CN113256715B - Positioning method and device for robot - Google Patents

Abstract

The embodiments of the present disclosure disclose a method and device for positioning a robot. A specific implementation of the method includes: in response to receiving a current frame image collected by the robot, obtaining a reference frame image matching the current frame image from a pre-established target map, wherein the reference frame image includes at least one view mark and identification information of the view mark, and the identification information includes edge information of the view mark and a reference pose of the robot collecting the reference frame image; determining a target view mark in the current image frame, performing edge extraction on the determined target view mark to obtain an extracted edge image of the target view mark; determining the current pose of the robot based on the identification information of the target view mark in the reference frame image and the extracted edge image of the target view mark in the current frame image. This implementation uses the edge image of the view mark in the image to determine the current pose of the robot, thereby improving the accuracy of the robot positioning.

Description

Robot positioning method and device

Technical Field

Embodiments of the present disclosure relate to the field of computer technology, and more particularly to a method and device for positioning a robot.

Background technique

Visual SLAM is one of the current hot topics in SLAM research. Robots can use visual SLAM (Simultaneous Localization And Mapping) technology to concurrently build maps and locate. In visual SLAM, the robot can use visual loop detection to compare the image of the current scene with all the images in the established map to identify the places the robot has been to. Then, the robot is located through methods such as feature point matching, thereby eliminating the accumulated errors generated during the positioning and mapping process.

In the related art, when the lighting is constant and the image acquisition scene is unchanged or changes little, the map established by visual SLAM can be reused and the positioning result is accurate. However, in the case of large lighting changes and dynamic scenes, the accuracy of robot positioning results is poor.

Summary of the invention

The embodiments of the present disclosure provide a method and device for positioning a robot.

In a first aspect, an embodiment of the present disclosure provides a robot positioning method, the method comprising: in response to receiving a current frame image captured by the robot, acquiring a reference frame image matching the current frame image from a pre-established target map, wherein the reference frame image comprises at least one view mark and identification information of the view mark, the identification information comprises edge information of the view mark and a reference pose of the robot when capturing the reference frame image; determining a target view mark in the current image frame, performing edge extraction on the determined target view mark to obtain an extracted edge image of the target view mark, wherein the reference frame image comprises the target view mark; determining the current pose of the robot based on the identification information of the target view mark in the reference frame image and the extracted edge image of the target view mark in the current frame image.

In some embodiments, in response to receiving a current frame image captured by a robot, a reference frame image matching the current frame image is obtained from a pre-established target map, including: in response to receiving a current frame image captured by a robot, performing scene recognition on the current frame image; based on the scene recognition result, determining a reference image frame matching the current image frame from a pre-established target map.

In some embodiments, determining a target view flag in a current image frame includes: identifying at least one view flag in the current frame image; and determining, for a view flag among the at least one identified view flag, in response to determining that the view flag is included in a reference frame image, determining the view flag as a target view flag.

In some embodiments, the current posture of the robot is determined based on the identification information of the target view mark in the reference frame image and the extracted edge image of the target view mark in the current frame image, including: determining a theoretical edge image of the target view mark in the current frame image based on the identification information of the target view mark in the reference frame image; and fitting the extracted edge image of the target view mark in the current frame image and the determined theoretical edge image using a nonlinear least squares method to obtain the current posture of the robot.

In some embodiments, the method also includes: determining the sum of squared Euclidean distances between the extracted edge image of the target view mark in the current frame image and the theoretical edge image as the objective function of the nonlinear least squares method; and determining the minimum value of the objective function to fit the extracted edge image of the target view mark in the current frame image and the theoretical edge image.

In some embodiments, a target map is established through the following steps: acquiring an environmental image collected by a robot and the position and posture of the robot; performing edge extraction on the environmental image to obtain edge information of a view mark in the environmental image, wherein the edge information includes pixel depth information and pixel coordinate information; using a SLAM algorithm to process the collected environmental image to generate and save a real-time map; setting identification information for the view mark in the real-time map to obtain a target map, wherein the identification information includes edge information and the position and posture of the robot.

In a second aspect, an embodiment of the present disclosure provides a positioning device for a robot, the device comprising: an acquisition unit, configured to, in response to receiving a current frame image collected by the robot, obtain a reference frame image matching the current frame image from a pre-established target map, wherein the reference frame image comprises at least one view mark and identification information of the view mark, the identification information comprises edge information of the view mark and a reference pose of the robot collecting the reference frame image; an edge extraction unit, configured to determine a target view mark in a current image frame, perform edge extraction on the determined target view mark to obtain an extracted edge image of the target view mark, wherein the reference frame image comprises the target view mark; a determination unit, configured to determine the current pose of the robot based on the identification information of the target view mark in the reference frame image and the extracted edge image of the target view mark in the current frame image.

In some embodiments, the acquisition unit is further configured to: in response to receiving a current frame image captured by the robot, perform scene recognition on the current frame image; and based on the scene recognition result, determine a reference image frame that matches the current image frame from a pre-established target map.

In some embodiments, the edge extraction unit is further configured to identify at least one view mark in the current frame image; for a view mark among the at least one identified view mark, in response to determining that the view mark is included in the reference frame image, the view mark is determined as a target view mark.

In some embodiments, the determination unit is further configured to: determine a theoretical edge image of the target view mark in the current frame image based on the identification information of the target view mark in the reference frame image; and use a nonlinear least squares method to fit the extracted edge image of the target view mark in the current frame image and the determined theoretical edge image to obtain the current posture of the robot.

In some embodiments, the determination unit is further configured to: determine the sum of squares of the Euclidean distances between the extracted edge image of the target view mark in the current frame image and the theoretical edge image as the objective function of the nonlinear least squares method; determine the minimum value of the objective function to fit the extracted edge image of the target view mark in the current frame image and the theoretical edge image.

In some embodiments, a target map is established through the following steps: acquiring an environmental image collected by a robot and the position and posture of the robot; performing edge extraction on the environmental image to obtain edge information of a view mark in the environmental image, wherein the edge information includes pixel depth information and pixel coordinate information; using a SLAM algorithm to process the collected environmental image to generate and save a real-time map; setting identification information for the view mark in the real-time map to obtain a target map, wherein the identification information includes edge information and the position and posture of the robot.

The robot positioning method and device provided by the embodiments of the present disclosure can, in response to receiving a current frame image collected by the robot, obtain a reference frame image that matches the current frame image from a pre-established target map, and then determine the target view mark in the current image frame, perform edge extraction on the view mark in the current image frame, and obtain an extracted edge image of the target view mark. Finally, based on the identification information of the target view mark in the reference frame image and the extracted edge image of the target view mark in the current frame image, the current posture of the robot can be determined, thereby realizing the determination of the current posture of the robot by using the edge image of the view mark in the image, so that the positioning of the robot is not affected by changes in lighting and scene, thereby improving the accuracy of the robot positioning.

BRIEF DESCRIPTION OF THE DRAWINGS

Other features, objects and advantages of the present disclosure will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

FIG1 is an exemplary system architecture diagram in which some embodiments of the present disclosure may be applied;

FIG2 is a flow chart of an embodiment of a positioning method of a robot according to the present disclosure;

FIG3 is a flow chart of another embodiment of a robot positioning method according to the present disclosure;

FIG4 is a schematic diagram of an application scenario of a robot positioning method according to an embodiment of the present disclosure;

FIG5 is a schematic structural diagram of an embodiment of a positioning device for a robot according to the present disclosure;

FIG. 6 is a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present disclosure.

Detailed ways

The present disclosure is further described in detail below in conjunction with the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings.

It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

FIG. 1 shows an exemplary system architecture 100 to which a robot positioning method or a robot positioning device according to an embodiment of the present disclosure can be applied.

As shown in Fig. 1, the system architecture 100 may include a robot 101, a network 102 and a server 103. The network 102 is used to provide a medium for a communication link between the robot 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

The robot 101 can interact with the server 103 through the network 102 to receive or send messages, etc. The robot 101 can be a robot used in different fields, such as a sweeping robot, AGV, etc., and the robot 101 can be provided with an image acquisition device, and the robot can perform image acquisition through the image acquisition device during movement.

The server 103 may be a server that provides various services, such as a background server that analyzes and processes data such as the current frame image collected by the robot 101. The background server may also feed back the processing results (such as the current position of the robot) to the robot.

It should be noted that the robot positioning method provided in the embodiment of the present disclosure may be executed by the server 103. Accordingly, the robot positioning device may be disposed in the server 103.

It should be noted that the server can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server is software, it can be implemented as multiple software or software modules for providing distributed services, or it can be implemented as a single software or software module. No specific limitation is made here.

It should be understood that the number of robots, networks and servers in Figure 1 is only illustrative. Any number of robots, networks and servers may be provided according to implementation requirements.

It should be noted that the robot 101 can directly locate itself. After the robot 101 obtains the current frame image from the image acquisition device therein, it can obtain a reference frame image matching the current frame image from the pre-established target map, determine the target view mark in the current image frame, perform edge extraction on the view mark in the current frame image, obtain the extracted edge image of the target view mark, and determine the current position and posture of the robot based on the identification information of the target view mark in the reference frame image and the extracted edge image. At this time, the robot's positioning method can also be executed by the robot 101, and accordingly, the robot's positioning device can also be set in the robot 101. At this time, the exemplary system architecture 100 can be without the server 103 and the network 102.

Continuing to refer to FIG2 , a process 200 of an embodiment of a robot positioning method according to the present disclosure is shown. The robot positioning method comprises the following steps:

Step 201 , in response to receiving a current frame image captured by a robot, obtaining a reference frame image matching the current frame image from a pre-established target map.

In this embodiment, the execution subject of the robot positioning method (such as the server shown in Figure 1) can receive the current frame image sent by the robot through a wired connection or a wireless connection. Here, the current frame image can be an image obtained by the robot at the current position through image acquisition. After receiving the current frame image acquired by the robot, the above-mentioned execution subject can use various methods to match the acquired current frame image with each frame image in the pre-established target map, obtain an image matching the current frame image, and determine the acquired image as a reference frame image of the current frame image. As an example, the above-mentioned execution subject can calculate the distance between the current frame image and each frame image in the target map, and determine the image with the smallest distance to the current frame image in the target map as the reference frame image.

The above-mentioned reference frame image may include at least one view mark and identification information of the view mark. Here, the view mark may be a landmark object such as a billboard, a traffic signal sign, etc. contained in the image. The identification information of the view mark may include edge information and a reference pose of the view mark. Among them, the edge image information may include image coordinate information of the edge image of the view mark in the reference frame image and depth information of the edge of the view mark. The reference pose may be the pose of the robot when collecting the reference frame image.

It should be noted that the above-mentioned wireless connection methods may include but are not limited to 3G/4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

In some optional implementations of this embodiment, the execution subject may obtain a reference frame image matching the current frame image from the target map in the following manner: in response to receiving the current frame image collected by the robot, the current frame image is subjected to scene recognition; based on the scene recognition result, a reference image frame matching the current image frame is determined from a pre-established target map. In this implementation, the execution subject may perform scene recognition on the current frame image in various ways, so as to determine the scene of the current frame image. As an example, the execution subject may use a bag of words model to perform scene recognition on the current frame image. It is understandable that the execution subject may also perform scene recognition by other methods, which are not limited here. Then, the execution subject may search for an image containing the recognized scene in the pre-established target map, and the image is the reference image. Determining the reference image of the current frame image by the scene recognition method may improve the accuracy of the reference frame image obtained.

In some optional implementations of this embodiment, the robot uses SLAM technology to concurrently locate and establish a map of the environment in which the robot is located, and the map is the target map. Therefore, after the robot is in the environment and collects the current frame image, it can match the reference frame image in the target map. Specifically, the target map can be obtained in the following manner: obtain the environment image collected by the robot and the robot's posture; then the edge extraction of the environment image can be performed to obtain the edge information of the view mark in the environment image, wherein the edge information can include depth information and pixel coordinates; then the SLAM algorithm can be used to process the collected environment image to generate and save a real-time map; finally, the identification information is set for the view mark in the real-time map to obtain the target map, wherein the identification information includes the edge information and the robot's posture. It can be understood that the target map can also be a map established by other means, and there is no unique limitation here.

Step 202: determine a target view mark in the current image frame, and perform edge extraction on the determined target view mark to obtain an extracted edge image of the target view mark.

In this embodiment, based on the current frame image received in step 201, the execution entity (such as the server shown in FIG. 1 ) may determine the target view mark in the current frame image in various ways. For example, the target view mark may be determined by specifying a view mark in each view mark in the current frame image. It should be noted that the reference image also includes the target view mark. Then, the execution entity may perform edge extraction on the target view mark in the current frame image, thereby obtaining an edge image of the target view mark in the current frame image, and determining the obtained edge image as the extracted edge image. As an example, the execution entity may perform edge detection on the current frame image using a sobel operator, etc., thereby determining the boundary line between the target view mark and the background in the current frame image, and the determined boundary line is the edge of the target view mark.

It is understandable that the above execution subject may also first extract edges of all view marks in the current image frame, and then determine the edge of the target view mark from the edges of all view marks extracted in the current frame image. There is no unique limitation here.

In some optional implementations of this embodiment, the execution subject may determine the target view mark in the following manner: identify at least one view mark in the current frame image; for a view mark in the at least one identified view mark, in response to determining that the reference frame image contains the view mark, determine the view mark as the target view mark. The execution subject may obtain all view marks contained in the current frame image and the reference image by adopting this implementation, and each determined view mark is a target view mark. This implementation may determine all target view marks in the current frame image, and a large number of target view marks may further improve the accuracy of the determined current position and posture of the robot.

Step 203 : determining the current posture of the robot based on the identification information of the target view mark in the reference frame image and the extracted edge image of the target view mark in the current frame image.

In this embodiment, based on the reference frame image obtained in step 201 and the extracted edge image of the target view mark in the current frame image obtained in step 202, the above-mentioned execution subject can process the identification information (including edge information and reference posture) of the target view mark in the reference frame image and the extracted edge image of the target view mark in the current frame image in various ways, so as to determine the current posture of the robot when collecting the current frame image. As an example, the above-mentioned execution subject can match the edge of the target view mark in the reference frame image with the extracted edge image of the target view mark in the current frame image, so as to realize the use of the edge information in the identification information of the target view mark in the reference frame image to solve the relative posture of the reference posture relative to the current posture, so as to determine the current posture of the robot.

The method disclosed in this embodiment utilizes the edge of the target view marker to align the current frame image and the reference frame image to determine the current posture of the robot. This method does not rely on the assumptions of consistent photometric values and non-dynamic scene changes. Therefore, under conditions of changing lighting and dynamic scene changes, the current posture of the robot is more robust.

The method provided by the above-mentioned embodiments of the present disclosure, in response to receiving the current frame image collected by the robot, can obtain a reference frame image matching the current frame image from a pre-established target map, and then determine the target view mark in the current image frame, perform edge extraction on the view mark in the current image frame, and obtain an extracted edge image of the target view mark. Finally, based on the identification information of the target view mark in the reference frame image and the extracted edge image of the target view mark in the current frame image, the current posture of the robot can be determined, thereby realizing the determination of the current posture of the robot by using the edge image of the view mark in the image, so that the positioning of the robot is not affected by changes in lighting and scene, thereby improving the accuracy of the robot positioning.

Further referring to FIG3 , it shows a process 300 of another embodiment of a method for positioning a robot. The process 300 of the method for positioning a net robot comprises the following steps:

Step 301 , in response to receiving a current frame image captured by a robot, obtaining a reference frame image matching the current frame image from a pre-established target map.

Step 302: determine a target view mark in the current image frame, and perform edge extraction on the determined target view mark to obtain an extracted edge image of the target view mark.

In this embodiment, the contents included in step 301 to step 302 are similar to the contents included in step 201 to step 201 in the above embodiment, and are not repeated here.

Step 303: Based on the identification information of the target view mark in the reference frame image, a theoretical edge image of the target view mark is determined in the current frame image.

In this implementation, the execution subject may determine a theoretical edge image of the target view mark in the current frame image based on the reference frame image and the current frame image acquired in step 301. Specifically, the execution subject may use the identification information of the target view mark in the reference frame image (including the edge information and reference pose of the target view mark) to convert and project the edge image of the target view mark in the reference frame image to the current frame image, thereby obtaining the theoretical edge image of the target view mark in the current frame image.

Step 304 , using a nonlinear least squares method, fits the extracted edge image of the target view mark in the current frame image and the determined theoretical edge image to obtain the current position and posture of the robot.

In this embodiment, based on the theoretical edge image of the target view mark in the reference frame image in the current frame image obtained in step 303, the above-mentioned execution subject can use the nonlinear least square method to fit the extracted edge image of the target view mark in the current frame image and the determined theoretical edge image, so as to obtain the current posture of the robot. That is, the nonlinear least square method is used to minimize the distance between the pixel points of the theoretical edge image of the target view mark in the current frame image and the pixels of the extracted edge image, so as to achieve the fitting of the extracted edge image of the target view mark in the current frame image and the determined theoretical edge image.

In some optional implementations of this embodiment, the execution subject may determine the sum of squares of the Euclidean distances between the extracted edge image of the target view mark in the current frame image and the theoretical edge image as the objective function of the nonlinear least squares method. The execution subject may then find the minimum value of the objective function, thereby fitting the extracted edge image of the target view mark in the current frame image with the theoretical edge image.

Continuing to refer to FIG4, FIG4 is a schematic diagram of an application scenario of the positioning method of the robot according to the present embodiment. In the application scenario of FIG4, after the robot acquires the current frame image, the background server can receive the current frame image c _n , obtain the reference frame image _cr matching the current frame image c _n from the pre-established target map, and then the background server can determine the target view mark 401 in the current frame image, as shown in FIG4, and perform edge extraction on the determined target view mark 401 to obtain the extracted edge image 402 of the target view mark, as shown in FIG4, and then the background server can determine the theoretical edge image 404 of the target view mark in the current frame image c _n using the identification information of the view mark in the reference frame image _cr (including the edge information and reference pose of the target view mark edge image 403), and finally the background server can fit the extracted edge image 402 of the target view mark in the current frame image c _n and the theoretical edge image 404 based on the nonlinear least squares method, and obtain the rotation matrix R _c c _r n and the translation matrix P _c c _r n that can minimize the objective function of the nonlinear least squares, thereby determining the current pose of the robot. Among them, the rotation _{matrix Rccrn} and the translation matrix _Pccrn are the rotation matrix and translation matrix of the reference frame image _{cr relative} to the current frame image _cn .

As can be seen from Figure 3, compared with the embodiment corresponding to Figure 2, the process 300 of the robot positioning method in this embodiment realizes the estimation of the current posture of the robot by fitting the extracted edge image of the target view mark in the current frame image and the determined theoretical edge image through the nonlinear least squares method, thereby improving the fitting effect of the extracted edge image of the target view mark in the current frame image and the determined theoretical edge image, thereby further improving the accuracy of the obtained current posture of the robot.

Further referring to FIG. 5 , as an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a positioning device for a robot. The device embodiment corresponds to the method embodiment shown in FIG. 2 , and the device can be specifically applied to various electronic devices.

As shown in FIG5 , the robot positioning device 500 of this embodiment includes: an acquisition unit 501, an edge extraction unit 502, and a determination unit 503. The acquisition unit 501 is configured to, in response to receiving a current frame image collected by the robot, acquire a reference frame image matching the current frame image from a pre-established target map, wherein the reference frame image includes at least one view mark and identification information of the view mark, and the identification information includes edge information of the view mark and a reference pose of the robot collecting the reference frame image; the edge extraction unit 502 is configured to determine a target view mark in the current image frame, perform edge extraction on the determined target view mark to obtain an extracted edge image of the target view mark, wherein the reference frame image includes the target view mark; the determination unit 503 is configured to determine the current pose of the robot based on the identification information of the target view mark in the reference frame image and the extracted edge image of the target view mark in the current frame image.

In some optional implementations of this embodiment, the acquisition unit 501 is further configured to: in response to receiving a current frame image captured by the robot, perform scene recognition on the current frame image; and based on the scene recognition result, determine a reference image frame that matches the current image frame from a pre-established target map.

In some optional implementations of this embodiment, the edge extraction unit 502 is further configured to identify at least one view mark in the current frame image; for a view mark in the at least one identified view mark, in response to determining that the reference frame image contains the view mark, determine the view mark as the target view mark.

In some optional implementations of this embodiment, the determination unit 503 is further configured to: determine a theoretical edge image of the target view mark in the current frame image based on the identification information of the target view mark in the reference frame image; and use a nonlinear least squares method to fit the extracted edge image of the target view mark in the current frame image and the determined theoretical edge image to obtain the current posture of the robot.

In some optional implementations of this embodiment, the determination unit 503 is further configured to: determine the sum of squares of the Euclidean distances between the extracted edge image of the target view mark in the current frame image and the theoretical edge image as the objective function of the nonlinear least squares method; determine the minimum value of the objective function to fit the extracted edge image of the target view mark in the current frame image and the theoretical edge image.

In some optional implementations of this embodiment, the target map is established through the following steps: obtaining the environment image collected by the robot and the robot's posture; performing edge extraction on the environment image to obtain edge information of the view mark in the environment image, wherein the edge information includes pixel depth information and pixel coordinate information; using the SLAM algorithm to process the collected environment image to generate and save a real-time map; setting identification information for the view mark in the real-time map to obtain a target map, wherein the identification information includes edge information and the robot's posture.

The units recorded in the device 500 correspond to the steps in the method described with reference to FIG2 . Therefore, the operations and features described above for the method are also applicable to the device 500 and the units contained therein, and are not repeated here. Referring to FIG6 , a schematic diagram of the structure of an electronic device (such as the server or robot in FIG1 ) 600 suitable for implementing an embodiment of the present disclosure is shown. The server shown in FIG6 is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

As shown in FIG6 , the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to the bus 604.

Typically, the following devices may be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 608 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 609. The communication device 609 may allow the electronic device 600 to communicate wirelessly or wired with other devices to exchange data. Although FIG. 6 shows an electronic device 600 with various devices, it should be understood that it is not required to implement or have all the devices shown. More or fewer devices may be implemented or have alternatively. Each box shown in FIG. 6 may represent one device, or may represent multiple devices as needed.

In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through a communication device 609, or installed from a storage device 608, or installed from a ROM 602. When the computer program is executed by the processing device 601, the above functions defined in the method of the embodiment of the present disclosure are executed. It should be noted that the computer-readable medium described in the embodiment of the present disclosure can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In an embodiment of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, an apparatus, or a device. In an embodiment of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, an apparatus, or a device. The program code contained on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

The computer-readable medium may be included in the electronic device; or it may exist independently without being assembled into the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: in response to receiving the current frame image collected by the robot, obtain a reference frame image matching the current frame image from a pre-established target map, wherein the reference frame image includes at least one view mark and identification information of the view mark, and the identification information includes edge information of the view mark and a reference pose of the robot collecting the reference frame image; determine the target view mark in the current image frame, perform edge extraction on the determined target view mark to obtain an extracted edge image of the target view mark, wherein the reference frame image includes the target view mark; determine the current pose of the robot based on the identification information of the target view mark in the reference frame image and the extracted edge image of the target view mark in the current frame image.

Computer program code for performing the operations of embodiments of the present disclosure may be written in one or more programming languages or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, as a separate software package, partially on a user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and/or flow chart, and the combination of the square boxes in the block diagram and/or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

The units involved in the embodiments described in the present disclosure may be implemented by software or by hardware. The described units may also be arranged in a processor, for example, may be described as: a processor includes an acquisition unit, an edge extraction unit, and a determination unit. Among them, the names of these units do not constitute a limitation on the unit itself in some cases. For example, the acquisition unit may also be described as "a unit that acquires a reference frame image matching the current frame image from a pre-established target map in response to receiving a current frame image collected by the robot."

The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) to form a technical solution.

Claims (10)

1. A robot positioning method, comprising: In response to receiving a current frame image captured by the robot, acquiring a reference frame image matching the current frame image from a pre-established target map, wherein the reference frame image includes at least one view mark and identification information of the view mark, and the identification information includes edge information of the view mark and a reference pose of the robot when capturing the reference frame image; Determining a target view mark in the current frame image, performing edge extraction on the determined target view mark to obtain an extracted edge image of the target view mark, wherein the reference frame image includes the target view mark; Based on the identification information of the target view mark in the reference frame image and the extracted edge image of the target view mark in the current frame image, the current posture of the robot is determined, including: matching the edge information of the target view mark in the reference frame image with the extracted edge image of the target view mark in the current frame image, using the edge information of the target view mark in the reference frame image to solve the relative posture of the reference posture with respect to the current posture, and determining the current posture of the robot. 2. The method according to claim 1, wherein, in response to receiving the current frame image captured by the robot, acquiring a reference frame image matching the current frame image from a pre-established target map comprises: In response to receiving a current frame image captured by the robot, performing scene recognition on the current frame image; Based on the scene recognition result, a reference image frame matching the current frame image is determined from a pre-established target map. 3. The method according to claim 1, wherein determining the target view flag in the current frame image comprises: Identifying at least one view mark in the current frame image; For a view flag in the at least one identified view flag, in response to determining that the reference frame image includes the view flag, the view flag is determined as the target view flag. 4. The method according to claim 1, wherein the determining the current posture of the robot based on the identification information of the target view mark in the reference frame image and the extracted edge image of the target view mark in the current frame image comprises: Based on identification information of the target view mark in the reference frame image, determining a theoretical edge image of the target view mark in the current frame image; The nonlinear least squares method is used to fit the extracted edge image of the target view mark in the current frame image and the determined theoretical edge image to obtain a rotation matrix and a translation matrix that minimize the objective function of the nonlinear least squares method, and determine the current posture of the robot. 5. The method according to claim 4, wherein the method further comprises: Determine the sum of squares of the Euclidean distances between the extracted edge image of the target view mark in the current frame image and the theoretical edge image as the objective function of the nonlinear least squares method; The minimum value of the objective function is determined to fit the extracted edge image of the target view mark in the current frame image with the theoretical edge image. 6. The method according to any one of claims 1 to 5, wherein the target map is established by the following steps: Acquire the environment image collected by the robot and the position and posture of the robot; Performing edge extraction on the environment image to obtain edge information of the view mark in the environment image, wherein the edge information includes pixel depth information and pixel coordinate information; Use SLAM algorithm to process the collected environmental images, generate and save real-time maps; The target map is obtained by setting identification information for the view mark in the real-time map, wherein the identification information includes edge information and the position and posture of the robot. 7. A robot positioning device, comprising: an acquisition unit, configured to, in response to receiving a current frame image acquired by the robot, acquire a reference frame image matching the current frame image from a pre-established target map, wherein the reference frame image includes at least one view mark and identification information of the view mark, and the identification information includes edge information of the view mark and a reference pose of the robot when acquiring the reference frame image; an edge extraction unit, configured to determine a target view mark in the current frame image, and perform edge extraction on the determined target view mark to obtain an extracted edge image of the target view mark, wherein the reference frame image includes the target view mark; a determination unit configured to determine a current posture of the robot based on identification information of the target view mark in the reference frame image and an extracted edge image of the target view mark in the current frame image; Wherein, the determination unit is further configured to: match the edge information of the target view mark in the reference frame image with the extracted edge image of the target view mark in the current frame image, use the edge information of the target view mark in the reference frame image to solve the relative pose of the reference pose with respect to the current pose, and determine the current pose of the robot. 8. The apparatus according to claim 7, wherein the determining unit is further configured to: Based on identification information of the target view mark in the reference frame image, determining a theoretical edge image of the target view mark in the current frame image; The nonlinear least squares method is used to fit the extracted edge image of the target view mark in the current frame image and the determined theoretical edge image to obtain a rotation matrix and a translation matrix that minimize the objective function of the nonlinear least squares method, and determine the current posture of the robot. 9. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6. 10. A computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.