A relocation system, method, apparatus and storage medium

Abstract

Embodiments of the present application disclose a relocation system, method, device and storage medium. When it is detected that a target mobile robot is out of connection in a specified area, the scheme provided by the present application can trigger a monitoring device and other mobile robots in the specified area to locate the target mobile robot through a server platform, so as to re-manage and control the target mobile robot according to the current position of the target mobile robot after the target mobile robot is located, thereby avoiding that the server platform cannot continue to perform task management on the target mobile robot. In addition, in the present application, the target mobile robot is located according to the monitoring device and other mobile robots in the specified area, so that more position data of the target mobile robot can be obtained, and the location is more accurate.

Description

Technical Field

[0001] This application relates to the field of image recognition, and in particular to a relocation system, method, apparatus and storage medium. Background Technology

[0002] With the development of industry, more and more factories are using mobile robots to perform tasks. For mobile robots performing tasks in factories, they need to report their real-time location on time during the movement process so that the mobile robot management platform can manage the task based on the real-time location of the mobile robot.

[0003] However, if the mobile robot encounters an abnormal state during task execution, such as a power outage, signal loss between the platform and the mobile robot, or a software or hardware error causing the mobile robot to restart, the management platform will lose the mobile robot's signal. Alternatively, the mobile robot may become unaware of its location, be unable to report its real-time location, and continue performing its task. All of these will prevent the management platform from obtaining the mobile robot's real-time location in a timely manner and from continuing to manage the mobile robot's tasks. Summary of the Invention

[0004] This application discloses a relocation system, method, apparatus, and storage medium for relocating a mobile robot when its real-time location cannot be obtained in a timely manner.

[0005] According to a first aspect of the embodiments of this application, a relocation system is provided, the relocation system including a mobile robot in a designated area, monitoring equipment deployed in the designated area, and a server platform for managing and controlling the mobile robot in the designated area;

[0006] The server platform is configured to, when a target mobile robot is detected to be out of contact within a designated area, trigger the monitoring equipment and other mobile robots within the designated area to locate the target mobile robot, and after locating the target mobile robot, re-manage and control the target mobile robot based on its current real location.

[0007] Optionally, the server platform triggering the monitoring device and other mobile robots in the designated area to locate the target mobile robot includes: the server platform notifying the monitoring device and other mobile robots in the designated area of ​​the robot identifier of the target mobile robot;

[0008] The monitoring equipment and the other mobile robots enable visual recognition function according to the notification, so as to identify whether the robot logo exists in the currently captured image based on the visual recognition function. When the robot logo is identified in the currently captured image, the target mobile robot's current position is repositioned by coordinate transformation according to the configured pose parameters, and the repositioned target mobile robot's current position is reported to the server platform.

[0009] Optionally, the monitoring device and the other mobile robots identify whether the robot identifier exists in the currently captured image based on the visual recognition function, including:

[0010] Based on the visual recognition function, the identification confidence level of each object in the currently captured image is calculated, and the identification confidence level is used to indicate whether the object is the robot identification.

[0011] If there is an object in the image with a confidence level higher than the first confidence level threshold, then it is determined that the robot identifier exists in the currently captured image.

[0012] Optionally, when the monitoring device and the other mobile robots identify the presence of the robot identifier in the currently captured image, they are also used to perform coordinate transformation and repositioning based on the configured pose parameters to determine their own current position, and calculate the position confidence of the target mobile robot's current position based on their own current position. The position confidence indicates whether the target mobile robot's current position is the target mobile robot's true position.

[0013] The server platform is also configured to receive identification confidence and / or location confidence reported by the monitoring device and / or other mobile robots, and determine a target location from at least one current location of the target mobile robot received based on the identification confidence and / or location confidence, wherein the target location is the actual location of the target mobile robot.

[0014] Optionally, the server platform is also configured to, after locating the target mobile robot, notify the monitoring device and other mobile robots within the designated area to disable the visual recognition function.

[0015] Optionally, the server platform triggering the monitoring device and other mobile robots within the designated area to locate the target mobile robot includes: the server platform triggering the monitoring device and other mobile robots within the designated area to acquire images;

[0016] When the monitoring equipment and the other mobile robots detect the trigger, they report the collected images to the server platform according to a set period.

[0017] The server platform is also configured to enable a visual recognition function to identify whether the robot identifier exists in the collected images based on the visual recognition function, and when the robot identifier is identified in the collected images, to perform coordinate transformation and reposition the target position of the target mobile robot according to the configured pose parameters corresponding to the collected images.

[0018] Optionally, the server platform identifies whether the robot identifier exists in the collected images based on the visual recognition function, including:

[0019] Based on the visual recognition function, the identification confidence score of each object contained in the collected images is calculated, and the identification confidence score is used to indicate whether the object is the robot identification;

[0020] If there are objects in the collected images with a confidence level higher than the second confidence threshold, then it is determined that the robot identifier exists in the collected images.

[0021] Optionally, the server platform performs coordinate transformation and repositioning to determine the target position of the target mobile robot based on the configured pose parameters corresponding to the acquired image, including:

[0022] For each image containing the robot identifier, coordinate transformation is performed based on the configured pose parameters corresponding to the acquired image to reposition the current position of the monitoring device or other mobile robot that acquired the image, as well as the current position of the target mobile robot in the acquired image.

[0023] The position confidence score of the target mobile robot is calculated based on the current position of the monitoring equipment or other mobile robots. The position confidence score indicates whether the current position of the target mobile robot is the true position of the target mobile robot.

[0024] A target position is determined from at least one current position of the target mobile robot based on the identification confidence and / or position confidence, wherein the target position is the true position of the target mobile robot.

[0025] Optionally, the server platform is also configured to, after locating the target mobile robot, notify the monitoring device and other mobile robots within the designated area to stop reporting images.

[0026] Optionally, the server platform re-manages and controls the target mobile robot based on its current real location, including:

[0027] Record the current real location of the target mobile robot, continue to assign tasks to the target mobile robot based on the real location, and output an alarm prompt if no response from the target mobile robot to the task assignment is received within a set time, so as to prompt the user to go to the real location to handle the target mobile robot.

[0028] According to a second aspect of the embodiments of this application, a relocation method is provided, applied to a server platform in a relocation system, the server platform being used to manage and control a mobile robot within a specified area, the method comprising:

[0029] When a target mobile robot is detected to be out of contact within the designated area, the monitoring equipment and other mobile robots within the designated area are triggered to locate the target mobile robot.

[0030] After locating the target mobile robot, the target mobile robot is re-managed and controlled based on its current real location.

[0031] According to a third aspect of the embodiments of this application, a relocation device is provided, applied to a server platform in a relocation system, the server platform being used to manage and control a mobile robot within a designated area, the device comprising:

[0032] The positioning unit is used to trigger the monitoring equipment and other mobile robots in the designated area to locate the target mobile robot when the target mobile robot is detected to be out of contact in the designated area.

[0033] The management unit is used to re-manage and control the target mobile robot based on its current real location after the target mobile robot has been located.

[0034] According to a fourth aspect of the embodiments of this application, a machine-readable storage medium is provided having a program stored thereon, which, when executed by a processor, implements the relocation method as described above.

[0035] The technical solutions provided by the embodiments of this application may include the following beneficial effects:

[0036] As can be seen from the above technical solutions, when the target mobile robot is detected to be out of contact within a designated area, the solution provided in this application can trigger the monitoring equipment and other mobile robots within the designated area to locate the target mobile robot through the server platform. After locating the target mobile robot, the server platform can re-manage and control the target mobile robot based on its current location, thus avoiding the server platform being unable to continue performing task management for the target mobile robot. Furthermore, by locating the target mobile robot based on the monitoring equipment and other mobile robots within the designated area, more location data of the target mobile robot can be obtained during the location process, resulting in more accurate positioning.

[0037] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0038] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this specification and, together with the description, serve to explain the principles of this specification.

[0039] Figure 1 This is a schematic diagram of the structure of a relocation system provided in an embodiment of this application;

[0040] Figure 2 A flowchart illustrating a relocation method provided in an embodiment of this application;

[0041] Figure 3 A flowchart illustrating the process of determining a target location is provided for an embodiment of this application;

[0042] Figure 4 A schematic diagram illustrating another process for determining a target location provided in an embodiment of this application;

[0043] Figure 5 This is a schematic block diagram of a repositioning device provided in an embodiment of this application. Detailed Implementation

[0044] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0045] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0046] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0047] To enable those skilled in the art to better understand the technical solutions provided in the embodiments of this application, and to make the above-mentioned objectives, features, and advantages of the embodiments of this application more apparent and understandable, the relocation schemes involved in the related technologies are briefly described below:

[0048] In related technologies, when a mobile robot operating in a factory is unable to locate its real-time position due to hardware power failure, software or hardware errors, and other issues, and thus cannot report its current real-time position information to the management platform in a timely manner, the mobile robot will perform self-localization through the surrounding environment. However, when relocating the mobile robot's current real-time position through self-localization, it may be unable to accurately determine the current real-time position due to insufficient information about the surrounding environment, excessive repetitive information in the environment, software malfunctions, etc.

[0049] To address the problems existing in the aforementioned related technologies, this application proposes a method for relocating the current real-time position of a mobile robot when it is detected that the mobile robot has lost contact in a designated area (such as within a factory). This method uses other mobile robots and monitoring devices that are different from the lost mobile robot to relocate its own current real-time position, thus avoiding the problems that occur when the lost mobile robot relocates its own current real-time position and making the relocation of the lost mobile robot more accurate.

[0050] The technical solutions in the embodiments of this application will be further described in detail below with reference to the accompanying drawings.

[0051] See Figure 1 , Figure 1 This is a schematic diagram of a relocation system structure provided in an embodiment of this application. Figure 1As shown, the relocation system in this embodiment of the application includes at least a mobile robot in a designated area, monitoring equipment deployed in the designated area, and a server platform for managing and controlling the mobile robot in the designated area.

[0052] In this embodiment, the designated area can refer to an area within a factory where mobile robots are employed. Under normal circumstances, a mobile robot can work within the designated area according to assigned tasks (such as transporting goods from point A to point B). Monitoring equipment refers to cameras and other monitoring devices within a monitoring system deployed within the designated area. The server platform manages each mobile robot within the designated area. The server platform can assign work tasks to the mobile robots based on their real-time locations, instructing them to work within the designated area.

[0053] In a specific implementation, the server platform in this application embodiment is used to trigger the monitoring equipment and other mobile robots in the designated area to locate the target mobile robot when the target mobile robot is detected to be out of contact in the designated area, and after the target mobile robot is located, to re-manage and control the target mobile robot according to the current real location of the mobile robot.

[0054] As an example, to facilitate the management of mobile robots by the server platform, each mobile robot connected to the server platform will report its real-time location information to the server platform at a preset period when performing tasks. Therefore, if the server platform does not receive location information reported by the target mobile robot performing a task in a specified area within a specified time, the server platform can determine that the target mobile robot is out of contact in the specified area. After determining that the target mobile robot is out of contact, the server platform can obtain the robot identifier corresponding to the target mobile robot based on the registration information pre-registered by the target mobile robot in the server platform.

[0055] In this embodiment, if the server platform determines that the target mobile robot has lost contact within a designated area, the relocation system provided in this embodiment can relocate the target mobile robot in the following two ways:

[0056] Example 1:

[0057] As an example, visual recognition can identify objects in any image. Therefore, if the monitoring equipment and other mobile robots in the designated area are equipped with visual recognition, in this embodiment, when the server platform detects that the target mobile robot has lost contact, it can notify the monitoring equipment and other mobile robots in the designated area of ​​the target mobile robot's robot identifier. The target mobile robot's robot identifier can refer to a unique identifier such as its number or icon. The server platform can broadcast the target mobile robot's robot identifier to the monitoring equipment and other mobile robots.

[0058] Upon receiving a notification from the aforementioned server platform, monitoring equipment and other mobile robots can activate the visual recognition function to identify whether the target robot's robot identifier exists in the currently captured image. When the robot identifier is identified in the currently captured image, the target mobile robot's current position is repositioned based on the configured pose parameters through coordinate transformation, and the repositioned target mobile robot's current position is reported to the server platform.

[0059] Optionally, the monitoring equipment and other mobile robots can identify whether the robot identifier exists in the currently captured image based on the visual recognition function in the following way: First, calculate the identifier confidence level corresponding to each object contained in the currently captured image based on the visual recognition function. The identifier confidence level is used to indicate whether the object is the robot identifier of the target robot. Then, if there is an object in the image with an identifier confidence level higher than the first confidence level threshold, it is determined that the robot identifier of the target robot exists in the currently captured image.

[0060] In this embodiment, the visual recognition function can identify whether each object in the currently captured image is similar to the robot identifier, and the degree of similarity. Optionally, the identifier confidence score of any object can be obtained based on the similarity score between the object and the robot identifier. The higher the identifier confidence score, the higher the probability that the object is a robot identifier. In this embodiment, the visual recognition function can use various methods to identify whether each object is a robot identifier and to calculate the identifier confidence score of each object. For specific details, please refer to related technologies; this application is not limited in this regard.

[0061] Optionally, when monitoring equipment and other mobile robots identify the presence of a robot identifier in the currently captured image, they can also perform coordinate transformation and repositioning based on the configured pose parameters to determine their own current position. Based on their own current position, they can calculate the position confidence of the target mobile robot's current position, which indicates whether the target mobile robot's current position is the target mobile robot's true position.

[0062] In this embodiment, for any monitoring device or any other mobile robot, the closer the distance between its current position relocated to the current position of the target mobile robot, the greater the confidence level of the calculated current position of the target mobile robot will be, indicating that the probability that the relocated current position of the target mobile robot is the true position of the target mobile robot is higher.

[0063] In this embodiment, the server platform is also used to receive identification confidence and / or location confidence reported by monitoring devices and / or other mobile robots. Based on the identification confidence and / or location confidence, the server platform can determine the target location from at least one current location of the target mobile robot received, thereby determining the target location as the true location of the target mobile robot.

[0064] Optionally, the server platform can determine the target location from at least one current location of the target mobile robot received, based on the identifier confidence level or the location confidence level, and thus determine that target location as the true location of the target mobile robot. For example, the current location of the target mobile robot corresponding to the highest identifier confidence level can be selected as the true location of the target mobile robot, or the current location of the target mobile robot corresponding to the highest location confidence level can be selected as the true location of the target mobile robot.

[0065] Optionally, the server platform can also determine the target location from at least one current location of the target mobile robot received based on the identifier confidence score and the location confidence score: For each monitoring device and / or other mobile robot reporting the identifier confidence score, location confidence score, and current location of the target mobile robot, the platform can first select the current location of at least one target mobile robot corresponding to the highest identifier confidence score, and then select the current location of the target mobile robot corresponding to the highest location confidence score from the selected at least one target mobile robot current locations, and determine that current location of the target mobile robot as the target location of the target mobile robot; or, the platform can first select the current location of at least one target mobile robot corresponding to the highest location confidence score, and then select the current location of the target mobile robot corresponding to the highest identifier confidence score from the selected at least one target mobile robot current locations, and determine that current location of the target mobile robot as the target location of the target mobile robot.

[0066] Optionally, the server platform can determine the target location from at least one current location of the target mobile robot received based on the identifier confidence score and the location confidence score. Alternatively, it can use the following method: For the identifier confidence score, location confidence score, and current location of the target mobile robot reported by each monitoring device and / or other mobile robot, a comprehensive confidence score can be obtained by performing a specified calculation on the identifier confidence score and the location confidence score. Then, the current location of the target mobile robot corresponding to the highest comprehensive confidence score is selected, and the current location of the target mobile robot is determined as the target location of the target mobile robot.

[0067] In this embodiment, after locating the target mobile robot (i.e., obtaining the target location of the target mobile robot), the server platform can further notify the monitoring equipment and other mobile robots in the designated area to turn off the visual recognition function and stop recognizing the robot identifier of the target robot from the currently captured image.

[0068] This embodiment has now completed the repositioning of the target mobile robot.

[0069] The above describes one way a relocation system can relocate a target mobile robot. The following describes another way a relocation system can relocate a target mobile robot:

[0070] Example 2:

[0071] As another embodiment, if the monitoring equipment and other mobile robots do not have visual recognition capabilities, visual recognition functionality can be added to the server platform. When the server platform detects that the target robot has lost contact, it can trigger only the monitoring equipment and other mobile robots within a designated area to collect images. Upon detecting this trigger, the monitoring equipment and other mobile robots within the designated area will then report the collected images to the server platform according to a set cycle.

[0072] In this embodiment, when the server platform detects that the target robot has lost contact, it will enable the visual recognition function to identify whether the robot identifier of the target robot exists in the collected images. When the robot identifier is identified in the collected images, the target position of the target mobile robot will be repositioned by coordinate transformation according to the configured pose parameters corresponding to the collected images.

[0073] In this embodiment, when the server platform identifies whether the target robot's robot identifier exists in the collected images based on the visual recognition function, it can first calculate the identifier confidence score corresponding to each object in the collected images based on the visual recognition function. This identifier confidence score is used to indicate whether the object is the target robot's robot identifier. Then, if an object with an identifier confidence score higher than a second confidence score threshold is detected in the collected images, it is determined that the target robot's robot identifier exists in the collected images. The calculation of the identifier confidence score can refer to the above embodiment, and will not be repeated here.

[0074] In this embodiment, the server platform can also perform coordinate transformation and repositioning on each image with a robot identifier containing a target robot, based on the configured pose parameters corresponding to the acquired image, to determine the current position of the monitoring device or other mobile robot that acquired the image, as well as the current position of the target mobile robot in the acquired image. Then, based on the current position of the monitoring device or other mobile robot, the platform calculates the position confidence of the target mobile robot's current position, which indicates whether the current position of the target mobile robot is the true position of the target mobile robot.

[0075] Furthermore, the server platform can determine the target location from at least one current location of the target mobile robot based on the identifier confidence level and / or location confidence level. This target location is the true location of the target mobile robot. The specific method by which the server platform determines the target location can be found in the above embodiments and will not be repeated here.

[0076] In this embodiment, after locating the target mobile robot, the server platform will notify the monitoring equipment and other mobile robots in the designated area to stop reporting images.

[0077] This embodiment has now completed the repositioning of the target mobile robot.

[0078] As an example, after locating the target mobile robot using any of the above methods, the server platform can re-manage and control the target mobile robot based on its current real location in the following ways: recording the target mobile robot's current real location, continuing to assign tasks to the target mobile robot based on that real location, and outputting an alarm prompt if no response from the target mobile robot to the task assignment is received within a set time, so as to prompt the user to go to the real location to handle the target mobile robot.

[0079] After the server platform locates the target mobile robot, it can add the target mobile robot's current real location to the target mobile robot's real-time location log. Based on this real location, it can continue to assign tasks to the target mobile robot, such as instructing the target mobile robot to continue to execute previously unfinished tasks, or issuing new tasks to the target mobile robot based on this real location.

[0080] This concludes the description of the relocation system in the embodiments of this application.

[0081] In this embodiment, when a target mobile robot is detected to be out of contact within a designated area, the server platform can trigger monitoring equipment and other mobile robots within the designated area to locate the target mobile robot. Once the target mobile robot is located, its current location allows for renewed management and control, preventing the server platform from being unable to continue managing the target mobile robot. Furthermore, this method of locating the target mobile robot based on monitoring equipment and other mobile robots within the designated area allows for the acquisition of more location data, resulting in more accurate positioning.

[0082] It should be noted that the pose parameters corresponding to the image in the above embodiments refer to the homography matrix pre-set for the mobile robot or monitoring device that captured the image. For any image containing a target mobile robot, the pixel coordinates of the target mobile robot's image pixels in the image can be identified. Then, using the homography matrix, the pixel coordinates of the target mobile robot's image pixels in the image are converted into position coordinates in a specified area. These position coordinates are used as the current position of the target mobile robot calculated from the image.

[0083] As an example, when the device capturing the image is a surveillance device, the homography matrix in the surveillance device can be obtained by calculating the correspondence between the pixel coordinates of each object in the image captured by the image acquisition device and the position coordinates of each object in the specified area, based on the fixed position coordinates of the surveillance device deployed in the specified area. Here, the position coordinates of each object in the specified area refer to the position coordinates in the visual coordinate system pre-established in the specified area.

[0084] As another embodiment, when the device for capturing the image is another mobile robot, since the other mobile robot may be in a moving state, when using the homography matrix in the other mobile robot, it is also necessary to first obtain the current position coordinates of the other mobile robot. Based on the current position coordinates of the other mobile robot and the homography matrix, the pixel coordinates of the target mobile robot's image in the image captured by the other mobile robot are converted into position coordinates in a specified area, and the position coordinates are used as the current position of the target mobile robot.

[0085] Based on the positioning of the target mobile robot by other mobile robots, if the target mobile robot runs into the current blind spot of the monitoring equipment and other mobile robots, since the other mobile robots may be in a moving state, as the other mobile robots move, they can move to the vicinity of the blind spot, and then the other mobile robots can take pictures containing the target mobile robot. This embodiment can further avoid the inability to relocate the target mobile robot when it is in the blind spot.

[0086] The relocation method provided in the embodiments of this application is described below. This application provides a relocation method applied to a server platform in a relocation system. For example... Figure 2 As shown, the method includes the following steps:

[0087] Step 201: When the target mobile robot is detected to be out of contact in the designated area, the monitoring equipment and other mobile robots in the designated area are triggered to locate the target mobile robot.

[0088] Step 202: After locating the target mobile robot, re-manage and control the target mobile robot based on its current real location.

[0089] Optionally, if visual recognition functionality is installed in the monitoring equipment and other mobile robots within the designated area, the target mobile robot can be triggered to locate the monitoring equipment and other mobile robots within the designated area through methods such as... Figure 3 The method shown:

[0090] Step 301: Notify the monitoring equipment and other mobile robots in the designated area of ​​the robot identifier of the target mobile robot.

[0091] As one embodiment, the robot identifier of the target mobile robot can be notified to the monitoring equipment and other mobile robots within a designated area, enabling the monitoring equipment and other mobile robots to activate visual recognition functions based on the notification. The monitoring equipment and other mobile robots can use visual recognition to identify whether the target robot's robot identifier exists in the currently captured image. Upon identifying the robot identifier, they can perform coordinate transformation based on configured pose parameters to reposition the target mobile robot's current location and report the repositioned location to the server platform.

[0092] Step 302: Determine the target position from at least one current position of the received target mobile robot.

[0093] When the monitoring equipment and other mobile robots within the designated area have enabled visual recognition, the monitoring equipment and other mobile robots within the designated area can further calculate the identification confidence of each object in the collected images based on the visual recognition function, and / or, when the robot identification is identified in the currently captured image based on the identification confidence, the robot performs coordinate transformation and repositions itself according to the configured pose parameters, calculates the position confidence of the target mobile robot's current position based on its own current position, and reports the identification confidence and / or position confidence to the server platform.

[0094] When the monitoring equipment and other mobile robots within the designated area report the identification confidence level and / or location confidence level to the server platform, the server platform can determine the target location from at least one current location of the target mobile robot received based on the identification confidence level and / or location confidence level. The target location is the true location of the target mobile robot.

[0095] Furthermore, after locating the target mobile robot, the monitoring equipment and other mobile robots within the designated area can be notified to disable the aforementioned visual recognition function.

[0096] Optionally, if the server platform has visual recognition capabilities installed, the target mobile robot can also be triggered by monitoring equipment and other mobile robots within a designated area to locate the target mobile robot through methods such as... Figure 4 The method shown:

[0097] Step 401: Trigger the monitoring equipment and other mobile robots in the designated area to collect images, so that when the monitoring equipment and other mobile robots detect the trigger, they will report the collected images to the server platform according to the set period.

[0098] Step 402: Based on the visual recognition function, identify whether there is a robot identifier of the target robot in the collected images. When the robot identifier is identified in the collected images, perform coordinate transformation and reposition the target position of the target mobile robot according to the configured pose parameters corresponding to the collected images. The target position is the real position of the target mobile robot.

[0099] Furthermore, after locating the target mobile robot, the monitoring equipment and other mobile robots within the designated area can be notified to stop reporting images.

[0100] Optionally, after relocating the target mobile robot, the server platform may re-manage and control the target mobile robot based on its current real location, including: recording the target mobile robot's current real location, continuing to assign tasks to the target mobile robot based on that real location, and outputting an alarm prompt if no response to the task assignment is received from the target mobile robot within a set time, so as to prompt the user to go to the real location to handle the target mobile robot.

[0101] This concludes the description of the relocation method embodiments provided in this application.

[0102] The following describes a repositioning device provided in an embodiment of this application. Figure 5 As shown, this device is used on a server platform in a relocation system, and the device includes:

[0103] The positioning unit 501 is used to trigger the monitoring device and other mobile robots in the designated area to locate the target mobile robot when the target mobile robot is detected to be out of contact in the designated area.

[0104] The management unit 502 is used to re-manage and control the target mobile robot according to its current real location after the target mobile robot is located.

[0105] Optionally, the positioning unit 501 triggering the monitoring device and other mobile robots in the designated area to locate the target mobile robot includes: the server platform notifying the monitoring device and other mobile robots in the designated area of ​​the robot identifier of the target mobile robot.

[0106] Optionally, the positioning unit 501 triggering the monitoring device and other mobile robots within the designated area to locate the target mobile robot includes: the server platform triggering the monitoring device and other mobile robots within the designated area to acquire images.

[0107] Optionally, the positioning unit 501 is further configured to receive the identification confidence level and / or location confidence level reported by the monitoring device and / or the other mobile robot, and determine the target location from at least one current location of the target mobile robot received based on the identification confidence level and / or location confidence level, wherein the target location is the true location of the target mobile robot.

[0108] Optionally, the positioning unit 501 is further configured to enable a visual recognition function to identify whether the robot identifier exists in the collected images based on the visual recognition function, and when the robot identifier is identified in the collected images, to perform coordinate transformation and reposition the target position of the target mobile robot according to the configured pose parameters corresponding to the collected images.

[0109] Optionally, the management unit 502 is further configured to, after locating the target mobile robot, notify the monitoring device and other mobile robots in the designated area to disable the visual recognition function.

[0110] Optionally, the management unit 502 is further configured to, after locating the target mobile robot, notify the monitoring device and other mobile robots in the designated area to stop reporting images.

[0111] Optionally, the management unit 502 may re-manage and control the target mobile robot based on its current real location, including: recording the current real location of the target mobile robot, continuing to assign tasks to the target mobile robot based on the real location, and outputting an alarm prompt when no response from the target mobile robot to the task assignment is received within a set time, so as to prompt the user to go to the real location to process the target mobile robot.

[0112] The specific implementation process of the above method and device embodiments can be referred to the embodiments described in the above relocation system, and will not be repeated here.

[0113] Correspondingly, embodiments of this application also provide a machine-readable storage medium storing a program thereon, which, when executed by a processor, implements the relocation method as described above.

[0114] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A relocation system, characterized in that, The relocation system includes a mobile robot within a designated area, monitoring equipment deployed within the designated area, and a server platform for managing and controlling the mobile robot within the designated area. The server platform is used to trigger the monitoring device and other mobile robots in the designated area to locate the target mobile robot when the target mobile robot is detected to be out of contact in the designated area, and to re-manage and control the target mobile robot according to its current real location after the target mobile robot is located. The true location of the target mobile robot is determined as follows: For each of the monitoring device and other mobile robots, the identification confidence level of each object in the image currently captured by the device is calculated based on the visual recognition function. The identification confidence level is used to indicate whether the object is the robot identification of the target mobile robot. The current position of the target mobile robot and the current position of the device are repositioned by coordinate transformation according to the pose parameters configured by the device. The position confidence level of the target mobile robot's current position is calculated based on the current position of the device itself. The position confidence level indicates whether the current position of the target mobile robot is the true position of the target mobile robot. The pose parameters are determined based on the correspondence between the pixel coordinates of each object in the image captured by the device and the position coordinates of each object in a specified area. The true position of the target mobile robot is determined from at least one current position of the target mobile robot based on each identification confidence level and / or each position confidence level.

2. The system according to claim 1, characterized in that, The server platform triggering the monitoring device and other mobile robots within the designated area to locate the target mobile robot includes: the server platform notifying the monitoring device and other mobile robots within the designated area of ​​the robot identifier of the target mobile robot; The monitoring equipment and the other mobile robots enable visual recognition function according to the notification, so as to identify whether the robot logo exists in the currently captured image based on the visual recognition function. When the robot logo is identified in the currently captured image, the target mobile robot's current position is repositioned by coordinate transformation according to the configured pose parameters, and the repositioned target mobile robot's current position is reported to the server platform.

3. The system according to claim 2, characterized in that, The monitoring equipment and the other mobile robots identify whether the robot identifier exists in the currently captured image based on the visual recognition function, including: Based on the visual recognition function, the identification confidence level of each object in the currently captured image is calculated, and the identification confidence level is used to indicate whether the object is the robot identification. If there is an object in the image with a confidence level higher than the first confidence level threshold, then it is determined that the robot identifier exists in the currently captured image.

4. The system according to claim 3, characterized in that, When the monitoring device and the other mobile robots identify the presence of the robot identifier in the currently captured image, they are also used to perform coordinate transformation and repositioning based on the configured pose parameters to determine their own current position, and calculate the position confidence of the target mobile robot's current position based on their own current position. The position confidence indicates whether the target mobile robot's current position is the target mobile robot's true position. The server platform is also configured to receive identification confidence and / or location confidence reported by the monitoring device and / or other mobile robots, and determine a target location from at least one current location of the target mobile robot received based on the identification confidence and / or location confidence, wherein the target location is the actual location of the target mobile robot.

5. The system according to any one of claims 2 to 4, characterized in that, The server platform is also used to notify the monitoring equipment and other mobile robots in the designated area to turn off the visual recognition function after the target mobile robot is located.

6. The system according to claim 1, characterized in that, The server platform triggering the monitoring device and other mobile robots within the designated area to locate the target mobile robot includes: the server platform triggering the monitoring device and other mobile robots within the designated area to acquire images; When the monitoring equipment and the other mobile robots detect the trigger, they report the collected images to the server platform according to a set period. The server platform is also configured to enable a visual recognition function to identify whether the robot identifier exists in the collected images based on the visual recognition function, and when the robot identifier is identified in the collected images, to perform coordinate transformation and reposition the target position of the target mobile robot according to the configured pose parameters corresponding to the collected images.

7. The system according to claim 6, characterized in that, The server platform identifies whether the robot identifier exists in the collected images based on the visual recognition function, including: Based on the visual recognition function, the identification confidence score of each object contained in the collected images is calculated, and the identification confidence score is used to indicate whether the object is the robot identification; If there are objects in the collected images with a confidence level higher than the second confidence threshold, then it is determined that the robot identifier exists in the collected images.

8. The system according to claim 7, characterized in that, The server platform performs coordinate transformation and repositioning to determine the target position of the target mobile robot based on the configured pose parameters corresponding to the acquired image, including: For each image containing the robot identifier, coordinate transformation is performed based on the configured pose parameters corresponding to the acquired image to reposition the current position of the monitoring device or other mobile robot that acquired the image, as well as the current position of the target mobile robot in the acquired image. The position confidence score of the target mobile robot is calculated based on the current position of the monitoring equipment or other mobile robots. The position confidence score indicates whether the current position of the target mobile robot is the true position of the target mobile robot. A target position is determined from at least one current position of the target mobile robot based on the identification confidence and / or position confidence, wherein the target position is the true position of the target mobile robot.

9. The system according to any one of claims 6 to 8, characterized in that, The server platform is also used to notify the monitoring equipment and other mobile robots in the designated area to stop reporting images after the target mobile robot is located.

10. The system according to claim 1, characterized in that, The server platform re-manages and controls the target mobile robot based on its current real location, including: Record the current real location of the target mobile robot, continue to assign tasks to the target mobile robot based on the real location, and output an alarm prompt if no response from the target mobile robot to the task assignment is received within a set time, so as to prompt the user to go to the real location to handle the target mobile robot.

11. A relocation method, characterized in that, A server platform applied in a relocation system, the server platform being used to manage and control mobile robots within a designated area, the method comprising: When a target mobile robot is detected to be out of contact within the designated area, the monitoring devices and other mobile robots within the designated area are triggered to locate the target mobile robot. The true location of the target mobile robot is determined as follows: For each of the monitoring devices and other mobile robots, the identification confidence score of each object in the currently captured image is calculated based on visual recognition. The identification confidence score indicates whether the object is the robot identification of the target mobile robot. The current location of the target mobile robot and the device itself are repositioned based on the device's configured pose parameters. The location confidence score of the target mobile robot's current location is calculated based on the device's own current location. The location confidence score indicates whether the target mobile robot's current location is its true location. The pose parameters are determined based on the correspondence between the pixel coordinates of each object in the captured image and the position coordinates of each object in the designated area. The true location of the target mobile robot is determined from at least one of its current locations based on the identification confidence score and / or the location confidence score. After locating the target mobile robot, the target mobile robot is re-managed and controlled based on its current real location.

12. A repositioning device, characterized in that, A server platform for use in a relocation system, the server platform being used to manage and control mobile robots within a designated area, the device comprising: A positioning unit is configured to, upon detecting that a target mobile robot has lost contact within a designated area, trigger monitoring devices and other mobile robots within the designated area to locate the target mobile robot. The true location of the target mobile robot is determined as follows: for each of the monitoring devices and other mobile robots, a confidence score for the identifier of each object in the currently captured image is calculated based on visual recognition, the confidence score indicating whether the object is the robot identifier of the target mobile robot; the current location of the target mobile robot and the device itself are repositioned based on the device's configured pose parameters; a position confidence score for the target mobile robot's current location is calculated based on the device's own current location, indicating whether the current location is the target mobile robot's true location; the pose parameters are determined based on the correspondence between the pixel coordinates of each object in the captured image and the position coordinates of each object in the designated area; and the true location of the target mobile robot is determined from at least one of its current locations based on the identifier confidence score and / or the position confidence score. The management unit is used to re-manage and control the target mobile robot based on its current real location after the target mobile robot has been located.

13. A machine-readable storage medium, characterized in that, It stores a program that, when executed by a processor, implements the relocation method as described in claim 11.

Images