Method, device and equipment for acquiring real trajectory of robot and medium

Abstract

The present disclosure provides a method and device for obtaining a real trajectory of a robot, and a medium, relating to the technical field of artificial intelligence, in particular to the technical field of computer vision, image processing, deep learning, etc. The specific implementation scheme is as follows: controlling the robot to travel along a preset trajectory in a preset venue, and enabling the camera to collect a positioning reference object identifier in a plurality of positioning reference object identifiers in real time during the travel of the robot; the plurality of positioning reference object identifiers are arranged on the ground along the preset trajectory; obtaining a video collected by the camera when the robot travels along the preset trajectory; based on each frame of image in the video and information of the positioning reference object identifier in each frame of image, obtaining corresponding pose information when each frame of image is collected by the camera; and based on the corresponding pose information when each frame of image is collected by the camera, obtaining the real trajectory of the robot. The present disclosure can effectively improve the accuracy of the obtained real trajectory of the robot.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of artificial intelligence, in particular to the technical field of computer vision, image processing, deep learning and the like, which can be applied to smart city, metaverse and the like, and in particular to a method and device for acquiring a real trajectory of a robot, equipment and a medium. BACKGROUND

[0002] At present, the method for acquiring the real trajectory (i.e., the real trajectory) of a robot based on visual positioning can be implemented by using the Simultaneous Localization and Mapping (SLAM) technology in computer vision.

[0003] For example, in the prior art, the trajectory of a robot given by a control system can be taken as a high-precision real trajectory of the robot, which is used to evaluate the error of a trajectory calculation method, or can be taken as training data of a trajectory prediction model. SUMMARY

[0004] The present disclosure provides a method and device for acquiring a real trajectory of a robot, equipment and a medium.

[0005] According to an aspect of the present disclosure, a method for acquiring a real trajectory of a robot is provided, comprising:

[0006] controlling the robot to travel along a preset trajectory in a preset space, and enabling a camera of the robot to collect a positioning reference mark in a plurality of positioning reference marks in real time during the travel of the robot, wherein the plurality of positioning reference marks are arranged on the ground along the preset trajectory;

[0007] acquiring a video collected by the camera when the robot travels along the preset trajectory;

[0008] based on each frame of image in the video and information of the positioning reference mark in each frame of image, acquiring pose information corresponding to the collection of each frame of image by the camera;

[0009] based on the pose information corresponding to the collection of each frame of image by the camera, acquiring the real trajectory of the robot.

[0010] According to another aspect of the present disclosure, a device for acquiring a real trajectory of a robot is provided, comprising:

[0011] a control module configured to control the robot to travel along a preset trajectory in a preset space, and enable a camera of the robot to collect a positioning reference mark in a plurality of positioning reference marks in real time during the travel of the robot, wherein the plurality of positioning reference marks are arranged on the ground along the preset trajectory;

[0012] a video acquisition module, configured to acquire a video collected by the camera when the robot travels according to the preset trajectory;

[0013] a pose acquisition module, configured to acquire pose information corresponding to each frame of image collected by the camera based on each frame of image in the video and information of the positioning reference object identified in each frame of image;

[0014] a trajectory acquisition module, configured to acquire a real trajectory of the robot based on the pose information corresponding to each frame of image collected by the camera.

[0015] According to still another aspect of the present disclosure, an electronic device is provided, comprising:

[0016] at least one processor; and

[0017] a memory connected with the at least one processor in communication; wherein

[0018] the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of the aspects and any possible implementation manner described above.

[0019] According to still another aspect of the present disclosure, a non-transitory computer readable storage medium storing computer instructions is provided, the computer instructions being used to cause the computer to perform the method of the aspects and any possible implementation manner described above.

[0020] According to still another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method of the aspects and any possible implementation manner described above.

[0021] According to the technology of the present disclosure, the accuracy of the real trajectory of the robot acquired can be effectively improved.

[0022] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0023] The accompanying drawings are used to better understand the present scheme, and do not limit the present disclosure. Among them:

[0024] Figure 1 is a schematic diagram according to the first embodiment of the present disclosure;

[0025] Figure 2 is a schematic diagram according to the second embodiment of the present disclosure;

[0026] Figure 3 is a schematic diagram of a trajectory segment provided by the present embodiment;

[0027] Figure 4 is a schematic diagram according to a third embodiment of the present disclosure;

[0028] Figure 5 is a schematic diagram of a two-dimensional code configured on a trajectory segment provided by the present embodiment;

[0029] Figure 6 is a schematic diagram according to a fourth embodiment of the present disclosure;

[0030] Figure 7 is a schematic diagram according to a fifth embodiment of the present disclosure;

[0031] Figure 8 is a block diagram of an electronic device used to implement the method of the present embodiment. DETAILED DESCRIPTION

[0032] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to help in understanding, and should be considered as merely exemplary. Thus, those skilled in the art should recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, for the sake of brevity and clarity, descriptions of well-known functions and constructions are omitted from the following description.

[0033] Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present disclosure.

[0034] It should be noted that the terminal device involved in the embodiments of the present disclosure can include, but is not limited to, a mobile phone, a personal digital assistant (PDA), a wireless handheld device, a tablet computer, and the like. The display device can include, but is not limited to, a personal computer, a television, and the like.

[0035] In addition, the term "and / or" in the present disclosure is merely a description of the association relationship between the associated objects, which means that there can be three relationships, for example, A and / or B can represent the three cases of A alone, A and B together, and B alone. In addition, the character " / " in the present disclosure generally represents an "or" relationship between the front and rear associated objects.

[0036] In actual application, the robot does not directly travel according to the trajectory given by the control system, and may be affected by control errors, environmental errors and the like in the middle; and in some scenarios, the trajectory needs to be changed according to the external environment. For the above reasons, in the existing scheme, the trajectory given by the control system to the robot is directly taken as the real trajectory of the robot, which may result in poor accuracy of the real trajectory of the robot.

[0037] Figure 1 is a schematic diagram according to the first embodiment of the present disclosure; as Figure 1 shown, the embodiment provides a method for acquiring the real trajectory of a robot, which can specifically include the following steps:

[0038] S101, controlling the robot to travel according to a preset trajectory in a preset venue, and enabling the camera of the robot to capture a positioning reference object mark in a plurality of positioning reference object marks in real time during the traveling process;

[0039] Among them, the plurality of positioning reference object marks are configured on the ground along the preset trajectory.

[0040] In the application scenario of the method for acquiring the real trajectory of the robot of the embodiment, a preset venue, which can also be referred to as a visual positioning venue, needs to be selected. In the preset venue, a preset trajectory is planned. Meanwhile, a plurality of positioning reference object marks are configured on the ground along the preset trajectory in the preset venue. Since the positioning reference marks are pre-configured, the real spatial position coordinates of the positioning reference object marks can be acquired in advance. The positioning reference object mark of the embodiment can identify the real spatial position coordinates of the position where the positioning reference object mark is located, and can be used to assist the acquisition of the real trajectory of the robot.

[0041] Based on the above configuration, the control system can control the robot to travel according to the preset trajectory, and the camera of the robot can capture a positioning reference object mark in the plurality of positioning reference object marks in real time during the traveling process.

[0042] Optionally, in the traveling process of the robot, each frame of image captured by the camera can include one positioning reference object mark, or can include two or more positioning reference object marks. The density of the plurality of positioning reference object marks configured on the ground along the preset trajectory can be referred to the traveling speed of the robot, so as to ensure that each frame of image captured by the camera in the traveling process of the robot includes at least one positioning reference object mark.

[0043] S102, acquiring a video captured by the camera when the robot travels according to the preset trajectory;

[0044] The control system controls the robot to travel according to the preset track. During the travel of the robot, the camera is in a collection state, and can collect all information on the ground along the preset track in real time, including the plurality of positioning reference object marks arranged on the ground along the preset track. The robot travels from the starting point of the preset track to the ending point, and the camera can collect a video of the whole process, which includes a plurality of video frames.

[0045] S103, based on each frame image in the video and information of the positioning reference object mark in each frame image, obtaining corresponding pose information of the camera when collecting each frame image;

[0046] Each frame image in the video collected by the camera includes at least one positioning reference object mark. In this embodiment, based on comprehensive analysis of each frame image and information of the positioning reference object mark in each frame image, the corresponding pose information of the camera when collecting each frame image can be calculated.

[0047] S104, based on the corresponding pose information of the camera when collecting each frame image, obtaining the real track of the robot.

[0048] In this embodiment, since the camera is arranged on the robot, when the corresponding pose information of the camera when collecting each frame image is obtained, the real track of the robot can be deduced according to the corresponding pose information of the camera when collecting each frame image.

[0049] The method for obtaining the real track of the robot in this embodiment can configure a plurality of positioning reference object marks on the ground along the preset track, control the robot to travel according to the preset track, and collect a video by the camera, and then based on each frame image in the video and information of the positioning reference object mark in each frame image, the corresponding pose information of the camera when collecting each frame image can be obtained, and the real track of the robot can be further obtained, which can effectively improve the accuracy of the obtained real track of the robot and improve the precision of the determined real track of the robot.

[0050] Moreover, in the technical solution of this embodiment, only the surface of the preset site needs to be textured, such as adding a plurality of positioning reference object marks on the ground along the preset track, and without any sensor except the camera, the real track data of the robot with high precision can be produced in batches at a low cost, and the efficiency of obtaining the real track of the robot can be effectively improved.

[0051] In an embodiment of the present disclosure, the robot is a movable robot, so it can also be called a mobile robot.

[0052] In one embodiment of the present disclosure, in step S103, based on the information of each frame image in the video and the positioning reference mark identified in each frame image, the corresponding pose information of the camera when capturing each frame image is obtained. In specific implementation, the following steps can be included:

[0053] (1) Based on each frame image in the video and the information of the positioning reference mark identified in each frame image, the real space position coordinates of the target positioning reference mark associated with each frame image are obtained.

[0054] (2) Based on the real space position coordinates of the target positioning reference mark associated with each frame image and the position information of the target positioning reference mark in each frame image, the corresponding pose information of the camera when capturing each frame image is obtained.

[0055] In the present embodiment, since there can be more than two positioning reference marks in each frame image, in order to improve the accuracy of the determined real trajectory of the robot, a target positioning reference mark needs to be associated with each frame image, so as to accurately obtain the real space position coordinates of the target positioning reference mark associated with each frame image based on the information of the target positioning reference mark associated with each frame image.

[0056] Further, in the present embodiment, the real space position coordinates of the target positioning reference mark associated with each frame image are the coordinates of a 3d space. The position information of the target positioning reference mark in each frame image is the coordinates of a 2d space in the image. The Perspective-n-Point (PnP) algorithm can be used to calculate the corresponding pose information of the camera when capturing each frame image according to the real space position coordinates of the target positioning reference mark associated with each frame image and the position information of the target positioning reference mark in each frame image. In the present embodiment, when the plurality of positioning reference marks are configured on the preset trajectory route in the preset venue, the real space position coordinates of each positioning reference mark can be obtained in advance, for example, the real space position coordinates of each vertex of each positioning reference mark. Similarly, in each frame image, the position information of each vertex of the target positioning reference mark can be obtained.

[0057] For example, the positioning reference mark of the present disclosure is two-dimensional, for example, a two-dimensional code or other two-dimensional image, which can realize the positioning of the corresponding position. Since the recognition degree of the camera to the two-dimensional code is higher and the capture is more accurate, preferably, the positioning reference mark in the present embodiment can adopt a two-dimensional code.

[0058] Optionally, in the embodiments of the present disclosure, the multiple positioning reference object identifiers configured on the route of the preset trajectory can be the same or different. However, if the multiple positioning reference object identifiers are the same, in order to facilitate positioning, the order identifiers of the multiple positioning reference object identifiers are required to be different, such as sequence numbers, so as to ensure that the positioning reference object identifiers with different order identifiers have different real space position coordinates.

[0059] In the embodiments, the real space position coordinates of the target positioning reference object identifiers associated with the multiple frames of images are acquired first in the above manner; and then the pose information corresponding to the multiple frames of images captured by the camera is acquired based on the real space position coordinates of the target positioning reference object identifiers associated with the multiple frames of images and the position information of the target positioning reference object identifiers in the multiple frames of images, so as to effectively improve the accuracy of the acquired pose information corresponding to the multiple frames of images captured by the camera, and further improve the accuracy of the real trajectory of the robot acquired subsequently.

[0060] Figure 2 is a schematic diagram according to a second embodiment of the present disclosure; the method for acquiring the real trajectory of the mobile robot in the embodiments is described taking the mobile robot as an example and based on the technical solutions of the above-mentioned embodiments. As shown in Figure 2 The method for acquiring the real trajectory of the mobile robot in the embodiments can specifically include the following steps:

[0061] S201, controlling the mobile robot to travel along a preset trajectory in a preset venue, and enabling the camera to capture a positioning reference object identifier in the multiple positioning reference object identifiers in real time during the travel of the mobile robot;

[0062] The multiple positioning reference object identifiers are configured on the ground along the preset trajectory.

[0063] In the embodiments, the positioning reference object identifier is taken as a two-dimensional code for example, that is, multiple two-dimensional codes are configured on the ground along the preset trajectory in the preset venue, and the multiple two-dimensional codes are different, that is, any two two-dimensional codes are not the same, and the multiple two-dimensional codes are all two-dimensional plane structures. In the preset venue, the size of each two-dimensional code is known, and the real space position coordinates corresponding to each two-dimensional code can also be acquired in advance. For example, the real space position coordinates of each position point in the two-dimensional code can be accurately known based on the size of the two-dimensional code and the space position coordinates of the center point of the two-dimensional code.

[0064] For example, Figure 3 is a schematic diagram of a trajectory segment provided by the embodiments. As shown in Figure 3 The multiple boxes form a part of the trajectory segment in the preset trajectory, and each box can identify a two-dimensional code.

[0065] S202, acquire a video collected by the camera when the mobile robot travels according to the preset track;

[0066] S203, based on each frame image in the video and the completeness of the positioning reference object identifier in each frame image, extract a complete target positioning reference object identifier in each frame image;

[0067] S204, establish an association relationship between each frame image and the corresponding target positioning reference object identifier;

[0068] Taking the positioning reference object identifier as a two-dimensional code, in this embodiment, one positioning reference object identifier, i.e., a two-dimensional code, can be collected in each frame image, or at least two two-dimensional codes can be collected. In theory, the target two-dimensional code associated with each frame image can be any two-dimensional code collected by the corresponding frame image. In order to more accurately obtain the corresponding pose information of each frame image collected by the camera, it is required that the target two-dimensional code associated with each frame image is as complete as possible, therefore, in this embodiment, a complete target two-dimensional code can be extracted based on the completeness of the two-dimensional code in each frame image, as the target two-dimensional code to be associated with the frame image. Further, an association relationship between each frame image and the corresponding target two-dimensional code is established.

[0069] It should be noted that if the complete two-dimensional code in the same frame image includes at least two, any one of the two-dimensional codes can be extracted as the target two-dimensional code. For example, in order to improve the accuracy of the corresponding pose information of each frame image collected by the camera, preferably, the two-dimensional code with the largest size of the two-dimensional code picture in each frame image is extracted as the target two-dimensional code.

[0070]

[0071] S205, based on the target positioning reference object identifier associated with each frame image and the real space position coordinates corresponding to each positioning reference object identifier obtained in advance, obtain the real space position coordinates of the target positioning reference object identifier associated with each frame image;

[0072] Taking the positioning reference object identifier as a two-dimensional code, since multiple two-dimensional codes are pre-configured on the road surface along the track, at this time, based on the positions of the two-dimensional codes, the real space position coordinates corresponding to each two-dimensional code can be obtained in advance. Based on this, based on the target two-dimensional code associated with each frame image, the real space position coordinates of the target two-dimensional code associated with each frame image can be obtained.

[0073]

[0074] S206, based on the real space position coordinates of the target positioning reference object identifier associated with each frame image,

[0075] and the position information of the target positioning reference object identifier in each frame image, obtain the corresponding pose information of the camera when collecting each frame image.​​

[0076] In this embodiment, the real space position coordinates of the target two-dimensional code associated with each frame of image are three-dimensional coordinates, and the position information of the target two-dimensional code in each frame of image is two-dimensional coordinate. Specifically, the PnP algorithm can be used to calculate the corresponding pose information of the camera when capturing each frame of image according to the real space position coordinates of each point of the target two-dimensional code associated with each frame of image and the position information of each point of the target two-dimensional code in each frame of image.

[0077]

[0078]

[0079] In this embodiment, the target two-dimensional code associated with each frame of image, as the positioning reference identifier, can identify the real space position coordinates of the current target two-dimensional code and assist in determining the pose information of the camera when capturing each frame of image, thereby achieving accurate positioning of the camera.

[0080] 5S207, based on the corresponding pose information of the camera when capturing each frame of image, obtaining the real trajectory point of the mobile robot when the camera captures each frame of image;

[0081]

[0082] Since the camera is the camera of the mobile robot and is arranged on the body of the mobile robot, the position of the mobile robot can be represented to a certain extent based on the pose information of the camera. For example, based on the above principle, the corresponding pose information of the camera when capturing each frame of image can be projected onto the ground, that is, the real trajectory point of the mobile robot when the camera captures each frame of image.

[0083] For example, for any frame of image, the direction vector x of the camera, the included angle theat between the pose of the camera and the ground are known, and the projection on the ground is x_ground=x*cos(theta), which is the real trajectory point of the mobile robot when the camera captures the frame of image.

[0084] S208, based on the real trajectory point of the mobile robot when the camera captures each frame of image, obtaining the real trajectory of the mobile robot when the mobile robot travels according to the preset trajectory;

[0085] The real trajectory point of the mobile robot when the camera captures each frame of image is concatenated in the order of the frames of image, and the real trajectory of the mobile robot when the mobile robot travels according to the preset trajectory is obtained.

[0086] S209, based on the preset trajectory and the real trajectory point of the mobile robot when the camera captures each frame of image, obtaining the error between the corresponding real trajectory point of each frame of image and the preset trajectory. ​​​

[0087] Optionally, the error can include a deviation angle and an offset distance, etc. This step is an optional step. After learning the real trajectory points of the robot when the camera captures each frame of image, the distance between the real trajectory points and the preset trajectory is obtained, that is, the offset distance of the real trajectory point of the moving robot corresponding to the current frame of image to the preset trajectory. Wherein, the deviation angle can be the angle formed between the line connecting the real trajectory point of the moving robot corresponding to the current frame of image and the real trajectory point of the moving robot corresponding to the previous frame and the preset trajectory.

[0088] In this embodiment, the real trajectory of the moving robot obtained by the above-mentioned method is the real trajectory in the process of the moving robot, which is very accurate. The real trajectory of the moving robot can be used to evaluate the calculation error of the trajectory calculation method, and can also be used as self-supervised training data to train the trajectory prediction model. Moreover, in the above-mentioned embodiment, the accuracy of the error between the real trajectory points of each frame of image and the preset trajectory can be ensured, and the error between the real trajectory points of each frame of image and the preset trajectory can also be used to evaluate the accuracy of the preset trajectory or other purposes, which will not be exemplified and described here.

[0089] The method for obtaining the real trajectory of the moving robot in this embodiment can configure a plurality of two-dimensional codes on the ground along the preset trajectory in the field, enable the camera to capture the two-dimensional codes in the process of controlling the moving robot to travel, and then associate a target two-dimensional code for each frame of image based on the two-dimensional codes in each frame of image captured by the camera, and obtain the pose information corresponding to each frame of image captured by the camera according to the real spatial position coordinates of the target two-dimensional code and the position information of the target two-dimensional code in each frame of image, and further obtain the real trajectory of the moving robot, which can effectively improve the accuracy of the determined real trajectory of the moving robot.

[0090] Moreover, in this embodiment, only the surface of the preset field needs to be textured, such as adding a plurality of two-dimensional codes on the ground along the preset trajectory, and without the need for sensors other than the camera, high-precision real trajectory data of the moving robot can be produced in large quantities at a low cost, and the efficiency of obtaining the real trajectory of the moving robot can be effectively improved.

[0091] Figure 4 is a schematic diagram according to the third embodiment of the present disclosure; the method for obtaining the real trajectory of the moving robot in this embodiment is based on the technical solutions of the above-mentioned embodiments, and the same plurality of positioning reference objects are identified, but the order is identified, such as the order number, and the robot is taken as an example of the moving robot to describe the technical solutions of the present disclosure. As shown in Figure 4 The method for obtaining the real trajectory of the moving robot in this embodiment can specifically include the following steps:

[0092] S401. Control the mobile robot to travel along a preset trajectory in a preset site, and enable the camera to capture a positioning reference object mark in a plurality of positioning reference object marks in real time during the travel of the mobile robot.

[0093] The plurality of positioning reference object marks are arranged on the ground along the preset trajectory. For details, refer to the arrangement manner of step S201 in the embodiment shown in Figure 2 The embodiment will not be described herein.

[0094] For example, Figure 5 is a schematic diagram of a two-dimensional code arranged on a trajectory segment according to the embodiment. As shown in Figure 5 For example, three two-dimensional codes are arranged on a certain trajectory segment. The three two-dimensional codes can be the same two-dimensional code, i.e., the shapes of the three two-dimensional codes can be completely the same. However, since the three two-dimensional codes are located at different positions in the preset trajectory, the order identifiers thereof are different, and the corresponding real space position coordinates are also different.

[0095] S402. Obtain a video captured by the camera when the mobile robot travels along the preset trajectory.

[0096] S403. Obtain an order identifier of a target positioning reference object mark corresponding to each frame image based on each frame image in the video and the completeness of the positioning reference object mark in each frame image.

[0097] For example, in a specific implementation, the following manner can be included:

[0098] For the first frame image, the order identifier of the target positioning reference object mark associated with the first frame image is determined to be a preset value, such as 1.

[0099] For other frame images, if the picture of the positioning reference object mark does not intersect the lower edge of the frame image in the corresponding frame image, the order identifier of the target positioning reference object mark associated with the frame image is determined to be the same as the order identifier of the positioning reference object mark associated with the previous frame image.

[0100] For other frame images, if the picture of the positioning reference object mark intersects the lower edge of the frame image in the corresponding frame image, the order identifier of the target positioning reference object mark associated with the frame image is determined to be

[0101] 1 added to the order identifier of the target positioning reference object mark associated with the previous frame image.

[0102] In addition, optionally, in the embodiment, the order identifier of the target positioning reference object identifier corresponding to each frame image can also be acquired in other manners. For example, for any current frame image other than the first frame, the tracking of the positioning reference object identifier can be performed, and the order identifier of the target positioning reference object 0 identifier corresponding to the current frame image can be acquired by referring to the order identifiers of the target positioning reference object identifiers of the previous continuous multiple frame images.

[0103] S404, establishing the association relationship between each frame image and the corresponding target positioning reference object identifier and the order identifier;

[0104] The difference between the above-mentioned embodiments and the embodiment is that the two-dimensional codes arranged on the surface of the preset track along line in the embodiment are completely the same. Therefore, when the association is performed, the association relationship between each frame image and the order identifier of the two-dimensional code 5 needs to be established. In the embodiment, the order identifiers of the multiple two-dimensional codes can be numbered in natural order according to the positions of the multiple two-dimensional codes in the preset track. For example, 1, 2, 3, and the like. Optionally, the order identifier of the two-dimensional code at the first position can also be any natural number other than 1, and the order identifiers of the two-dimensional codes at the other positions can be accumulated on the basis of the order identifier of the two-dimensional code at the previous position. Figure 2

[0105] When the order identifier of the target two-dimensional code corresponding to each frame image is acquired, the order identifier of the target two-dimensional code corresponding to each frame image can be acquired in sequence according to the order of the frames in the video. The density of the two-dimensional codes arranged on the preset track along line in the embodiment can be referred to the moving speed of the mobile robot to ensure that at least one two-dimensional code is included in each frame image.

[0106] The target two-dimensional code acquired for each frame image in the embodiment can be the two-dimensional code closest to the lower 5 edges in each frame image, or in other words, the two-dimensional code closest to the mobile robot in the moving of the mobile robot.

[0107]

[0108] The density of the two-dimensional codes arranged on the preset track along line in the embodiment can be referred to the moving speed of the mobile robot to ensure that at least one two-dimensional code is included in each frame image.

[0109] The target two-dimensional code acquired for each frame image in the embodiment can be the two-dimensional code closest to the lower 5 edges in each frame image, or in other words, the two-dimensional code closest to the mobile robot in the moving of the mobile robot.

[0110] The density of the two-dimensional codes arranged on the preset track along line in the embodiment can be referred to the moving speed of the mobile robot to ensure that at least one two-dimensional code is included in each frame image.

[0111] ​​For the first frame image, the mobile robot is controlled to move, and the two-dimensional code with the sequence identifier 1 is first captured, so it can be determined that the sequence identifier of the target positioning reference identifier associated with the first frame image is 1. In actual application, it can also be detected whether the first frame image includes the two-dimensional code. If it includes, at this time, since the current frame image is the first frame image, that is, the mobile robot is located at the starting point of the preset track, during debugging, the camera is controlled to capture the two-dimensional code with the sequence identifier 1 in the first frame image. At this time, it can be directly determined that the sequence identifier of the target positioning reference identifier associated with the first frame image is 1.

[0112] Next, with the movement of the mobile robot, the two-dimensional code with the sequence identifier 1 gradually moves backward in the video, and finally moves out from the lower edge of a certain frame video. Based on this principle, the second frame image and other frame images are detected in turn. For example, for the second frame image, it can be first detected and determined that the second frame image includes the two-dimensional code, that is, the current second frame image is a valid image. If the picture of the two-dimensional code does not exist in the second frame image and intersects with the lower edge of the second frame image, at this time, it can be determined that the two-dimensional code with the sequence identifier 1 is still in the current second frame image and is complete, at this time, it is determined that the sequence identifier of the target two-dimensional code associated with the second frame image is the same as that of the target two-dimensional code associated with the first frame image, and both are 1.

[0113] If the corresponding second frame image includes the two-dimensional code intersecting with the lower edge of the frame image, the intersecting two-dimensional code must be the two-dimensional code with the sequence identifier 1, because the two-dimensional code with the sequence identifier 1 is the two-dimensional code with the most forward position, at this time, it can be determined that the two-dimensional code with the sequence identifier 1 is partially moved out from the frame image, and the two-dimensional code with the sequence identifier 1 in the current second frame image is not complete, at this time, the two-dimensional code with the sequence identifier 2 can be taken, that is, it can be determined that the sequence identifier of the target two-dimensional code associated with the second frame image is 2, which is 1 plus 1. By analogy, the sequence identifier of the target positioning reference identifier associated with the third frame image and other frame images can be obtained. And the association relationship between each frame image and the corresponding target two-dimensional code and the sequence identifier of the target two-dimensional code is established.

[0114] Because the two-dimensional codes in the scene of the embodiment are all the same, the sequence identifier of the target two-dimensional code must be carried in the association relationship, so as to establish an accurate association relationship.

[0115] In the embodiment, by the above-mentioned manner, the sequence identifier of the target positioning reference identifier associated with each frame image can be accurately determined, and the accuracy of the established association relationship corresponding to each frame image and the accuracy of the real space position coordinates of the target positioning reference identifier associated with each frame image can be ensured.

[0116] S405, based on the sequence identifier of the target positioning reference object identifier associated with each frame image and the real space position coordinates of the positioning reference object identifier of each sequence identifier obtained in advance, obtaining the real space position coordinates of the target positioning reference object identifier associated with each frame image;

[0117] Taking the positioning reference object identifier as a two-dimensional code as an example, since each two-dimensional code is configured, the real space position coordinates corresponding to each sequence identifier of the two-dimensional code can be obtained in advance. Based on this, based on the sequence identifier of the target two-dimensional code associated with each frame image, the real space position coordinates of the target two-dimensional code corresponding to the sequence identifier associated with each frame image can be obtained. Since the sequence identifier is the sequence identifier of the target two-dimensional code, it can also be said that the real space position coordinates of the target two-dimensional code associated with each frame image.

[0118] S406, based on the real space position coordinates of the target positioning reference object identifier associated with each frame image and the position information of the target positioning reference object identifier in each frame image, obtaining the pose information corresponding to the camera when collecting each frame image;

[0119] S407, based on the pose information corresponding to the camera when collecting each frame image, obtaining the real trajectory point of the mobile robot when the camera collects each frame image;

[0120] S408, based on the real trajectory point of the mobile robot when the camera collects each frame image, obtaining the real trajectory of the mobile robot when the mobile robot travels according to the preset trajectory;

[0121] S409, based on the preset trajectory and the real trajectory point of the mobile robot when the camera collects each frame image, obtaining the error between the real trajectory point corresponding to each frame image and the preset trajectory.

[0122] Steps S406-S409 are the same as steps S206-S209 of the above-mentioned embodiment, and details can be referred to the description of the above-mentioned related embodiments, which will not be repeated here. Figure 2

[0123] The method for obtaining the real trajectory of the mobile robot of the present embodiment can effectively improve the accuracy of the determined real trajectory of the mobile robot by using the above-mentioned scheme. Moreover, it can also produce high-precision real trajectory data of the mobile robot in large quantities at a lower cost, and effectively improve the acquisition efficiency of the real trajectory of the mobile robot.

[0124] Figure 6 is a schematic diagram according to the fourth embodiment of the present disclosure; as Figure 6 shown, the present embodiment provides a real trajectory acquisition device 600 of a robot, comprising:

[0125] ​The control module 601 is configured to control the robot to travel along a preset track in a preset field, and enable the camera to capture the positioning reference mark in the plurality of positioning reference marks in real time during the travel of the robot.

[0126] The video acquisition module 602 is configured to acquire a video captured by the camera when the robot travels along the preset track.

[0127] The pose acquisition module 603 is configured to acquire pose information corresponding to the camera when each frame of image is captured based on each frame of image in the video and information of the positioning reference mark in each frame of image.

[0128] The track acquisition module 604 is configured to acquire a real track of the robot based on the pose information corresponding to the camera when each frame of image is captured.

[0129] The real track acquisition device 600 of the robot in the embodiment is implemented by using the above modules, and the implementation principle and technical effects of the acquisition of the real track of the robot are the same as those of the above-mentioned related method embodiments. For details, refer to the description of the above-mentioned related method embodiments, which will not be repeated here.

[0130] Figure 7 is a schematic view according to the fifth embodiment of the disclosure; as Figure 7 indicated, the embodiment provides a real track acquisition device 700 of a robot, which comprises the same name and same function modules as shown in the above Figure 6 indicated: a control module 701, a video acquisition module 702, a pose acquisition module 703, and a track acquisition module 704.

[0131] As Figure 7 indicated, in the real track acquisition device 700 of the robot in the embodiment, the pose acquisition module 703 comprises:

[0132] The space coordinate acquisition unit 7031 is configured to acquire real space position coordinates of a target positioning reference mark associated with each frame of image based on each frame of image in the video and information of the positioning reference mark in each frame of image.

[0133] The pose acquisition unit 7032 is configured to acquire pose information corresponding to the camera when each frame of image is captured based on the real space position coordinates of the target positioning reference mark associated with each frame of image and position information of the target positioning reference mark in each frame of image.

[0134] Further optionally, in an embodiment of the disclosure, the space coordinate acquisition unit 7031 is configured to:

[0135] if the multiple positioning reference object identifiers are different, based on each frame image in the video and completeness of the positioning reference object identifier in each frame image, extracting the target positioning reference object identifier complete in each frame image;

[0136] establishing an association relationship between each frame image and the corresponding target positioning reference object identifier;

[0137] based on the target positioning reference object identifier associated with each frame image and the real space position coordinates of the positioning reference object identifier corresponding to each sequence identifier obtained in advance, obtaining the real space position coordinates of the target positioning reference object identifier associated with each frame image.

[0138] Further optionally, in an embodiment of the present disclosure, the space coordinate obtaining unit 7031 is configured to:

[0139] if the multiple positioning reference object identifiers are the same, but the sequence identifiers of the multiple positioning reference object identifiers are different, based on each frame image in the video and completeness of the positioning reference object identifier in each frame image, obtaining the sequence identifier of the target positioning reference object identifier corresponding to each frame image;

[0140] establishing an association relationship between each frame image and the corresponding target positioning reference object identifier and the sequence identifier;

[0141] based on the sequence identifier of the target positioning reference object identifier associated with each frame image and the real space position coordinates of the positioning reference object identifier corresponding to each sequence identifier obtained in advance, obtaining the real space position coordinates of the target positioning reference object identifier associated with each frame image.

[0142] Further optionally, in an embodiment of the present disclosure, the space coordinate obtaining unit 7031 is configured to:

[0143] for the first frame image, determining that the sequence identifier of the target positioning reference object identifier associated with the first frame image is a preset value;

[0144] for other frame images, if the picture of the positioning reference object identifier in the corresponding frame image does not intersect with the lower edge of the frame image, determining that the sequence identifier of the target positioning reference object identifier associated with the frame image is the same as the sequence identifier of the positioning reference object identifier associated with the previous frame image.

[0145] Further optionally, in an embodiment of the present disclosure, the space coordinate obtaining unit 7031 is further configured to:

[0146] For other frame images, if the picture corresponding to the positioning reference object mark in the frame image intersects with the lower edge of the frame image, the order identifier of the target positioning reference object mark associated with the frame image is determined to be 1 added on the basis of the order identifier of the target positioning reference object mark associated with the previous frame image.

[0147] Further optionally, in an embodiment of the present disclosure, the trajectory acquisition module 704 is configured to:

[0148] acquire real trajectory points of the robot when the camera captures each frame image based on the corresponding pose information when the camera captures each frame image;

[0149] acquire the real trajectory of the robot when the robot travels according to the preset trajectory based on the real trajectory points of the robot when the camera captures each frame image.

[0150] Further optionally, as shown in Figure 7 In an embodiment of the present disclosure, the real trajectory acquisition device 700 of the robot further comprises:

[0151] The error acquisition module 705 is configured to acquire the error between the real trajectory point corresponding to each frame image and the preset trajectory based on the preset trajectory and the real trajectory point of the robot when the camera captures each frame image.

[0152] Further optionally, in an embodiment of the present disclosure, the positioning reference object mark is a two-dimensional code.

[0153] The real trajectory acquisition device 700 of the robot of the present embodiment realizes the implementation principle and technical effects of acquiring the real trajectory of the robot by using the above modules, which are the same as the implementation of the above-mentioned related method embodiments. For details, refer to the description of the above-mentioned related method embodiments, which will not be repeated here.

[0154] According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0155] Figure 8A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present disclosure described and / or claimed in this document.

[0156] As shown in Figure 8 The device 800 includes a computing unit 801 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 802 or a computer program loaded into a random access memory (RAM) 803 from a storage unit 808. Various programs and data required for the operation of the device 800 can also be stored in the RAM 803. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other through a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0157] Various components in the device 800 are connected to the I / O interface 805, including an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; the storage unit 808, such as a magnetic disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0158] The computing unit 801 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs various methods and processes described above, such as the above-described methods of the present disclosure. For example, in some embodiments, the above-described methods of the present disclosure can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded onto the RAM 803 and executed by the computing unit 801, one or more steps of the above-described methods of the present disclosure described above can be performed. Alternatively, in other embodiments, the computing unit 801 can be configured to perform the above-described methods of the present disclosure by any other suitable means, such as by means of firmware.

[0159] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a complex programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0160] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces a means for implementing the functions / acts specified in the flowcharts and / or block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0161] In the context of this disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0162] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0163] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0164] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0165] It should be understood that the various forms of flow shown above can be reordered, added to, or

[0166] It should be understood that the various forms of flow shown above can be reordered, added to, or

[0167] The specific embodiments described above are not intended to be limiting. One skilled in the art will appreciate that various modifications, combinations, sub-combinations, and alternatives can be made to the specific embodiments without departing from the spirit and scope of the disclosure. Any further modifications, equivalents, and / or alterations of the specific embodiments described herein are included in the scope of the disclosure.

Claims

1. A method for obtaining a real trajectory of a robot, comprising: controlling the robot to travel along a preset trajectory in a preset space, and enabling a camera to collect all information on the ground along the preset trajectory in real time during the traveling, including a plurality of positioning reference object marks arranged on the ground along the preset trajectory; the camera faces the traveling direction during the traveling of the robot; obtaining a video collected by the camera when the robot travels along the preset trajectory; at least one of the positioning reference object marks is included in each frame of the video; based on the information of each frame of the video and the positioning reference object marks in each frame, obtaining corresponding pose information of the camera when each frame of the video is collected; based on the corresponding pose information of the camera when each frame of the video is collected, obtaining the real trajectory of the robot; based on the information of each frame of the video and the positioning reference object marks in each frame, obtaining corresponding pose information of the camera when each frame of the video is collected, comprising: based on the information of each frame of the video and the positioning reference object marks in each frame, obtaining a target positioning reference object mark associated with each frame of the video; the target positioning reference object mark included in each frame is complete; obtaining real spatial position coordinates of the target positioning reference object mark associated with each frame; based on the real spatial position coordinates of the target positioning reference object mark associated with each frame and the position information of the target positioning reference object mark in each frame, obtaining the corresponding pose information of the camera when each frame of the video is collected by using a perspective-n-point algorithm.

2. The method of claim 1, wherein, based on the information of each frame of the video and the positioning reference object marks in each frame, obtaining a target positioning reference object mark associated with each frame of the video, comprising: if the plurality of positioning reference object marks are different, based on the completeness of each frame of the video and the positioning reference object marks in each frame, extracting the complete target positioning reference object mark in each frame; establishing an association between each frame and the corresponding target positioning reference object mark to obtain the target positioning reference object mark associated with each frame; obtaining real spatial position coordinates of the target positioning reference object mark associated with each frame, comprising: based on the target positioning reference object mark associated with each frame and the real spatial position coordinates of each positioning reference object mark obtained in advance, obtaining the real spatial position coordinates of the target positioning reference object mark associated with each frame.

3. The method of claim 1, wherein, based on the information of each frame of the video and the positioning reference object marks in each frame, obtaining real spatial position coordinates of the target positioning reference object mark associated with each frame of the video, comprising: if the plurality of positioning reference object marks are the same but the sequence identifiers of the plurality of positioning reference object marks are different, based on the completeness of each frame of the video and the positioning reference object marks in each frame, obtaining the sequence identifier of the target positioning reference object mark corresponding to each frame; Establish an association between each frame of image and the corresponding target positioning reference object identifier and the sequence identifier; Based on the sequence identifier of the target positioning reference object identifier associated with each frame of image and the real space position coordinates of the positioning reference object identifier of each sequence identifier obtained in advance, obtain the real space position coordinates of the target positioning reference object identifier associated with each frame of image.

4. The method of claim 3, wherein, Based on the completeness of each frame of image in the video and the positioning reference object identifier in each frame of image, obtain the sequence identifier of the target positioning reference object identifier associated with each frame of image, including: For the first frame of image, determine the sequence identifier of the target positioning reference object identifier associated with the first frame of image as a preset value; For other frames of image, if there is no picture of the positioning reference object identifier in the corresponding frame of image intersecting with the lower edge of the frame of image, determine that the sequence identifier of the target positioning reference object identifier associated with the frame of image is the same as the sequence identifier of the positioning reference object identifier associated with the previous frame of image.

5. The method of claim 4, wherein, Based on the completeness of each frame of image in the video and the positioning reference object identifier in each frame of image, obtain the sequence identifier of the target positioning reference object identifier associated with each frame of image, further including: For other frames of image, if there is a picture of the positioning reference object identifier in the corresponding frame of image intersecting with the lower edge of the frame of image, determine that the sequence identifier of the target positioning reference object identifier associated with the frame of image is 1 added to the sequence identifier of the target positioning reference object identifier associated with the previous frame of image.

6. The method of claim 1, wherein, Based on the corresponding pose information when the camera collects each frame of image, obtain the real trajectory of the robot, including: Based on the corresponding pose information when the camera collects each frame of image, obtain the real trajectory point of the robot when the camera collects each frame of image; Based on the real trajectory point of the robot when the camera collects each frame of image, obtain the real trajectory of the robot when the robot travels according to the preset trajectory.

7. The method of any one of claims 1-6, wherein, The method further includes: Based on the preset trajectory and the real trajectory point of the robot when the camera collects each frame of image, obtain the error between the real trajectory point corresponding to each frame of image and the preset trajectory.

8. The method of any one of claims 1-6, wherein, The positioning reference object identifier is a two-dimensional code.

9. An apparatus for obtaining a real trajectory of a robot, comprising: a control module configured to control a robot to travel according to a preset trajectory in a preset field, and enable a camera to collect all information on the ground along the preset trajectory in real time during the travel of the robot, including a positioning reference object identifier in a plurality of positioning reference object identifiers arranged on the ground along the preset trajectory; during the travel of the robot, the camera faces the travel direction; a video acquisition module configured to acquire a video collected by the camera when the robot travels according to the preset trajectory; a pose acquisition module configured to acquire corresponding pose information when the camera collects each frame of image based on each frame of image in the video and information of the positioning reference object identifier in each frame of image. The trajectory acquisition module is configured to acquire a real trajectory of the robot based on the pose information corresponding to the acquisition of each frame of image by the camera. The pose acquisition module comprises: The space coordinate acquisition unit is configured to: If the multiple positioning reference object identifiers are different, the space coordinate acquisition unit is configured to extract the target positioning reference object identifier that is complete in each frame of image based on each frame of image in the video and completeness of the positioning reference object identifier in each frame of image. The space coordinate acquisition unit is configured to:

10. The apparatus of claim 9, wherein, If the multiple positioning reference object identifiers are different, the space coordinate acquisition unit is configured to extract the target positioning reference object identifier that is complete in each frame of image based on each frame of image in the video and completeness of the positioning reference object identifier in each frame of image. The space coordinate acquisition unit is configured to: If the multiple positioning reference object identifiers are different, the space coordinate acquisition unit is configured to extract the target positioning reference object identifier that is complete in each frame of image based on each frame of image in the video and completeness of the positioning reference object identifier in each frame of image. The space coordinate acquisition unit is configured to:

11. The apparatus of claim 9, wherein, If the multiple positioning reference object identifiers are different, the space coordinate acquisition unit is configured to extract the target positioning reference object identifier that is complete in each frame of image based on each frame of image in the video and completeness of the positioning reference object identifier in each frame of image. The space coordinate acquisition unit is configured to: If the multiple positioning reference object identifiers are different, the space coordinate acquisition unit is configured to extract the target positioning reference object identifier that is complete in each frame of image based on each frame of image in the video and completeness of the positioning reference object identifier in each frame of image. The space coordinate acquisition unit is configured to:

12. The apparatus of claim 11, wherein, If the multiple positioning reference object identifiers are different, the space coordinate acquisition unit is configured to extract the target positioning reference object identifier that is complete in each frame of image based on each frame of image in the video and completeness of the positioning reference object identifier in each frame of image. The space coordinate acquisition unit is configured to: For the first frame of image, the space coordinate acquisition unit is configured to determine that the sequence identifier of the target positioning reference object identifier associated with the first frame of image is a preset value.

13. The apparatus of claim 12, wherein, For other frames of image, if the picture of the positioning reference object identifier does not intersect with the lower edge of the frame of image in the corresponding frame of image, the space coordinate acquisition unit is configured to determine that the sequence identifier of the target positioning reference object identifier associated with the frame of image is the same as the sequence identifier of the positioning reference object identifier associated with the previous frame of image. The space coordinate acquisition unit is configured to:

14. The apparatus of claim 9, wherein, For other frames of image, if the picture of the positioning reference object identifier does not intersect with the lower edge of the frame of image in the corresponding frame of image, the space coordinate acquisition unit is configured to determine that the sequence identifier of the target positioning reference object identifier associated with the frame of image is the same as the sequence identifier of the positioning reference object identifier associated with the previous frame of image. The trajectory acquisition module is configured to acquire a real trajectory of the robot based on the pose information corresponding to the acquisition of each frame of image by the camera. Based on the pose information corresponding to the acquisition of each frame of image by the camera, a real trajectory point of the robot when acquiring each frame of image by the camera is obtained; Based on the real trajectory point of the robot when acquiring each frame of image by the camera, a real trajectory of the robot when advancing according to the preset trajectory is obtained.

15. The apparatus of any of claims 9-14, wherein, The device further comprises: An error obtaining module is configured to obtain an error between the real trajectory point corresponding to each frame of image and the preset trajectory based on the preset trajectory and the real trajectory point of the robot when acquiring each frame of image by the camera.

16. The apparatus of any of claims 9-14, wherein, The positioning reference object is a two-dimensional code. 17.An electronic device comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.

18. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to perform the method of any one of claims 1-8. 19.A computer program product comprising a computer program which, when executed by a processor, implements the method of any one of claims 1-8.

Images