WO2021129071A1

WO2021129071A1 - Robot, positioning method, and computer readable storage medium

Info

Publication number: WO2021129071A1
Application number: PCT/CN2020/121655
Authority: WO
Inventors: 赵仕伟; 陈超
Original assignee: 北京极智嘉科技股份有限公司
Priority date: 2019-12-25
Filing date: 2020-10-16
Publication date: 2021-07-01
Also published as: CN113031582A

Abstract

A robot, a positioning method, and a computer readable storage medium. The method comprises: first, a robot photographs a target image comprising one or more positioning markers (step 610); next, on the basis of a first position coordinate of a key point corresponding to each positioning marker in the target image, and first attitude information of each positioning marker in a geographic coordinate system (step 620), determining multiple pieces of second attitude information of the robot in the geographic coordinate system (step 630); and finally, determining target attitude information of the robot in the geographic coordinate system on the basis of the second attitude information corresponding to each positioning marker (step 640). According to the method, the attitude information of the robot in the geographic coordinate system can be accurately determined on the basis of position information of multiple positioning markers.

Description

Robot, positioning method and computer readable storage medium

This application claims the priority of a Chinese patent filed with the Chinese Patent Office, the application number is 201911358248.4, and the application name is "robots, positioning methods, and computer-readable storage media" on December 25, 2019, the entire contents of which are incorporated herein by reference. Applying.

Technical field

This application relates to the field of positioning and image processing, and specifically, to a robot, a positioning method, and a computer-readable storage medium.

Background technique

With the rapid development of artificial intelligence, more and more automated devices have brought great convenience to people's lives. For example, robots are gradually being used in all walks of life with their automation and intelligence.

In the process of using and controlling the robot, it is first necessary to determine the pose of the robot. Based on the pose of the robot and the control target of the robot, the next action of the robot can be determined and controlled. Therefore, a technical solution is needed to accurately determine the pose of the robot.

Summary of the invention

In view of this, this application provides at least a robot, a positioning method, and a computer-readable storage medium.

In the first aspect, the present application provides a robot including a camera and a processor; the processor includes an analysis processing module, an image coordinate determination module, a pose transformation module, and a target pose determination module;

The camera is set to capture a target image including one or more positioning landmarks;

The analysis processing module is configured to determine the first pose information of each of the positioning landmarks in the geographic coordinate system;

The image coordinate determining module is configured to determine the first position coordinate of the key point corresponding to each of the positioning markers in the target image;

The pose transformation module is configured to, for each positioning landmark, determine the second position of the robot in the geographic coordinate system based on the first position coordinates and the first pose information corresponding to the positioning landmark. Pose information

The target pose determination module is configured to determine the target pose information of the robot in the geographic coordinate system based on the second pose information corresponding to each positioning landmark.

In a possible implementation manner, the analysis processing module is further configured to determine the second position coordinates of the key point corresponding to the positioning marker in the marker coordinate system;

The pose transformation module is specifically set to:

Determining the third pose information of the robot relative to the positioning marker based on the first position coordinates and the second position coordinates corresponding to the positioning marker;

Based on the third pose information and the first pose information of the positioning marker in the geographic coordinate system, the second pose information of the robot in the geographic coordinate system is determined.

In a possible implementation manner, the target pose determination module is specifically set to:

Determining the reprojection error corresponding to each of the second pose information;

Regarding the minimum sum of all the reprojection errors as the target, adjust each second pose information;

Based on each second posture information after adjustment, the target posture information is determined.

In a possible implementation manner, when the target pose determination module determines the target pose information based on each second pose information after adjustment, the specific settings are as follows:

Determine the reprojection error corresponding to each second pose information after adjustment;

The adjusted second pose information corresponding to the smallest reprojection error is used as the target pose information.

In a possible implementation manner, the analysis processing module is specifically configured to:

Screening the positioning marker from the target image;

Determining the identification information of each of the positioning markers;

Based on the identification information of each positioning landmark, the first pose information of each positioning landmark in the geographic coordinate system is determined.

In a possible implementation, the location marker is a two-dimensional code;

When the analysis processing module determines the identification information of each of the positioning markers, it is specifically set as follows:

Decode each QR code separately to obtain the identification information of each QR code

In a possible implementation manner, when the analysis processing module selects the positioning marker from the target image, the specific setting is as follows:

Extracting contour information of each object from the target image;

Determine the shape of each object in the target image based on the contour information of each object;

Based on the shape of each object in the target image, it is determined whether each object is the positioning marker.

In a possible implementation manner, when the analysis processing module determines whether each object is the positioning marker based on the shape of each object in the target image, the specific settings are as follows:

Determine the shape of the front view of each object based on the shape of each object in the target image;

Based on the shape of the front view of each object, it is determined whether each object is the positioning marker.

In the second aspect, this application discloses a positioning method, including:

Obtain a target image taken by the robot including one or more positioning markers;

Determining the first pose information of each of the positioning landmarks in the geographic coordinate system and the first position coordinates of the key points corresponding to each of the positioning landmarks in the target image;

For each positioning landmark, determine the second pose information of the robot in the geographic coordinate system based on the first position coordinates and the first pose information corresponding to the positioning landmark;

Based on the second pose information corresponding to each positioning landmark, determine the target pose information of the robot in the geographic coordinate system.

In a possible implementation manner, the determining the second pose information of the robot in the geographic coordinate system based on the first position coordinates and the first pose information corresponding to the positioning landmark includes :

Acquiring the second position coordinates of the key point corresponding to the positioning marker in the marker coordinate system;

In a possible implementation manner, the determining the target pose information of the robot in the geographic coordinate system based on the second pose information corresponding to each positioning landmark includes:

In a possible implementation manner, the determining the first pose information of each of the positioning landmarks in a geographic coordinate system includes:

Screening the positioning marker from the target image;

Determining the identification information of each of the positioning markers;

In a possible implementation, the location marker is a two-dimensional code;

The determining the identification information of each of the positioning markers includes:

Each two-dimensional code is decoded separately to obtain the identification information of each two-dimensional code.

In a possible implementation manner, the screening of the positioning markers from the target image includes:

Extracting contour information of each object from the target image;

In a possible implementation manner, the determining whether each object is the positioning marker based on the shape of each object in the target image includes:

In a third aspect, the present application also provides a computer-readable storage medium with a computer program stored on the computer-readable storage medium, and the computer program executes the steps of the above positioning method when the computer program is run by a processor.

The present application provides a robot, a positioning method, and a computer-readable storage medium. The robot first takes a target image including multiple positioning markers; then, based on the key point corresponding to each positioning marker in the target image A position coordinate and the first pose information of each positioning landmark in the geographic coordinate system determine the multiple second pose information of the robot in the geographic coordinate system; finally, based on the second position corresponding to each positioning landmark Pose information, to determine the target pose information of the robot in the geographic coordinate system. The above technical solution is able to more accurately determine the pose information of the robot in the geographic coordinate system based on the position information of multiple positioning landmarks.

Description of the drawings

In order to more clearly describe the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings that need to be used in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application, and therefore do not It should be regarded as a limitation of the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative work.

Figure 1 shows a schematic structural diagram of a robot provided by an embodiment of the present application;

FIG. 2 shows a schematic diagram of an image obtained after preprocessing the target image in an embodiment of the present application;

FIG. 3 shows a schematic diagram of an image obtained after polygonal approximation is performed on a preprocessed target image in an embodiment of the present application;

Fig. 4 shows a front view obtained after performing affine transformation on a parallelogram in an embodiment of the present application;

FIG. 5 shows a schematic diagram of an image obtained by performing grid division on positioning markers obtained by screening in an embodiment of the present application;

Fig. 6 shows a flowchart of a positioning method provided by an embodiment of the present application.

Detailed ways

In order to make the purpose, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions in the embodiments of this application will be described clearly and completely in conjunction with the drawings in the embodiments of this application. It should be understood that this application is attached The drawings are only for the purpose of illustration and description, and are not used to limit the protection scope of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. The flowchart used in this application shows operations implemented according to some embodiments of this application. It should be understood that the operations of the flowchart may be implemented out of order, and steps without logical context may be reversed in order or implemented at the same time. In addition, under the guidance of the content of this application, those skilled in the art can add one or more other operations to the flowchart, or remove one or more operations from the flowchart.

In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application generally described and shown in the drawings herein may be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of the application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work shall fall within the protection scope of the present application.

It should be noted that the term "including" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but it does not exclude the addition of other features.

Based on the current needs for robot positioning and the lack of accuracy in current robot positioning, this application provides a robot, a positioning method, and a computer-readable storage medium. The robot first photographs a target including multiple positioning markers. Image; After that, based on the first position coordinates of the key points corresponding to each positioning landmark in the target image and the first pose information of each positioning landmark in the geographic coordinate system, determine the number of robots in the geographic coordinate system Second pose information; Finally, based on the second pose information corresponding to each positioning marker, determine the target pose information of the robot in the geographic coordinate system. The present application can determine the pose information of the robot in the geographic coordinate system more accurately based on the position information of multiple positioning landmarks.

As shown in FIG. 1, the present application provides a robot, including a camera 110, a processor 120; the processor 120 includes an analysis processing module 1201, an image coordinate determination module 1202, a pose transformation module 1203, and a target pose determination module 1204.

The camera 110 is configured to capture a target image including one or more positioning landmarks.

The analysis processing module 1201 is configured to determine the first pose information of each of the positioning landmarks in the geographic coordinate system.

The image coordinate determining module 1202 is configured to determine the first position coordinate of the key point corresponding to each positioning marker in the target image.

The pose transformation module 1203 is configured to, for each positioning landmark, determine the first position of the robot in the geographic coordinate system based on the first position coordinates and the first pose information corresponding to the positioning landmark. Two pose information.

The target pose determination module 1204 is configured to determine the target pose information of the robot in the geographic coordinate system based on the second pose information corresponding to each positioning marker.

The aforementioned pose information includes the position coordinates of the object in the corresponding coordinate system and the rotation angle of the object in the corresponding coordinate system.

The target image taken by the robot with the camera includes multiple positioning markers, and these positioning markers are used to determine the pose information of the robot in the geographic coordinate system. In practical applications, the positioning marker may be a two-dimensional code set on the ground, and the analysis processing module 1201 decodes the two-dimensional code in the image to obtain identification information of the positioning marker. After that, the analysis processing module 1201 can determine the first pose information of the positioning marker in the geographic coordinate system by using the identification information of the positioning marker.

In specific implementation, one or more of the above-mentioned positioning markers can be deployed in advance on one or more fixed objects of the ground, shelf sides, ceiling, and walls; the deployment position is that the robot can be photographed by the camera during the movement. There is no limit to the shooting direction of the camera. For example, you can shoot toward the front (the side of the shelf or the wall), you can shoot upward (the ceiling), you can shoot downward (the ground), or you can shoot toward the side (side of the shelf) Or wall). You can install multiple cameras on the robot to shoot in different directions. Regardless of which fixture is used for the deployment of the positioning marker, the above positioning method provided by the embodiments of the present disclosure can be used, because the pose of the positioning marker in the geographic coordinate system is predetermined when the positioning marker is deployed Therefore, based on the pose information of the positioning landmark in the image coordinate system corresponding to the target image taken by the robot, and the pose information of the positioning landmark in the geographic coordinate system, the robot's target in the geographic coordinate system can be determined For pose information, please refer to the following description for details.

Because the positioning marker is set in advance, after the positioning marker is set, the first pose information of the positioning marker in the geographic coordinates has been determined and known. After each positioning marker is set, the first pose information of each positioning marker and the identification information of each positioning marker can be respectively established a mapping relationship and stored in the memory of the robot. After the analysis processing module 1201 obtains the identification information of the positioning landmark in the target image, it can determine the first pose information of the positioning landmark in the geographic coordinate system based on the foregoing mapping relationship.

Before the analysis processing module 1201 analyzes the positioning markers and obtains the identification information, it first needs to screen the positioning markers from the target image. Specifically, the analysis processing module 1201 uses the following steps to screen positioning markers from the target image:

Step 1: Extract contour information of each object from the target image.

The analysis processing module 1201 first needs to preprocess the target image before extracting the contour information of each object from the target image. For example, the target image can be binarized. The image obtained after quantization.

After preprocessing the target image, the analysis processing module 1201 extracts contour information of each object from the obtained image.

Step 2: Determine the shape of each object in the target image based on the contour information of each object.

After extracting the contour information of each object, the analysis processing module 1201 respectively performs polygonal approximation on each object based on the contour information of each object to obtain the shape of each object in the target image. Figure 3 shows the image obtained after polygonal approximation of the preprocessed target image.

After determining the shape of each object in the target image, the shape can be matched with the shape of the pre-stored positioning marker. If the direct matching is successful, it can be determined that the object is a positioning marker. In actual implementation, since the shooting angle of the camera may be in any direction, and the shape of the pre-stored positioning marker is generally the shape of the front view, the following step 3 can be performed at this time, first determine the shape of the front view of the object .

Step 3: Determine the shape of the front view of each object based on the shape of each object in the target image.

After the analytical processing module 1201 determines the shape of each object in the target image, it sorts the corners of each shape and performs radial transformation to obtain the front view of each shape, that is, determine the front view of each object shape. Figure 4 shows the front view obtained after performing affine transformation on a parallelogram.

Step 4: Based on the shape of the front view of each object, determine whether each object is the positioning marker.

After determining the shape of the front view of each object, the analysis processing module 1201 filters the positioning markers based on the shape of the front view of the object. For example, in the case where the positioning marker is a two-dimensional code, the analysis processing module 1201 selects objects whose front view is square as the positioning marker.

After the analysis processing module 1201 filters the positioning markers from the target image, it divides the positioning markers in the target image into grids, and then performs a decoding operation based on the positioning markers after the grid is divided to obtain the positioning markers Identification information. Figure 5 shows the image obtained by meshing the selected positioning markers.

The image coordinate determination module 1202 analyzes and processes the target image, and determines the first position coordinate of the key point corresponding to each positioning marker in the target image. The first position coordinate here is the coordinate of the key point corresponding to the positioning marker in the robot coordinate system.

The pose transformation module 1203 can determine the pose of the robot in the geographic coordinate system based on the first position coordinates of the key points corresponding to the positioning markers in the robot coordinate system and the first pose information of the positioning markers in the geographic coordinate system. Information, that is, the above-mentioned second pose information.

Specifically, the pose transformation module 1203 may use the following steps to determine the second pose information of the robot in the geographic coordinate system:

Step 1: Determine the third pose information of the robot relative to the positioning marker based on the first position coordinates and the second position coordinates corresponding to the positioning marker.

Before the pose transformation module 1203 performs this step, the analysis processing module 1201 first needs to determine the second position coordinates of the key points corresponding to the positioning markers in the marker coordinate system. The position coordinates of the positioning marker in the marker coordinate system have been determined and known. The identification information of the positioning marker is preset with a mapping relationship with its position coordinates in the marker coordinate system, and is stored in the memory of the robot. After decoding the identification information of the positioning marker, the analysis processing module 1201 can determine the position coordinates of the positioning marker in the marker coordinate system, that is, the second position coordinates, in combination with the foregoing mapping relationship.

After determining the second position information of the positioning marker in the marker coordinate system, the pose transformation module 1203 is based on the first position coordinates of the key point corresponding to the positioning marker in the robot coordinates and the key point corresponding to the positioning marker The second position coordinates in the marker coordinate system can determine the pose information of the robot relative to the positioning marker in the marker coordinate system, that is, the above-mentioned third pose information.

Both the first position coordinates and the second position coordinates may include the coordinates of at least 3 non-collinear points on the positioning marker.

Step 2: Determine the second pose information of the robot in the geographic coordinate system based on the third pose information and the first pose information of the positioning landmark in the geographic coordinate system.

The pose transformation module 1203 determines the robot's first pose in the geographic coordinate system based on the third pose information of the robot relative to the positioning landmark in the landmark coordinate system and the first pose information of the positioning landmark in the geographic coordinate system. Two pose information.

After obtaining multiple second pose information of the robot in the geographic coordinate system, the target pose determination module 1204 can use the following steps to determine the target pose information of the robot in the geographic coordinate system:

Step 1: Determine the reprojection error corresponding to each of the second pose information.

The target pose determination module 1204 projects the positioning marker and the pose corresponding to the second pose information of the positioning marker onto the same image, and then determines the pose corresponding to each second pose information in the image. The error between the projection on the image and the projection of the positioning marker on the image is to determine the reprojection error corresponding to each second pose information.

Step 2: Regarding the minimum sum of all the reprojection errors as the target, adjust each second pose information.

Here, the target pose determination module 1204 calculates the sum of all reprojection errors, and adjusts each second pose information with the minimum sum as the target.

Step 3: Determine the target pose information based on each second pose information after adjustment.

Here, the target pose determination module 1204 determines the reprojection error corresponding to each adjusted second pose information after finishing the adjustment of the pose information; and corresponds the adjusted second pose to the smallest reprojection error The information is used as the target pose information.

After the target pose determination module 1204 adjusts each second pose information, it may also calculate the average value of the adjusted second pose, and use the obtained average value as the target pose information.

The above solution can be used as an independent positioning solution to be applied to the positioning during the movement of the robot. It can also be implemented in combination with other positioning schemes, for example, it can be used to determine the initial positioning pose of other positioning schemes, can be used to perform pose calibration during the positioning process, and can also be used to perform pose relocation. For example, the initial positioning pose information of the robot can be obtained first based on the positioning method of the embodiment of the present disclosure, and then the inertial measurement unit (IMU) of the robot can be used to determine the positioning pose of the robot in real time, and in the real-time positioning process , Periodically adopt the solution of the embodiments of the present disclosure to determine the pose of the robot to calibrate the real-time positioning pose of the robot. It is also possible to implement the present disclosure when the measurement information of the IMU cannot be obtained or the measurement information of the IMU is unstable. The scheme of the example performs robot relocation. The above process can be applied to the process of visual real-time positioning and mapping (Simultaneous Localization and Mapping, SLAM).

Corresponding to the above-mentioned robot, the embodiment of the present application also provides a positioning method, which is applied to the above-mentioned robot, and is used to realize the positioning of the above-mentioned robot, and can achieve the same or similar beneficial effects, so the repeated parts will not be repeated here. .

As shown in FIG. 6, the positioning method provided by the embodiment of the present application may include the following steps:

S610. Obtain a target image that includes one or more positioning markers taken by the robot.

S620: Determine the first pose information of each of the positioning landmarks in the geographic coordinate system and the first position coordinates of the key points corresponding to each of the positioning landmarks in the target image.

S630. For each positioning landmark, determine the second pose information of the robot in the geographic coordinate system based on the first position coordinates and the first pose information corresponding to the positioning landmark.

S640: Determine the target pose information of the robot in the geographic coordinate system based on the second pose information corresponding to each positioning landmark.

In some embodiments, the determining the second pose information of the robot in the geographic coordinate system based on the first position coordinates and the first pose information corresponding to the positioning landmark includes:

In some embodiments, the determining the target pose information of the robot in the geographic coordinate system based on the second pose information corresponding to each positioning landmark includes:

In some embodiments, the determining the first pose information of each of the positioning landmarks in a geographic coordinate system includes:

Screening the positioning marker from the target image;

Determining the identification information of each of the positioning markers;

In some embodiments, the location marker is a two-dimensional code;

In some embodiments, the screening of the positioning markers from the target image includes:

Extracting contour information of each object from the target image;

The embodiment of the present application also provides a computer program product corresponding to the above method, which includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the method in the previous method embodiment. For specific implementation, see The method embodiment will not be repeated here.

The above description of the various embodiments tends to emphasize the differences between the various embodiments, and the same or similarities can be referred to each other. For the sake of brevity, the details are not repeated herein.

Those skilled in the art can clearly understand that, for convenience and concise description, the specific working process of the system and device described above can refer to the corresponding process in the method embodiment, which will not be repeated in this application. In the several embodiments provided in this application, it should be understood that the disclosed system, device, and method can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there may be other divisions in actual implementation. For example, multiple modules or components may be combined or It can be integrated into another system, or some features can be ignored or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some communication interfaces, devices or modules, and may be in electrical, mechanical or other forms.

The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

In addition, the functional units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.

If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solution of the present application essentially or the part that contributes to the existing technology or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, ROM, RAM, magnetic disk or optical disk and other media that can store program codes.

The above are only specific implementations of this application, but the protection scope of this application is not limited to this. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and they should all be covered Within the scope of protection of this application. Therefore, the protection scope of this application shall be subject to the protection scope of the claims.

Claims

A robot, characterized in that it includes a camera and a processor; the processor includes an analysis processing module, an image coordinate determination module, a pose transformation module, and a target pose determination module;

The camera is configured to shoot a target image including one or more positioning landmarks;

The analysis processing module is configured to determine the first pose information of each of the positioning landmarks in the geographic coordinate system;

The image coordinate determining module is configured to determine the first position coordinate of the key point corresponding to each of the positioning markers in the target image;

The pose transformation module is configured to, for each positioning landmark, determine the second position of the robot in the geographic coordinate system based on the first position coordinates and the first pose information corresponding to the positioning landmark. Pose information

The target pose determination module is configured to determine the target pose information of the robot in the geographic coordinate system based on the second pose information corresponding to each positioning landmark.
The robot according to claim 1, wherein the analysis processing module is further configured to determine the second position coordinates of the key point corresponding to the positioning marker in the marker coordinate system;

The pose transformation module is specifically set to:

Determining the third pose information of the robot relative to the positioning marker based on the first position coordinates and the second position coordinates corresponding to the positioning marker;

Based on the third pose information and the first pose information of the positioning marker in the geographic coordinate system, the second pose information of the robot in the geographic coordinate system is determined.
The robot according to claim 1 or 2, wherein the target pose determination module is specifically set to:

Determining the reprojection error corresponding to each of the second pose information;

Regarding the minimum sum of all the reprojection errors as the target, adjust each second pose information;

Based on each second posture information after adjustment, the target posture information is determined.
The robot according to claim 3, wherein when the target pose determination module determines the target pose information based on each second pose information after adjustment, the specific settings are as follows:

Determine the reprojection error corresponding to each second pose information after adjustment;

The adjusted second pose information corresponding to the smallest reprojection error is used as the target pose information.
The robot according to any one of claims 1 to 4, wherein the analysis processing module is specifically configured to:

Screening the positioning marker from the target image;

Determining the identification information of each of the positioning markers;

Based on the identification information of each positioning landmark, the first pose information of each positioning landmark in the geographic coordinate system is determined.
The robot according to claim 5, wherein the positioning marker is a two-dimensional code;

When the analysis processing module determines the identification information of each of the positioning markers, it is specifically set as follows:

Each two-dimensional code is decoded separately to obtain the identification information of each two-dimensional code.
The robot according to claim 5 or 6, characterized in that, when the analysis processing module selects the positioning marker from the target image, the specific setting is as follows:

Extracting contour information of each object from the target image;

Determine the shape of each object in the target image based on the contour information of each object;

Based on the shape of each object in the target image, it is determined whether each object is the positioning marker.
The robot according to claim 7, wherein when the analysis processing module determines whether each object is the positioning marker based on the shape of each object in the target image, the specific settings are as follows:

Determine the shape of the front view of each object based on the shape of each object in the target image;

Based on the shape of the front view of each object, it is determined whether each object is the positioning marker.
A positioning method, characterized in that it comprises:

Obtain a target image taken by the robot including one or more positioning markers;

Determining the first pose information of each of the positioning landmarks in the geographic coordinate system and the first position coordinates of the key points corresponding to each of the positioning landmarks in the target image;

For each positioning landmark, determine the second pose information of the robot in the geographic coordinate system based on the first position coordinates and the first pose information corresponding to the positioning landmark;

Based on the second pose information corresponding to each positioning landmark, determine the target pose information of the robot in the geographic coordinate system.
The positioning method according to claim 9, wherein the first position coordinates and the first pose information corresponding to the positioning marker are used to determine the second position of the robot in the geographic coordinate system. Pose information, including:

Acquiring the second position coordinates of the key point corresponding to the positioning marker in the marker coordinate system;

Determining the third pose information of the robot relative to the positioning marker based on the first position coordinates and the second position coordinates corresponding to the positioning marker;

Based on the third pose information and the first pose information of the positioning marker in the geographic coordinate system, the second pose information of the robot in the geographic coordinate system is determined.
The positioning method according to claim 9 or 10, wherein the determining the target pose information of the robot in the geographic coordinate system based on the second pose information corresponding to each positioning marker includes :

Determining the reprojection error corresponding to each of the second pose information;

Regarding the minimum sum of all the reprojection errors as the target, adjust each second pose information;

Based on each second posture information after adjustment, the target posture information is determined.
The positioning method according to any one of claims 9 to 11, wherein the determining the first pose information of each of the positioning markers in a geographic coordinate system comprises:

Screening the positioning marker from the target image;

Determining the identification information of each of the positioning markers;

Based on the identification information of each positioning landmark, the first pose information of each positioning landmark in the geographic coordinate system is determined.
The positioning method according to claim 12, wherein the positioning marker is a two-dimensional code;

The determining the identification information of each of the positioning markers includes:

Each two-dimensional code is decoded separately to obtain the identification information of each two-dimensional code.
The positioning method according to claim 12 or 13, wherein the screening of the positioning markers from the target image comprises:

Extracting contour information of each object from the target image;

Determine the shape of each object in the target image based on the contour information of each object;

Based on the shape of each object in the target image, it is determined whether each object is the positioning marker.
The positioning method according to claim 14, wherein the determining whether each object is the positioning marker based on the shape of each object in the target image comprises:

Determine the shape of the front view of each object based on the shape of each object in the target image;

Based on the shape of the front view of each object, it is determined whether each object is the positioning marker.
A computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and the computer program executes the positioning method according to any one of claims 9-15 when the computer program is run by a processor.