A control method, device, and apparatus for a robot, and a storage medium

Abstract

The application relates to the technical field of robots, and provides a control method, device and equipment of a robot and a storage medium, the method comprising the following steps: obtaining a target image obtained by the robot shooting a preset mark, the preset mark comprising at least a first pattern element and a second pattern element, and the first pattern element and the second pattern element at least partially not coinciding; when the target image comprises the first pattern element and the second pattern element, identifying a pattern formed by the first pattern element and the second pattern element to obtain a first identification result, and controlling the robot according to the first identification result; and when the target image comprises the first pattern element and does not comprise the second pattern element, identifying the first pattern element to obtain a second identification result, and controlling the robot according to the second identification result. The robot can accurately observe the preset mark at both long and short distances, and the robot can make accurate path planning.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of robots, and particularly relates to a control method and device of a robot, equipment and a storage medium. BACKGROUND

[0002] A robot is a device that can automatically perform work, and can accept human command or automatically run a pre-arranged program. The main task of the robot is to assist or replace human work, such as delivering goods, ordering food, etc. At present, the robot develops rapidly and is widely used in fields such as restaurants, shopping malls, hotels, cinemas, etc.

[0003] When the robot performs a task, it is easy to cause inaccurate positioning due to a large number of people. For example, the distance between people in a cinema is very close. If the target is noticed only at a very close distance, it is necessary to constantly adjust the pose by advancing and retreating, which leads to a decrease in the work efficiency of the robot.

[0004] Therefore, the existing positioning method cannot realize fast and accurate positioning at a close distance, which leads to the fact that the robot cannot accurately and quickly complete a task during the execution of the task. SUMMARY

[0005] The main purpose of the present application is to provide a control method and device of a robot, equipment and a storage medium, which are beneficial to the robot to accurately observe a preset mark at a close or long distance, and can make the robot make accurate path planning.

[0006] In a first aspect, the present application provides a control method of a robot, comprising:

[0007] obtaining a target image obtained by the robot shooting a preset mark, wherein the preset mark at least includes a first pattern element and a second pattern element, and the first pattern element and the second pattern element at least partially do not coincide;

[0008] when the target image includes the first pattern element and the second pattern element, identifying a pattern formed by the first pattern element and the second pattern element to obtain a first identification result, and controlling the robot according to the first identification result;

[0009] when the target image includes the first pattern element and does not include the second pattern element, identifying the first pattern element to obtain a second identification result, and controlling the robot according to the second identification result.

[0010] In an embodiment, the second pattern element is arranged at the periphery of the first pattern element.

[0011] In an embodiment, the first pattern element and the second pattern element each include a black region and a white region; the black region is made of light-absorbing material, and the white region is made of light-reflecting material.

[0012] In an embodiment, a distance between the first recognition result corresponding preset identifier and the robot is greater than a distance between the second recognition result corresponding preset identifier and the robot.

[0013] In an embodiment, the first recognition result or the second recognition result includes a current pose relationship between the preset identifier and the robot.

[0014] The controlling the robot according to the first recognition result or the second recognition result includes:

[0015] According to the current pose relationship, the robot is controlled to move to a first preset region corresponding to the preset identifier or to avoid a second preset region corresponding to the preset identifier.

[0016] In an embodiment, the chassis of the robot is a differential chassis.

[0017] In an embodiment, the obtaining of the target image obtained by the robot shooting the preset identifier includes:

[0018] The obtaining of the target image obtained by the robot shooting the preset identifier includes:

[0019] The selecting of the target image from the multiple images includes: the target image has a higher definition than other images in the multiple images.

[0020] In a second aspect, the present application further provides a control device of a robot, including:

[0021] An obtaining module is configured to obtain a target image obtained by a robot shooting a preset identifier, the preset identifier including at least a first pattern element and a second pattern element, and the first pattern element and the second pattern element at least partially not coinciding.

[0022] A first control module is configured to, when the target image includes the first pattern element and the second pattern element, identify a pattern formed by the first pattern element and the second pattern element to obtain a first recognition result, and control the robot according to the first recognition result.

[0023] A second control module is configured to, when the target image includes the first pattern element and does not include the second pattern element, identify the first pattern element to obtain a second recognition result, and control the robot according to the second recognition result.

[0024] In a third aspect, the present application provides a computer device, comprising a memory and a processor;

[0025] a memory for storing a computer program;

[0026] a processor for executing the computer program and implementing the robot control method as described above when executing the computer program.

[0027] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, and the computer program, when executed by a processor, implements the steps of the robot control method as described above.

[0028] The present application provides a robot control method, device, equipment and storage medium, wherein the method comprises: obtaining a target image obtained by the robot shooting a preset identifier, the preset identifier comprising at least a first pattern element and a second pattern element, and the first pattern element and the second pattern element at least partially not coinciding; when the target image comprises the first pattern element and the second pattern element, identifying a pattern formed by the first pattern element and the second pattern element to obtain a first identification result, and controlling the robot according to the first identification result; when the target image comprises the first pattern element and does not comprise the second pattern element, identifying the first pattern element to obtain a second identification result, and controlling the robot according to the second identification result. In the present application, the preset identifier comprises at least the first pattern element and the second pattern element, the first pattern element can be identified together with the second pattern element to form a pattern, or can be identified as a pattern alone, so that at least one complete and identifiable pattern can always appear in the field of view of the robot, which is conducive to the robot accurately observing and identifying the preset identifier at near and far distances; since the robot can shoot the complete and identifiable pattern in the preset identifier to obtain the target image at near and far distances, the robot can make accurate path planning by identifying the target images shot at near and far distances to obtain the identification results, and then controlling the robot based on the identification results. BRIEF DESCRIPTION OF DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0030] Figure 1 A flowchart of a robot control method provided by an embodiment of the present application;

[0031] Figure 2 A schematic diagram of a preset identifier provided for an embodiment of the present application;

[0032] Figure 3 A schematic diagram of imaging effects of a robot at different distances provided for an embodiment of the present application;

[0033] Figure 4 A schematic diagram of imaging effects of a robot at a long distance provided for an embodiment of the present application;

[0034] Figure 5 A schematic diagram of imaging effects of a robot at a short distance provided for an embodiment of the present application;

[0035] Figure 6 A schematic diagram of a robot moving to a target object provided for an embodiment of the present application;

[0036] Figure 7 A schematic diagram of a robot moving to a target object provided for an embodiment of the present application;

[0037] Figure 8 A schematic block diagram of a control device of a robot provided for an embodiment of the present application;

[0038] Figure 9 A schematic block diagram of a structure of a computer device provided for an embodiment of the present application. DETAILED DESCRIPTION

[0039] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0040] The flowcharts shown in the drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor do they have to be executed in the described order. For example, some operations / steps can be further decomposed, combined or partially merged, so the actual execution order can be changed according to actual situations.

[0041] The embodiments of the present application provide a control method, device and equipment of a robot and a storage medium. The control method of the robot can be applied to the robot, or can be applied to a server. The server can be a separate server, or can be a cloud server providing basic cloud computing services such as cloud service, cloud database, cloud computing, cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, content delivery network (CDN), and big data and artificial intelligence platform.

[0042] Some embodiments of the present application will be described in detail with reference to the drawings. The following examples and features in the examples can be combined with each other in the case of no conflict.

[0043] Please refer to Figure 1 , Figure 1 A flowchart of a control method of a robot provided by an embodiment of the present application is shown. It should be noted that the control method of the robot provided by the embodiment of the present application can be used for a robot, and of course, can also be used for a server.

[0044] As Figure 1 shown, the control method of the robot includes steps S101 to S103.

[0045] Step S101, obtaining a target image obtained by the robot shooting a preset identifier, the preset identifier at least including a first pattern element and a second pattern element, and the first pattern element and the second pattern element at least partially not coinciding.

[0046] The robot is a device that can automatically perform tasks. For example, the robot can perform tasks such as serving food in a hotel or guiding directions in a shopping mall according to a program set by a person in advance. It should be noted that the robot needs to shoot the surrounding environment and position during the execution of the task, and constantly adjust the path in the case of understanding the road conditions. Therefore, the robot needs to shoot the preset identifier through the camera, so as to identify and position according to the target image of the shot preset identifier.

[0047] The preset identifier in the embodiment of the present application can be an ArUco code, an AprilTag code, etc. Among them, the ArUco code is a synthetic square marker, which is composed of a wide black frame and an internal binary matrix that determines its identifier. The black frame helps its rapid detection in the image, and the binary coding allows its identification and the application of error detection and correction technology. The size of the marker determines the size of the internal matrix. The AprilTag code is a positioning marker based on two-dimensional code, which can realize high-precision target positioning and attitude estimation in complex environment. The position and attitude of the target are determined by identifying the feature points of the AprilTag code, so as to realize the tracking and positioning of the target. Among them, the specific implementation process mainly includes two steps, detection and identification. In the detection stage, the image is preprocessed, such as grayscale, binarization, filtering, etc., and then the feature points in the image are extracted through edge detection and corner detection methods; in the identification stage, the two-dimensional code is identified according to the position and arrangement of the feature points, and the position and attitude of the target are calculated.

[0048] As Figure 2As shown, the preset identifier in the embodiment of the present application includes a first pattern element and a second pattern element. For example, the first pattern element and the second pattern element in the embodiment of the present application are at least partially non-coincident. Specifically, the part of the pattern coinciding with the first pattern element and the second pattern element can be the pattern belonging to the second pattern element or the pattern belonging to the first pattern element. Therefore, the distance range in which the preset identifier can be successfully identified is relatively large, which is beneficial for the robot to observe the first pattern element and / or the second pattern element at a long distance or a short distance.

[0049] For example, the pattern of the first pattern element and the pattern of the second pattern element can be the same or different.

[0050] In step S102, when the target image includes the first pattern element and the second pattern element, the pattern formed by the first pattern element and the second pattern element is identified to obtain a first identification result, and the robot is controlled according to the first identification result.

[0051] For example, when the target image of the preset identifier obtained by the robot includes the first pattern element and the second pattern element, it can be determined that the robot is relatively far away from the preset identifier or the robot is not located opposite to the preset identifier. In actual application, when it is detected that the robot captures the target image of the preset identifier, the preset identifier is identified, that is, the two-dimensional code is identified according to the position and arrangement of the feature points in the target image of the preset identifier, and the position and pose of the preset identifier are calculated. Based on this, the pattern formed by the first pattern element and the second pattern element can be identified to obtain a first identification result, and the robot is controlled according to the first identification result.

[0052] For example, the first target pose of the pattern formed by the first pattern element and the second pattern element in the robot coordinate system can be determined first, and then the robot is controlled according to the first target pose and the coordinates of the robot. For example, the robot can be controlled to move to the position corresponding to the preset identifier. For example, the pose of the pattern formed by the first pattern element and the second pattern element in the camera coordinate system can be calculated according to the intrinsic parameters of the camera, and then the first target pose of the pattern formed by the first pattern element and the second pattern element in the robot coordinate system is calculated according to the pose and the extrinsic parameters of the camera. In the robot coordinate system, the coordinates of the robot are the origin, and therefore, the navigation route of the robot can be determined according to the calculated first target pose and the origin coordinates of the robot to control the robot.

[0053] In step S103, when the target image includes the first pattern element and does not include the second pattern element, the first pattern element is identified to obtain a second identification result, and the robot is controlled according to the second identification result.

[0054] When the target image obtained by the robot shooting the preset mark includes the first pattern element and does not include the second pattern element during the movement of the robot, it can be determined that the robot is relatively close to the preset mark, and thus can only shoot the first pattern element and cannot shoot the second pattern element. At this time, the first pattern element can be identified to obtain a first identification result, and the robot can be controlled according to the first identification result.

[0055] For example, the embodiment of the present application can determine the second target pose of the first pattern element in the robot coordinate system according to the target image, and then control the robot according to the second target pose and the coordinates of the robot. For example, the robot can be controlled to move to the position corresponding to the preset mark. It can be understood that the embodiment of the present application can calculate the pose of the first pattern element in the camera coordinate system according to the camera intrinsic parameter, and then calculate the second target pose of the first pattern element in the robot coordinate system according to the pose and the camera extrinsic parameter. In the robot coordinate system, the coordinates of the robot are the origin, and thus the navigation route of the robot can be determined according to the calculated second target pose and the origin coordinates of the robot to control the robot.

[0056] The control method of the robot provided in the above embodiment includes: obtaining a target image obtained by a robot shooting a preset mark, the preset mark including at least a first pattern element and a second pattern element, and the first pattern element and the second pattern element at least partially not coinciding; when the target image includes the first pattern element and the second pattern element, identifying a pattern formed by the first pattern element and the second pattern element to obtain a first identification result, and controlling the robot according to the first identification result; and when the target image includes the first pattern element and does not include the second pattern element, identifying the first pattern element to obtain a second identification result, and controlling the robot according to the second identification result. The preset mark in the present application includes at least the first pattern element and the second pattern element, the first pattern element can be identified together with the second pattern element to form a pattern, or can be identified as a pattern alone, which can ensure that at least one complete and identifiable pattern always appears in the field of view of the robot, and is conducive to the robot accurately observing and identifying the preset mark at a distance. Since the robot can shoot the complete and identifiable pattern in the preset mark to obtain the target image at a distance, the robot can make accurate path planning by identifying the target images shot at different distances to obtain the identification results, and then controlling the robot based on the identification results.

[0057] For example, the embodiment of the present application can determine the second target pose of the first pattern element in the robot coordinate system according to the target image, and then control the robot according to the second target pose and the coordinates of the robot. For example, the robot can be controlled to move to the position corresponding to the preset mark. It can be understood that the embodiment of the present application can calculate the pose of the first pattern element in the camera coordinate system according to the camera intrinsic parameter, and then calculate the second target pose of the first pattern element in the robot coordinate system according to the pose and the camera extrinsic parameter. In the robot coordinate system, the coordinates of the robot are the origin, and thus the navigation route of the robot can be determined according to the calculated second target pose and the origin coordinates of the robot to control the robot. Figure 3As shown, existing identification codes are generally single patterns. Robots can see the complete pattern at a distance, but only a portion of the pattern at close range, making accurate code recognition impossible. Therefore, the image at a distance presents a complete pattern, while the image at close range only shows a partial area, preventing the robot from continuously viewing the complete pattern. Thus, it is generally necessary to place multiple single patterns at different locations to expand the distance range at which the patterns can be successfully recognized.

[0058] In one exemplary embodiment, the second pattern element is disposed around the first pattern element.

[0059] like Figure 2 As shown, in this embodiment of the application, the dimensions of the first pattern element and the second pattern element are different; for example, the size of the first pattern element is smaller than the size of the second pattern element. For instance, the second pattern element can be disposed around the first pattern element.

[0060] Since the first pattern element is surrounded by the second pattern element, when the robot captures a pattern composed of the first and second pattern elements, recognizing the pattern composed of the first and second pattern elements is equivalent to recognizing a larger identifiable pattern; when the robot captures a first pattern element, recognizing the first pattern element is equivalent to recognizing a smaller identifiable pattern.

[0061] In this embodiment of the application, when the robot views a preset sign from a distance, it can capture a pattern composed of a first pattern element and a second pattern element, such as... Figure 4 As shown; when the robot views the preset sign at close range, it can capture the first pattern element, such as... Figure 5 As shown. In other words, when the robot moves towards the preset marker from a distance and takes an image of the preset marker, a complete and recognizable pattern will always appear in the image, and there will be no situation where only part of the pattern is unrecognizable.

[0062] For example, the identifier obtained by recognizing a single pattern can be the same as the identifier obtained by recognizing two overlapping patterns. Therefore, regardless of whether the robot captures a pattern composed of the first and second pattern elements, or captures only the first pattern element, if the identified identifiers are the same, it can be determined that the preset identifiers appearing in the robot's field of vision belong to the same preset identifier.

[0063] Compared with the existing single pattern, the distance range in which the preset identifier in the embodiment of the present application can be successfully identified is relatively large. For example, when the robot is 5m away from the target position, the pattern composed of the first pattern element and the second pattern element in the preset identifier pasted at the target position can be successfully identified; when the robot approaches the target position until the distance between the robot and the target position is 1m, the pattern of the second pattern element in the preset identifier can be successfully identified. Therefore, during the movement of the robot, the preset identifier can be continuously observed, so that the preset identifier can be continuously identified, and only one preset identifier needs to be set to enable the robot to continuously identify, so as to ensure that continuous pose information of the preset identifier can be acquired during the movement of the robot, thereby being beneficial to the control of the robot.

[0064] For example, the identifier number obtained by identifying the pattern composed of the first pattern element and the second pattern element can also be different from the identifier number obtained by identifying the first pattern element. When the target object or target position corresponding to the two different identifier numbers is the same, it can be determined that the preset identifier appearing in the field of view of the robot belongs to the same preset identifier.

[0065] In addition, in an embodiment, the preset identifier in the embodiment of the present application can include a third pattern element, and the third pattern element is arranged at the periphery of the second pattern element. That is, the third pattern element is arranged at the periphery of the first pattern element and the second pattern element, so that the distance range in which the preset identifier can be successfully identified can be further expanded. Of course, the preset identifier can also include a fourth pattern element, and the number of pattern elements can be set by the person skilled in the art according to the actual working environment of the robot, which is not limited specifically herein.

[0066] In an exemplary embodiment, the first pattern element and the second pattern element each include a black region and a white region; the black region is made of light-absorbing material, and the white region is made of light-reflecting material.

[0067] It should be noted that the first pattern element and the second pattern element each include a black region and a white region, the black region is composed of a plurality of black squares, the white region is composed of a plurality of white squares, and one black square represents a value of 1 and one white square represents a value of 0. The shape of the black region can be a square, and the white region can be composed of a plurality of dispersed matrices. Generally, the robot needs to observe the surrounding environment first, and when a square black object is observed, the direction of the field of view of the robot can be adjusted to ensure that the image of the preset identifier is captured, so that the image of the preset identifier is identified.

[0068] In an embodiment, the black region of the preset identifier can be made of light-absorbing material, and the white region can be made of light-reflecting material, so as to further extend the identification distance of the robot to the preset identifier.

[0069] In an example embodiment, the distance between the first recognition result corresponding preset identifier and the robot is greater than the distance between the second recognition result corresponding preset identifier and the robot.

[0070] For example, when the distance between the robot and the preset identifier is far, the robot can capture the pattern composed of the first pattern element and the second pattern element, and when the distance between the robot and the preset identifier is close, the robot can capture the first pattern element. That is, when the target image obtained by the robot capturing the preset identifier includes the first pattern element and the second pattern element, the first recognition result obtained by recognizing the pattern composed of the first pattern element and the second pattern element is the recognition result of recognizing the preset identifier when the robot is far from the preset identifier; when the target image obtained by the robot capturing the preset identifier includes the first pattern element and does not include the second pattern element, the second recognition result obtained by recognizing the first pattern element is the recognition result of recognizing the preset identifier when the robot is close to the preset identifier.

[0071] In the example embodiment of the present application, from the beginning of the robot observing the preset identifier to gradually approaching the preset identifier, multiple images of the preset identifier can be captured and multiple different recognition results can be obtained, that is, the robot is not only controlled according to one recognition result, but also controlled by multiple recognition results obtained by recognizing the preset identifier during the movement of the robot, so that the robot can be more intelligently controlled, thereby improving the sensitivity of the robot.

[0072] In an example embodiment, the first recognition result or the second recognition result includes a current pose relationship between the preset identifier and the robot; wherein the step S102 or the step S103 comprises:

[0073] The step S200 comprises: controlling the robot to move to a first preset area corresponding to the preset identifier according to the current pose relationship, or to avoid a second preset area corresponding to the preset identifier.

[0074] For example, the first recognition result in the example embodiment of the present application includes the pose relationship when the distance between the preset identifier and the robot is far, and the second recognition result includes the pose relationship when the distance between the preset identifier and the robot is close. That is, the robot captures the target image of the preset identifier in the process of approaching the preset identifier, and the distance between the robot and the preset identifier corresponding to the target image is different, so the pose relationship between the robot and the preset identifier corresponding to the recognition result obtained by recognizing the target image is also different. In this way, the pose information of the preset identifier can be obtained during the movement of the robot, so as to control the robot and make the robot make more accurate path planning.

[0075] Specifically, the embodiment of the present application can control the robot to move to the first preset area corresponding to the preset mark according to the current pose relationship between the robot and the preset mark. The first preset area can be the position where the robot performs a task. For example, in the application scenario where the robot performs a serving task in a hotel, the A10 table that needs to be served is the first preset area. During the movement of the robot, the robot needs to be controlled to move to the A10 table and perform the serving operation according to the current pose relationship between the robot and the preset mark pasted on the A10 table.

[0076] As shown in FIG. 1, when the distance between the preset mark and the robot is far, the moving direction of the robot can be adjusted, so that the robot can quickly move to the first preset area in the shortest time; steps S101 to S103 can be repeated during the approach of the robot to the first preset area, so as to update the current pose relationship between the preset mark and the robot; and the moving direction of the robot can be further adjusted according to the updated current pose relationship, so that the robot can accurately move to the first preset area corresponding to the preset mark. Figure 6

[0077] The embodiment of the present application can also control the robot to avoid the second preset area corresponding to the preset mark according to the current pose relationship between the robot and the preset mark. The second preset area can be an area that the robot cannot reach or touch. For example, in the application scenario where the robot performs a patrol task in a power system, the position of the transformer that cannot be touched is the second preset area. Therefore, during the patrol of the robot, the robot can be controlled to avoid the transformer to bypass the transformer for subsequent patrol tasks according to the current pose relationship between the robot and the preset mark pasted on the transformer. Since the pose relationship between the robot and the preset mark is continuously changing, the pose relationship between the robot and the preset mark can be obtained at any time, so that the robot can make more accurate path planning, and the second preset area can be determined and avoided in time when the distance between the robot and the preset mark is far.

[0078] In an exemplary embodiment, the chassis of the robot in the embodiment of the present application is a differential chassis.

[0079] In the embodiment of the present application, the chassis of the robot can be a differential chassis. It should be noted that the working principle of the differential chassis refers to a double-wheel differential moving chassis, which is realized by controlling the speed difference of the two wheels. At present, the chassis of the robot is mostly a differential chassis.

[0080] As shown in FIG. 1, when the distance between the preset mark and the robot is far, the moving direction of the robot can be adjusted, so that the robot can quickly move to the first preset area in the shortest time; steps S101 to S103 can be repeated during the approach of the robot to the first preset area, so as to update the current pose relationship between the preset mark and the robot; and the moving direction of the robot can be further adjusted according to the updated current pose relationship, so that the robot can accurately move to the first preset area corresponding to the preset mark. Figure 7 ​As shown in the prior art, when a robot needs to align with a preset marker and move to a specific position, it generally needs to see the preset marker from a considerable distance and plan a path from its current position to the position corresponding to the preset marker to improve work efficiency. If the robot only starts aligning with the preset marker at a very close distance, since the differential chassis can only move forward and backward, not horizontally, when the direction of the robot's movement deviates from the direction of the preset marker, it needs to continuously move forward and backward to adjust its direction. This process is time-consuming and can easily lead to a decrease in the robot's work efficiency.

[0081] Based on this, such as Figure 2 As shown, the preset marker proposed in this embodiment includes a first pattern element and a second pattern element, and the preset marker can be successfully recognized over a large distance range. Therefore, the preset marker can be observed even when the robot is far away from it. Figure 6 As shown, during the robot's movement toward the preset marker, the identifiable pattern in the preset marker always appears within the robot's field of vision. This allows the robot to adjust its movement direction in a timely manner based on the recognition results obtained from recognizing the preset marker, enabling the robot to quickly move to the target location with the preset marker in the shortest possible time, thereby improving the robot's work efficiency.

[0082] In an exemplary embodiment, step S101 includes steps S1011 and S1012.

[0083] Step S1011: Obtain multiple images of the preset mark captured by the robot using multiple cameras with different focal lengths.

[0084] Step S1012: Select a target image from multiple images, where the clarity of the target image is higher than that of the other images in the multiple images.

[0085] For example, in this application embodiment, a robot can be controlled to take pictures of a preset mark using cameras with different focal lengths to obtain multiple images with different resolutions, and then the target image with the highest resolution can be selected from the multiple images with different resolutions.

[0086] For example, the robot in the embodiments of the present application can include a long-focus camera and a short-focus camera. The image obtained by the long-focus camera shooting the preset mark and the image obtained by the short-focus camera shooting the preset mark can be binarized first; then the field contrast of the two images, i.e. the gray gradient difference between adjacent pixels in the same image, is judged respectively; then, the three regions with the largest gradient difference in each image are selected and cross-contrast is performed on the three regions. For example, three regions with the most obvious contrast in the image shot by the short-focus camera are determined, recorded as a1, a2, a3, and the corresponding gradient differences are 12, 10, and 8 respectively; similarly, three regions with the most obvious contrast in the image shot by the long-focus camera are determined, recorded as b1, b2, b3, and the corresponding gradient differences are 22, 20, and 18 respectively. Obviously, through comparison, it can be determined that the imaging effect of the image shot by the long-focus camera has higher definition, at this time, the image obtained by the long-focus camera shooting the preset mark can be selected as the target image, and the target image is recognized, the target image with higher definition is selected and recognized, which can improve the accuracy of recognition.

[0087] Referring to Figure 8 , Figure 8 is a schematic block diagram of a control device of a robot provided by the embodiments of the present application. The control device of the robot can be configured in a server or an electronic device, and is used for executing the control method of the robot.

[0088] As Figure 8 shown, the control device of the robot includes an acquisition module 110, a first control module 120, and a second control module 130.

[0089] The acquisition module 110 is used for acquiring a target image obtained by a robot shooting a preset mark, the preset mark at least including a first pattern element and a second pattern element, and the first pattern element and the second pattern element at least partially not coinciding.

[0090] The first control module 120 is used for, when the target image includes the first pattern element and the second pattern element, recognizing a pattern formed by the first pattern element and the second pattern element to obtain a first recognition result, and controlling the robot according to the first recognition result.

[0091] The second control module 130 is used for, when the target image includes the first pattern element and does not include the second pattern element, recognizing the first pattern element to obtain a second recognition result, and controlling the robot according to the second recognition result.

[0092] In an exemplary embodiment, the second pattern element is arranged at the periphery of the first pattern element.

[0093] In an example embodiment, the first pattern element and the second pattern element each include a black region and a white region; the black region is made of light-absorbing material, and the white region is made of light-reflecting material.

[0094] In an example embodiment, a distance between the first recognition result corresponding preset identifier and the robot is greater than a distance between the second recognition result corresponding preset identifier and the robot.

[0095] In an example embodiment, the first recognition result or the second recognition result includes a current pose relationship between the preset identifier and the robot.

[0096] The first control module 120 or the second control module 130 is specifically configured to control the robot to move to a first preset area corresponding to the preset identifier or to avoid a second preset area corresponding to the preset identifier according to the current pose relationship.

[0097] In an example embodiment, the chassis of the robot is a differential chassis.

[0098] In an example embodiment, the acquisition module 110 can include a first acquisition submodule and a selection submodule.

[0099] The first acquisition submodule is configured to acquire a plurality of images of the preset identifier captured by the robot through a plurality of cameras with different focal lengths.

[0100] The selection submodule is configured to select a target image from the plurality of images, and the clarity of the target image is higher than that of other images in the plurality of images.

[0101] It should be noted that, for the convenience and brevity of description, the specific working processes of the above-described apparatuses and modules and units can refer to the corresponding processes in the foregoing method embodiments, which will not be described herein.

[0102] The methods of the present application can be implemented in a number of computing / processing environments. For example, these methods can be implemented in the context of a personal computer, a server computer, a handheld or portable device, a tablet device, a multiprocessor system, a microprocessor-based system, a set top box, programmable consumer electronics, a network PC, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The present application can be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, and the like, that perform particular tasks or implement particular abstract data types. The present application can also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules can be located in both local and remote computer storage media including memory storage devices.

[0103] By way of example, the above-described methods, devices, and systems can be implemented in the form of a computer program that can run on a computer device.

[0104] Referring to Figure 9 , Figure 9 is a structural schematic block diagram of a computer device provided by an embodiment of the present application. The computer device can be a server or an electronic device.

[0105] As shown in Figure 9 , the computer device includes a processor, a memory, and a network interface connected through a system bus, wherein the memory can include a storage medium and an internal memory.

[0106] The storage medium can store an operating system and a computer program. The computer program includes program instructions that, when executed, can cause the processor to perform the steps of any of the robot control methods.

[0107] The processor is configured to provide computing and control capabilities to support the operation of the entire computer device.

[0108] The internal memory provides an environment for the execution of the computer program in the storage medium, which, when executed by the processor, can cause the processor to perform the steps of any of the robot control methods.

[0109] The network interface is configured to perform network communication, such as sending assigned tasks, etc.

[0110] Those skilled in the art can understand that Figure 9It should be understood that the structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0111] It should be understood that the processor can be a central processing unit (CPU), and the processor can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0112] In one embodiment, the processor is configured to execute the computer program and implement the following steps when executing the computer program:

[0113] Obtaining a target image obtained by the robot shooting a preset identifier, the preset identifier at least including a first pattern element and a second pattern element, and the first pattern element and the second pattern element at least partially not coinciding;

[0114] When the target image includes the first pattern element and the second pattern element, identifying the pattern formed by the first pattern element and the second pattern element to obtain a first identification result, and controlling the robot according to the first identification result;

[0115] When the target image includes the first pattern element and does not include the second pattern element, identifying the first pattern element to obtain a second identification result, and controlling the robot according to the second identification result.

[0116] In one embodiment, the first identification result or the second identification result includes a current pose relationship between the preset identifier and the robot;

[0117] Controlling the robot according to the first identification result, or controlling the robot according to the second identification result, includes:

[0118] According to the current pose relationship, controlling the robot to move to a first preset area corresponding to the preset identifier, or to avoid a second preset area corresponding to the preset identifier.

[0119] In one embodiment, obtaining the target image obtained by the robot shooting the preset identifier includes:

[0120] obtaining a plurality of images of the preset mark captured by the robot through a plurality of cameras with different focal lengths;

[0121] selecting a target image from the plurality of images, the target image having a higher definition than other images in the plurality of images.

[0122] It should be noted that, for the convenience and brevity of description, the specific working process of the robot control described above can refer to the corresponding process in the embodiments of the robot control method described above, and will not be described here.

[0123] The embodiments of the application also provide a computer readable storage medium, the computer readable storage medium stores a computer program, and the method implemented by the processor when the computer program is executed can refer to each embodiment of the robot control method provided by the application.

[0124] The computer readable storage medium can be an internal storage unit of the computer device, such as a hard disk or a memory of the computer device. The computer readable storage medium can also be an external storage device of the computer device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc.

[0125] It should be understood that the terms used herein in the specification of the application are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in the specification of the application and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0126] It should also be understood that the term "and / or" used in the specification and the appended claims of the application means any combination of one or more of the associated listed items and all possible combinations, and includes these combinations. It should be noted that in this document, the terms "include", "contain" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or system including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or system. Without more limitations, the element defined by the statement "including a" does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0127] The above sequence numbers of the embodiments of the present application are only for description, and do not represent advantages or disadvantages of the embodiments. The above are merely specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical range disclosed by the present application, and these modifications or replacements should be encompassed in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A control method of a robot characterized by, The method comprises the following steps: obtaining a target image of a preset mark photographed by a robot, wherein the preset mark at least comprises a first pattern element and a second pattern element, and the first pattern element and the second pattern element are at least partially non-overlapping; when the target image comprises the first pattern element and the second pattern element, identifying a pattern formed by the first pattern element and the second pattern element to obtain a first identification result; when the target image comprises the first pattern element and does not comprise the second pattern element, identifying the first pattern element to obtain a second identification result; a distance between the preset mark corresponding to the first identification result and the robot is greater than a distance between the preset mark corresponding to the second identification result and the robot; the first identification result or the second identification result comprises a current pose relationship between the preset mark and the robot; controlling the robot to move to a first preset area corresponding to the preset mark or to avoid a second preset area corresponding to the preset mark according to the current pose relationship.

2. The control method of the robot according to claim 1, characterized by, The second pattern element is arranged at the periphery of the first pattern element.

3. The control method of the robot according to claim 2, characterized by, The first pattern element and the second pattern element each comprise a black region and a white region; the black region is made of light-absorbing material, and the white region is made of light-reflecting material.

4. The control method of the robot according to any one of claims 1 to 3, characterized by, The chassis of the robot is a differential chassis.

5. The control method of the robot according to any one of claims 1 to 3, characterized by, The method of obtaining the target image of the preset mark photographed by the robot comprises the following steps: obtaining a plurality of images of the preset mark photographed by the robot through a plurality of cameras with different focal lengths; selecting the target image from the plurality of images, wherein the clarity of the target image is higher than that of other images in the plurality of images.

6. A control device of a robot characterized by comprising: The method comprises the following steps: an obtaining module is configured to obtain a target image of a preset mark photographed by a robot, wherein the preset mark at least comprises a first pattern element and a second pattern element, and the first pattern element and the second pattern element are at least partially non-overlapping; a first control module is configured to, when the target image comprises the first pattern element and the second pattern element, identify a pattern formed by the first pattern element and the second pattern element to obtain a first identification result; a second control module is configured to, when the target image comprises the first pattern element and does not comprise the second pattern element, identify the first pattern element to obtain a second identification result; a distance between the preset mark corresponding to the first identification result and the robot is greater than a distance between the preset mark corresponding to the second identification result and the robot; the first identification result or the second identification result comprises a current pose relationship between the preset mark and the robot; the first control module or the second control module is specifically configured to control the robot to move to a first preset area corresponding to the preset mark or to avoid a second preset area corresponding to the preset mark according to the current pose relationship.

7. A computer device, comprising: The computer device comprises a memory and a processor; the memory is configured to store a computer program; A processor for executing a computer program and implementing the control method of the robot as claimed in any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that A computer program for implementing the control method of the robot as claimed in any one of claims 1 to 5 when executed by a processor.

Images