative error generated by the automatic walking device during movement, is usually difficult to ensure that the movement trajectory is completely parallel, and is easy to cause the angles of different paths to be different, resulting in some positions in the target working area being unable to be covered. Taking a mowing robot as an example, Figure 6 The black area in the middle is the missed area of the mowing operation.

[0090] In order to avoid the above situation, the embodiment of the present application constructs a boundary sub-map for the boundary position in the target working area before the automatic walking device turns around, and corrects the movement trajectory of the automatic walking device according to the boundary sub-map before each turn, avoiding the situation that Figure 6 The automatic walking device continuously generates and accumulates errors during movement, resulting in larger and larger errors. Through the pose correction method provided by the embodiment of the present application, the actual movement trajectory of the automatic walking device corresponds to the Figure 5 movement trajectory as much as possible, avoiding the situation that Figure 6 the movement trajectory, improving the aesthetics of the movement trajectory, reducing the missed area in the target working area, and taking the mowing robot as an example, reducing the missed area of the mowing robot in the mowing operation.

[0091] Please refer to Figure 7 , Figure 7 for the structure schematic diagram of the automatic walking device provided by an embodiment of the present application.

[0092] As shown in Figure 7 , the embodiment of the present application also provides an automatic walking device, which comprises:

[0093] a body 10;

[0094] a travel module 20 for driving the body to travel;

[0095] a working module 30 arranged on the body and used for mowing the position where the automatic walking device is located;

[0096] a collection module (not shown in the figure) at least used for collecting images of the environment where the automatic walking device is located and collecting the pose of the automatic walking device;

[0097] a controller (not shown in the figure) connected to the travel module and the collection module, used for executing the pose correction method of the automatic walking device according to any one of the embodiments of the present application.

[0098] For example, the automatic walking device provided by the embodiment of the present application can be used to perform mowing operation during movement, of course, it is not limited thereto, and the automatic walking device provided by the embodiment of the present application can also perform cleaning, snow sweeping, leaf blowing and other operations, which are not limited herein.

[0099] The collection module of the automatic walking device is configured to collect image data of an environment where the robot is located and collect a pose. For example, the collection module can include a visible light camera or an infrared light camera configured to collect image data, an inertial measurement module configured to obtain a collection direction, and a real-time dynamic positioning module configured to obtain a collection position. Of course, the collection module is not limited to this, and can be replaced by other devices or include more components, which are not limited herein.

[0100] For example, the controller is configured to implement the map construction method provided in the embodiments of the present application to obtain a boundary sub-map, and correct the movement of the automatic walking device based on the boundary sub-map.

[0101] The embodiments of the present application also provide a computer readable storage medium, which stores a computer program. The computer program includes program instructions. The method implemented by the program instructions can refer to the embodiments of the pose correction method of the automatic walking device.

[0102] The computer readable storage medium can be an internal storage unit of the computer device, such as a hard disk or a memory of the computer device. The computer readable storage medium can also be an external storage device of the computer device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc.

[0103] It should be understood that the terms used herein in the specification and the appended claims are merely used for the purpose of describing particular embodiments and are not intended to limit the present application. As used in the specification and the appended claims, the singular forms “a,” “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise.

[0104] It should also be understood that the term “and / or” as used herein in the specification and in the claims, is intended to mean one or the other of the listed terms, as well as both, and includes all possible combinations of the listed terms. It should be noted that, as used in the specification and the appended claims, the terms “comprise” “comprising” or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article or apparatus. Without further limitation, an element preceded by “comprises a” does not exclude the existence of additional identical elements in the process, method, article or apparatus that comprises the element.

[0105] The above-mentioned sequence numbers of the embodiments of the present application are only for description, and do not represent advantages or disadvantages of the embodiments. The above describes only the specific implementation of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical range disclosed by the present application, and these modifications or replacements should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A pose correction method for an automatic walking device, characterized by, The method comprises: in response to a user's control instruction, starting a working mode of the automatic walking device; acquiring a boundary image corresponding to a boundary position of the automatic walking device in a target working area; constructing a boundary sub-map corresponding to at least two different boundary positions according to the boundary image; verifying image data acquired by the automatic walking device according to the boundary sub-map to obtain a first image pose; correcting an error of a historical pose of the automatic walking device according to the first image pose to obtain a target pose.

2. The method of claim 1, wherein, The verification of the image data acquired by the automatic walking device according to the boundary sub-map to obtain the first image pose comprises that the image data comprises a sub-image collected by the automatic walking device within a preset time window; extracting a feature point of the boundary sub-map and performing position verification on a feature point in the sub-image to obtain the first image pose.

3. The method of claim 1, wherein, The correction of the error of the historical pose of the automatic walking device according to the first image pose to obtain the target pose comprises: acquiring a first time point matched with the first image pose and acquiring first pose information of the first time point; correcting an error of the first pose information of the first time point based on the first image pose to obtain a first target pose.

4. The method of claim 3, wherein, The historical pose is corrected gradually through the process to obtain the target pose.

5. The method of claim 4, wherein, The gradual correction of the historical pose to obtain the target pose comprises: establishing a first constraint condition between the first pose information matched with the first time point and the first image pose; establishing a second constraint condition between the first pose information and the second pose information adjacent to the first time point; correcting an error of the historical pose according to the first constraint condition and the second constraint condition to obtain the target pose.

6. The method of claim 1, wherein, The automatic walking device enters the same boundary area at least twice during a first driving operation in the working mode, and positions of the at least two times of entering the same boundary area do not coincide in an extension direction of the boundary area.

7. The method of claim 6, wherein, The driving path of the first driving operation is in an arc shape.

8. The method of claim 1, wherein, The construction of the boundary sub-map corresponding to at least two different boundary positions according to the boundary image comprises: acquiring a collection pose of the automatic walking device when each boundary image is collected; classifying the boundary images according to the collection pose to obtain the boundary sub-map corresponding to at least two different boundary positions.

9. The method of claim 8, wherein, The collection pose comprises a collection position and a collection direction, and the classification of the boundary images according to the collection pose to obtain the boundary sub-map corresponding to at least two different boundary positions comprises: acquiring a feature direction and a feature position of each boundary sub-map; In a case where the acquisition direction of the boundary image matches the feature direction, and the acquisition position matches the feature position, it is determined that the boundary image corresponds to the boundary sub-map.

10. An automatic walking apparatus characterized by comprising: The device comprises: a body; a driving module for driving the body to move; a working module arranged on the body and configured to perform a mowing operation on a position where the automatic walking device is located; an acquisition module configured to at least acquire an image of an environment where the automatic walking device is located and to acquire a pose of the automatic walking device; a controller connected to the driving module and the acquisition module and configured to execute the pose rectification method of the automatic walking device according to any one of claims 1-9.

11. A computer storage medium, characterized in that The computer storage medium stores a computer program, and the computer program is executed by a processor to implement the pose rectification method of the automatic walking device according to any one of claims 1-9. The computer storage medium stores a computer program, and the computer program is executed by a processor to implement the pose rectification method of the automatic walking device according to any one of claims 1-9.

Images