Robots and methods, systems, storage media, workstations for same

Abstract

The application discloses a robot, a method for identifying a work station of the robot, a system for identifying the work station of the robot, the robot, a computer storage medium, the work station, and a work station system. The robot is provided with a laser device, the work station is provided with an identification image, the identification image is formed with at least three continuous regions with varying reflection intensity in the scanning direction of the laser device, and the method for identifying the work station of the robot comprises the following steps: acquiring point cloud data of the laser device scanning the surrounding environment; the point cloud data comprises coordinate information and first reflection intensity information; clustering the point cloud data based on the coordinate information and the first reflection intensity information to determine the spatial information and second reflection intensity information of each point cloud data set formed by clustering; and matching the point cloud data set based on the region information of the identification image to identify the work station.

Description

Technical Field

[0001] This application relates to the field of robotics technology, specifically to a robot and a method for recognizing a workstation therebetween, a system for recognizing a workstation by a robot, a robot, a computer storage medium, a workstation, and a robot system. Background Technology

[0002] With the development of automation technology and artificial intelligence, robots are widely used in various situations to replace manual labor. For example, in some scenarios, robots clean floor surfaces instead of humans. However, after working for a certain period of time, robots usually need to dock with a workstation so that the workstation can provide services such as charging the robot, adding clean water, and discharging wastewater. These services all require the robot to be able to dock accurately.

[0003] Existing technologies typically include two solutions: infrared guidance and image recognition. Infrared guidance requires an infrared sensor on the workstation specifically for guiding the robot's docking. Infrared sensors are only accurate at close range, which is sufficient for small-area applications like home environments, but unsuitable for large-area applications such as supermarkets and hotels. Image recognition, on the other hand, has limitations. Firstly, it is less adaptable to changing lighting conditions; changes in light intensity or color can cause errors in the robot's recognition of the workstation. Secondly, image recognition relies on visual sensors on the robot, but in some applications where robots only use laser sensors for recognition and navigation, image recognition is not applicable. Summary of the Invention

[0004] In view of the shortcomings of the above-mentioned related technologies, the purpose of this application is to provide a robot and a method for recognizing a workstation, a system for recognizing a robot workstation, a robot, a computer storage medium, a workstation, and a workstation system, so as to overcome the technical problems of poor recognition effect and adaptability in the above-mentioned related technologies.

[0005] To achieve the above and other related objectives, the first aspect of this application discloses a method for identifying a robot workstation. The robot is equipped with a laser device, and the workstation is equipped with a marker image. The marker image forms at least three continuous regions with varying reflection intensity in the scanning direction of the laser device. The method includes: acquiring point cloud data of the surrounding environment scanned by the laser device; the point cloud data includes coordinate information and first reflection intensity information; clustering the point cloud data based on the coordinate information and the first reflection intensity information to determine the spatial information and second reflection intensity information of each point cloud dataset formed by the clustering; and matching the point cloud dataset based on the region information of the marker image to identify the workstation.

[0006] In some embodiments of the first aspect of this application, the region information of the marker image is set to be pre-stored in a storage device, including the width distribution information and intensity distribution information of each region of the marker image.

[0007] In some embodiments of the first aspect of this application, the step of clustering the point cloud data based on the coordinate information and the first reflection intensity information to determine the spatial information and second reflection intensity information of each point cloud dataset formed by the clustering includes: clustering point cloud data that are spatially continuous and whose reflection intensity is within a preset range into a class of point cloud datasets; wherein, the spatial continuity is determined based on the coordinate information of the point cloud data; the reflection intensity being within a preset range is determined based on the first reflection intensity information of the point cloud data; and determining the spatial information and second reflection intensity information of the point cloud dataset based on the coordinate information and the first reflection intensity information of each point cloud data in the point cloud dataset.

[0008] In some embodiments of the first aspect of this application, the spatial information of the point cloud dataset includes: location information and length information; wherein the location information is used to reflect the relative position of the point cloud dataset in space, and the length information is used to reflect the span range of the point cloud dataset.

[0009] In some embodiments of the first aspect of this application, the second reflection intensity information is obtained based on the first reflection intensity information of the point cloud data in the point cloud dataset.

[0010] In some embodiments of the first aspect of this application, the step of matching the point cloud dataset with the region information of the marked image to identify the workstation includes: determining a comparison dataset that satisfies a first matching condition and a second matching condition as a target dataset based on the region information of the marked image, so as to identify the workstation based on the target dataset; wherein, the comparison dataset refers to multiple point cloud datasets that are spatially continuous and whose number is consistent with the number of regions of the marked image; wherein, the first matching condition is that the spatial information of each point cloud dataset in the comparison dataset is consistent with the width distribution information of each region of the marked image; the second matching condition is that the second reflection intensity information of each point cloud dataset in the comparison dataset is consistent with the intensity distribution information of each region.

[0011] In some embodiments of the first aspect of this application, the method further includes: determining the positional relationship between the workstation and the robot based on the target dataset, so as to control the robot to dock with the workstation.

[0012] In some embodiments of the first aspect of this application, the step of determining a guidance route based on the target dataset so that the robot docks with the workstation based on the guidance route includes: selecting a feature dataset based on the spatial information or second reflection intensity information of each point cloud dataset in the target dataset; performing line segment fitting on the feature dataset to determine the center point and normal vector of the fitted line segment; and controlling the robot to dock with the workstation based on the positional relationship between the center line and the normal vector relative to the robot.

[0013] In some embodiments of the first aspect of this application, the method further includes: determining an error compensation parameter, the error compensation parameter being used to compensate for the positional relationship of the workstation relative to the robot.

[0014] In some embodiments of the first aspect of this application, the two adjacent regions have a grayscale difference to form the change in reflectance intensity.

[0015] In some embodiments of the first aspect of this application, the marking image is formed in the scanning direction of the laser device, comprising three consecutive regions of black, white, and black.

[0016] In some embodiments of the first aspect of this application, the logo image is provided with three parts: black, white, and black arranged side by side.

[0017] In some embodiments of the first aspect of this application, the marking image is configured such that the black portion surrounds the white portion in a U-shape to form three consecutive regions with varying reflectance in the scanning direction of the laser device.

[0018] In some embodiments of the first aspect of this application, the step of acquiring point cloud data of the surrounding environment scanned by the laser device includes: controlling the robot to move to a predetermined area based on a reference pose information; wherein, within the predetermined area, the laser device can scan the marker image; and controlling the laser device to scan the surrounding environment to acquire point cloud data including the marker image.

[0019] In some embodiments of the first aspect of this application, the robot is a cleaning robot.

[0020] The second aspect of this application discloses a system for identifying a robot workstation. The robot is equipped with a laser device, and the workstation is equipped with a marker image. The marker image forms at least three continuous regions with varying reflection intensity in the scanning direction of the laser device. The system includes: an acquisition module for acquiring point cloud data of the surrounding environment scanned by the laser device; the point cloud data includes coordinate information and first reflection intensity information; a clustering module for clustering the point cloud data based on the coordinate information and the first reflection intensity information to determine the spatial information and second reflection intensity information of each point cloud dataset formed by the clustering; and a matching module for matching the point cloud dataset based on the region information of the marker image to identify the workstation.

[0021] The third aspect of this application discloses a robot, comprising: a laser device disposed on the top of the robot to scan the surrounding environment; a moving device disposed on the bottom of the robot to drive the robot to move; and a control device disposed on the robot for controlling the laser device and the moving device to work together to perform a robot recognition workstation method as described in any embodiment of the first aspect of this application.

[0022] The fourth aspect of this application discloses a computer storage medium storing at least one program, which, when invoked, executes the method of a robot recognition workstation as described in any embodiment of the first aspect of this application.

[0023] The fifth aspect of this application discloses a workstation, comprising: a workstation body, a service interface provided thereon, the workstation providing services to a robot based on the service interface, the robot including a laser device; and a marker image disposed on the workstation body and located on the surface of the service interface; wherein the marker image has at least three regions with contrasting reflectance in the scanning direction of the laser device.

[0024] The sixth aspect of this application discloses a robot system, comprising: a robot as described in any embodiment of the third aspect of this application, and a workstation as described in any embodiment of the fifth aspect of this application.

[0025] In summary, the robot, its workstation identification method, system, robot, computer storage medium, workstation, and workstation system disclosed in this application identify the identification image by setting a two-dimensional marker image on the workstation. This marker image has at least three consecutive regions with contrasting reflective intensity in the scanning direction of the laser device mounted on the robot, thereby enabling identification of the marker image through a combination of spatial characteristics and reflective intensity characteristics. This method only requires setting a two-dimensional plane as the marker on the workstation, eliminating the need for complex structural design and simplifying the manufacturing process, significantly reducing production costs. Furthermore, using a two-dimensional plane as the marker greatly improves the robot's perception distance of the workstation, making it particularly suitable for robots operating in large areas. In addition, the method of identifying the marker image by combining spatial characteristics and reflective intensity characteristics in this application achieves high accuracy and avoids misidentification.

[0026] Other aspects and advantages of this application will readily be apparent to those skilled in the art from the detailed description below. Only exemplary embodiments of this application are shown and described in the following detailed description. As will be appreciated by those skilled in the art, the content of this application enables them to make modifications to the disclosed specific embodiments without departing from the spirit and scope of the invention to which this application pertains. Accordingly, the descriptions in the accompanying drawings and specification of this application are merely exemplary and not restrictive. Attached Figure Description

[0027] The specific features of the invention involved in this application are shown in the appended claims. The features and advantages of the invention can be better understood by referring to the exemplary embodiments and drawings described in detail below. A brief description of the drawings is as follows:

[0028] Figure 1 The diagram shows the scanning direction of the laser device in one embodiment of this application.

[0029] Figure 2 The diagram shown is a schematic representation of the overall pattern of the identifier image in one embodiment of this application.

[0030] Figure 3 The diagram shows an overall pattern of the identifier image in another embodiment of this application.

[0031] Figure 4 The diagram shown is a flowchart illustrating a method for using a robot recognition workstation according to one embodiment of this application.

[0032] Figure 5 The diagram shows a flowchart of acquiring point cloud data in one embodiment of this application.

[0033] Figure 6The diagram shows the position and orientation of the robot relative to the workstation in one embodiment of this application.

[0034] Figure 7 The diagram shown is a flowchart of step S120 in one embodiment of this application.

[0035] Figure 8 The image shown is a schematic diagram of point cloud data corresponding to the identifier image in one embodiment of this application.

[0036] Figure 9 The diagram shown illustrates a mismatch method in one embodiment of this application.

[0037] Figure 10 The diagram shown is a flowchart of a robot docking workstation according to one embodiment of this application.

[0038] Figure 11 The diagram shown is a structural schematic of a robot according to one embodiment of this application.

[0039] Figure 12 The diagram shown is a schematic representation of the system architecture of a robot recognition workstation according to one embodiment of this application. Detailed Implementation

[0040] The following specific embodiments illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification.

[0041] In the following description, reference is made to the accompanying drawings, which illustrate several embodiments of the present application. It should be understood that other embodiments may also be used, and changes in module or unit composition, electrical and operational aspects may be made without departing from the spirit and scope of this disclosure. The following detailed description should not be considered limiting, and the scope of the embodiments of the present application is defined solely by the claims of the published patents. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the present application.

[0042] While the terms first, second, etc., are used in some instances herein to describe various elements or parameters, these elements or parameters should not be limited by these terms. These terms are used only to distinguish one element or parameter from another. For example, first reflection intensity information may be referred to as second reflection intensity information, and similarly, second reflection intensity information may be referred to as first reflection intensity information, without departing from the scope of the various described embodiments. Both first reflection intensity information and second reflection intensity information describe a reflection intensity information, but unless the context otherwise explicitly indicates otherwise, they are not the same reflection intensity information.

[0043] Furthermore, as used herein, the singular forms “a,” “an,” and “the” are intended to include the plural forms as well, unless the context indicates otherwise. It should be further understood that the terms “comprising,” “including,” indicate the presence of the stated feature, step, operation, element, component, item, kind, and / or group, but do not preclude the presence, occurrence, or addition of one or more other features, steps, operations, elements, components, items, kinds, and / or groups. The terms “or” and “and / or” as used herein are to be interpreted inclusively, or mean any one or any combination thereof. Thus, “A, B, or C” or “A, B, and / or C” means “any one of: A; B; C; A and B; A and C; B and C; A, B, and C.” Exceptions to this definition occur only when combinations of elements, functions, steps, or operations are inherently mutually exclusive in some way.

[0044] As described in the background section, existing methods for robot docking with workstations either have poor accuracy or are highly dependent on hardware. In some embodiments, to achieve functional reuse, a laser device mounted on the robot is used to identify the workstation, enabling the robot to dock with it.

[0045] In some examples, a reflector is placed on the workstation. A laser device scans the surrounding environment to detect the reflector and calculates a guidance route based on it to guide the robot to dock with the workstation. In this example, the reflector is detected by identifying the reflection intensity of each object to the laser device, and the reflection point corresponding to the reflection intensity above a predetermined threshold is identified as the corresponding reflector. However, in this method, the laser device needs to be set as a specific laser sensor capable of detecting specific reflection intensity values, such as a laser sensor using a linear mode APD (Avalanche Photodiode) as the detection element. For laser sensors using non-linear mode diodes (such as SPAD, Single Photon Avalanche Diode) as the detection element, due to their extremely high detection sensitivity and detection distance, and lower requirements for reflection intensity, they are the main application and development direction of laser sensors. However, for this type of laser sensor, the reflector and a bright background have almost no difference in reflection intensity, making it difficult to identify the reflector from the background, and thus lacking adaptability. In addition, the reflectors also need to be manufactured using a specific process and made from various materials, and then manually attached to specific positions on the workstation, which further increases the cost.

[0046] In some examples, a specific 3D structure is set up on the workstation, and the surrounding environment is scanned by a laser device to detect the 3D structure. In this example, the 3D structure requires both changes to the external structure of the workstation and specific parameter design. Taking the 3D structure as a concave-convex structure formed on one side wall of the workstation as an example, the depth difference between the protruding and concave parts needs to be configured to be large enough; otherwise, the shape change cannot be detected at a distance. In other words, setting up a concave-convex structure limits the robot's perception distance of the workstation to some extent and also increases the complexity of the engineer's work.

[0047] In view of this, this application discloses a robot and a method for recognizing a workstation, a system for recognizing a robot workstation, a robot, a computer storage medium, a workstation, and a workstation system. By setting a two-dimensional marker image on the workstation, the marker image has at least three consecutive regions with contrasting reflective intensity in the scanning direction of the laser device mounted on the robot, thereby recognizing the marker image through a combination of spatial characteristics and reflective intensity characteristics. This method only requires setting a two-dimensional plane as the marker on the workstation, eliminating the need for complex structural design, simplifying the manufacturing process, and significantly reducing production costs. Furthermore, using a two-dimensional plane as the marker greatly improves the robot's perception distance of the workstation, making it particularly suitable for robots operating in large areas. In addition, this application uses a combination of spatial characteristics and reflective intensity characteristics to recognize the marker image, resulting in high accuracy and avoiding misidentification.

[0048] The robot described in this application is a mobile device equipped with a laser device for performing operations based on the laser device. These operations include recognition, localization, map building, navigation, and the robot recognition workstation method disclosed in this application. The laser device can be a laser sensor with a linear mode detection element or a laser sensor with a non-linear mode detection element. In different application scenarios, the robot can be configured to perform corresponding tasks. For example, the robot can be used indoors to clean floors; in this application scenario, the robot can also be called a cleaning robot, a floor-washing robot, or an automatic cleaning robot. In other indoor scenarios, the robot can also be a home companion mobile robot, a patrol robot, or a food / item delivery robot.

[0049] The workstation described in this application is a device or apparatus for the robot to dock, facilitating the provision of services to the robot. For example, the workstation can provide services such as charging, water replacement, and waste recycling for the robot. Depending on the functions and application scenarios it provides, the workstation may also be referred to as a base station, charging station, charging pile, recycling station, dust collection station, or water replacement station, etc.

[0050] The robot system described in this application is a system comprising a robot and a workstation. The robot and the workstation may be, for example, the robot and workstation disclosed in any embodiment of this application. In some application examples, the robot system may also include a remote control for operation or interaction, a smart terminal with an application installed, and / or a cloud server / cluster for performing data storage and processing in the cloud.

[0051] In some embodiments, this application discloses a workstation, which includes a workstation body and an identification image disposed on the workstation body. In some examples, the workstation body is provided with a service interface, and the workstation provides services to a robot based on the service interface, with the identification image located on the surface where the service interface is located. In some examples, the workstation also includes a base disposed at the bottom of the workstation body for the robot to dock.

[0052] In one embodiment, the service interface can be configured as a charging interface, a water filling interface, a guiding interface, etc. The robot is equipped with a structure corresponding to the service interface. When the robot docks at the workstation, the service interface cooperates with the structure on the robot to achieve docking between the workstation and the robot, thereby providing the corresponding service to the robot. For example, if the service interface is a charging interface, when the workstation docks with the robot, the charging interface is electrically connected to a corresponding structure on the robot, such as an electrode plate, to charge the robot. As another example, if the service interface is a water filling interface, when the workstation docks with the robot, the water filling interface is connected to a corresponding structure on the robot, such as a water inlet, to add water to the robot. Yet another example is a guiding interface; after the robot enters the docking space within the workstation, a corresponding structure on the robot, such as a protruding structure, contacts the guiding interface, which further guides the robot to dock with the workstation. Of course, the service interface can also be configured to provide multiple services; this application does not limit this.

[0053] In one embodiment, the marker image forms at least three consecutive regions with varying reflection intensity along the scanning direction of the laser device deployed on the robot. The laser scanning direction refers to the direction of the scanning trajectory formed by the intersection of the laser plane projected by the laser device and the plane containing the marker image. See also... Figure 1The figure shows a schematic diagram of the scanning direction of a laser device in one embodiment of this application. As shown, for example, a laser device 10 with a single-line laser projects a laser line 100 and scans within a 360-degree range to form a laser plane in three-dimensional space. When the laser plane is on the plane where the identification image 20 is located, the laser plane intersects with the plane where the identification image 20 is located to form a scanning trajectory 101 of the laser line 100 on the plane where the identification image 20 is located. The direction of the scanning trajectory 101 is the laser scanning direction.

[0054] The change in reflection intensity refers to a difference in the reflection intensity of the laser line projected onto its surface, a difference that can be detected by the laser device. In other words, the marking image having at least three consecutive regions of contrasting reflection intensity in the scanning direction of the laser device deployed on the robot means that the laser device will continuously detect at least two regions where the reflection intensity changes when scanning the marking image with the projected laser line. Figure 1 Taking the example shown, using the dashed line parallel to the marker image 20 as a dividing line, the marker image 20 is continuously provided with a first region A1, a second region B1, and a third region C1. Along the scanning trajectory 101 of the laser device 10 on the marker image 20, a change in reflection intensity is detected when moving from the first region A1 to the second region B1, and another change in reflection intensity is detected when moving from the second region B1 to the third region C1. It should be noted that the laser device continuously detecting changes in reflection intensity between two adjacent regions means detecting a relative change in the reflection intensity between the two adjacent regions. In this embodiment, the change in reflection intensity between the two adjacent regions is relative in strength. In actual implementation, it is not necessarily required that the laser device detect specific numerical values ​​of the reflection intensity between the two adjacent regions.

[0055] In one embodiment, the change in reflectance intensity is achieved through the grayscale difference between two adjacent regions. In some examples, the grayscale difference is a color difference, that is, the change in reflectance intensity is achieved through the color difference between two adjacent regions. In some examples, the marking image may be set as a two-dimensional planar pattern formed over a portion or all of a surface on the workstation, the two-dimensional planar pattern having at least two grayscale changes in the laser scanning direction. For example, the two-dimensional planar pattern may be formed by using different material properties or different color coatings over a portion or all of a surface on the workstation; the two-dimensional planar pattern may also be formed by attaching a planar texture to a portion or all of the surface.

[0056] In one embodiment, the marking image is formed in three consecutive regions of black, white, and black in the scanning direction of the laser device. The following explanation uses a horizontal laser scanning direction as an example.

[0057] In one embodiment, the continuous regions in the identified image are arranged side-by-side. See also... Figure 2 The figure shows a schematic diagram of the overall pattern of the identification image in one embodiment of this application. As shown, the identification image 20 is set as black, white, and black parts (A2, B2, C2) arranged side by side, so that the identification image 20 as a whole has a vertical striped pattern. These three parts correspond to three consecutive areas, from the laser scanning direction (i.e. Figure 2 As shown by the dashed line, there is a change in reflection intensity that can be detected by a laser device from the black part A2 to the white part B2, and there is a change in reflection intensity that can be detected by a laser device from the white part B2 to the black part C2.

[0058] In another embodiment, the continuous areas in the logo image form a square-shaped pattern. See also... Figure 3 The figure shows a schematic diagram of the overall pattern of the identification image in another embodiment of this application. As shown, the identification image 20 is set so that the black part surrounds the white part in a square shape, that is, the identification image 20 is in the shape of a square, and the laser scanning direction is in the middle part of the square pattern (as shown in the figure). Figure 3 The area between the two dashed lines is used to form three continuous regions with varying reflection intensity in the scanning direction of the laser device: region A3 on one side of the black part, region B3 on the white part, and region C3 on the other side of the black part. That is, from the laser scanning direction, the laser device projects the image 220 onto the marking image 220 from region A3 on one side of the black part to region B3 on the white part, and then from region B3 on the white part to region C3 on the other side of the black part, so that the laser device can detect two changes in reflection intensity.

[0059] It should be understood that, Figure 2 and Figure 3 This is merely one example of an icon image and is not intended to limit the patterns formed by the icon image. Inspired by the above embodiments, those skilled in the art can design other icons in the icon image that differ from the provided examples. Figure 2 and Figure 3 The pattern should still be covered by the claims of this application.

[0060] In some embodiments, this application discloses a method for robot identification of a workstation. The robot is equipped with a laser device, and the workstation is equipped with a marker image. The workstation is, for example, the workstation described in any of the foregoing embodiments. In one embodiment, the method for robot identification of the workstation is performed by the robot; more specifically, it can be performed by a control device configured on the robot. In another embodiment, the method for robot identification of the workstation can also be performed by a control device configured on a remote server, which can communicate remotely with the robot to control the robot to perform corresponding actions when executing the method for robot identification of the workstation disclosed in this application. The following embodiments illustrate this by assuming that the method for robot identification of the workstation is performed by a control device configured on the robot.

[0061] Please see Figure 4 The figure shows a flowchart of a method for identifying a robot workstation in one embodiment of this application. As shown, the method for identifying a robot workstation includes steps S110, S120, and S130.

[0062] In step S110, the control device acquires point cloud data of the surrounding environment scanned by the laser device.

[0063] In one embodiment, the laser device is horizontally positioned on top of the robot. This ensures that when the robot controls the laser device to rotate and project laser lines, it is not obstructed by the robot's body, allowing the laser device to scan the surrounding environment over the maximum range. Of course, in other embodiments, depending on the application scenario or the function being provided, the laser device may also be positioned at a certain angle at the front or top of the robot; this application does not impose any limitations on this.

[0064] The point cloud data includes data on each reflection point of the laser device scanning the surrounding environment with a laser line and being reflected by the surfaces of objects in the surrounding environment. In one embodiment, the point cloud data includes coordinate information and first reflection intensity information. The coordinate information reflects the two-dimensional position of each reflection point in space, and depending on the coordinate system used, the coordinate information may be represented by polar coordinates or Cartesian coordinates, for example. The first reflection intensity information reflects the reflection intensity of the laser line by each reflection point.

[0065] Considering that in some scenarios, the laser device deployed within the robot's operating area may be unable to scan the marker images on the workstation, meaning the point cloud data lacks information about the marker images. For example, if the robot is operating in a large area (e.g., thousands of square meters), it may be far from the workstation, exceeding the detection range of the laser device. In this case, the point cloud data obtained by the robot controlling the laser device to scan the surrounding environment will not contain any information about the workstation. In other scenarios, although the robot is working around the workstation, the marker images on the workstation may not be detected by the laser device; for example, the robot may be located behind the workstation, while the marker images on the workstation are located at the front. Therefore, please refer to [link to relevant documentation]. Figure 5 The diagram shows a flowchart of acquiring point cloud data in one embodiment of this application. In some embodiments, step S110 includes steps S111 and S112.

[0066] In step S111, the control device controls the robot to move to a predetermined area based on a reference pose information; within the predetermined area, the laser device can scan the identification image on the workstation.

[0067] The reference pose information reflects the robot's position and orientation within a pre-built map when the robot is positioned at a location where its laser device can scan the marked image. For example, the pre-built map can be a grid map built by the robot based on a laser device including a SLAM system, or a visual map built by the robot based on a vision device including a VSLAM system. This application does not limit the map construction method.

[0068] Therefore, in some embodiments, the method for robot identification of workstations further includes step S100 (not shown), in which the robot's control device records the reference pose information when the robot is positioned in a preset posture at a preset position. When the robot is positioned in the preset posture at the preset position, the identification image on the workstation is within the scanning field of view of the laser device configured on the robot. For example, the robot can be manually positioned in the preset posture at the preset position. Further, please refer to... Figure 6The figure shows a schematic diagram of the position and posture of the robot relative to the workstation in one embodiment of this application. As shown, the preset posture can be the surface where the robot 1 faces the marker image 20 of the workstation 2, and the preset position can be a certain distance directly in front of the workstation, such as 1m, so that when the robot 1 is located at this position, the laser line 100 projected by its laser device 10 can scan the marker image 20. Specifically, the robot 1 can be manually pushed to this position, and then the position and posture of the robot 1 at this time in the pre-constructed map can be recorded as reference pose information. The reference pose information can be recorded, for example, in the storage device of the robot 1. The preset posture and preset position are not fixed values ​​and can be any posture and position formed by manual operation, as long as it is ensured that the laser device 10 of the robot 1 can scan the marker image 20 at this posture and position.

[0069] It should be noted that, depending on the application environment, step S100 may be selectively executed before step S110. In some examples, step S100 is executed when the robot cannot obtain the reference pose information. For example, when the robot is first deployed in the environment of the current workstation, it typically does not have the reference pose information. In other examples, step S100 is executed when the robot continues to execute steps S110 to S130 based on the obtained reference pose information, but cannot match the marker image. For example, although the robot is not being deployed in the environment of the current workstation for the first time, the position of the workstation has changed, so that when the robot moves to the predetermined area based on the reference pose information, its configured laser device cannot scan the marker image on the workstation.

[0070] Please continue reading. Figure 5 In step S112, the control device controls the laser device to scan the surrounding environment to obtain point cloud data including the marker image on the workstation. In some embodiments, the point cloud data including the marker image on the workstation is all the point cloud data obtained by the laser device scanning the surrounding environment in a predetermined area. In other embodiments, to reduce computational load, the point cloud data including the marker image on the workstation is only a portion of the point cloud data obtained by the laser device scanning the surrounding environment in a predetermined area. For example, the entire point cloud data can be filtered according to the reflection angle of each reflection point to retain the point cloud data of the workstation and its vicinity. Of course, the filtering method is not limited to the reflection angle; those skilled in the art only need to ensure that the retained portion of the point cloud data includes the marker image.

[0071] Please continue reading. Figure 4In step S120, the control device clusters the point cloud data based on the coordinate information and the first reflection intensity information to determine the spatial information and second reflection intensity information of each point cloud dataset formed by the clustering. Here, clustering refers to aggregating scattered data points (e.g., point cloud data obtained by a laser device scanning the surrounding environment) into mutually independent categories based on differences generated according to a predetermined rule.

[0072] In one embodiment, please refer to Figure 7 The figure shows a flowchart of step S120 in one embodiment of the present application. As shown, step S120 includes step S121 and step S122.

[0073] In step S121, the control device clusters point cloud data that are spatially continuous and whose reflection intensity is within a preset range into a single point cloud dataset. That is, the conditions of spatial continuity and reflection intensity within a preset range are used as predetermined rules for clustering.

[0074] In one embodiment, the spatial continuity is determined based on the coordinate information of the point cloud data, and the reflection intensity within a preset range is determined based on the first reflection intensity information of the point cloud data. Specifically, the spatial continuity means that the spatial positions of the reflection points on the object surface hit by the laser beam projected by the laser device change continuously.

[0075] As mentioned earlier, the coordinate information of point cloud data reflects the spatial position of each reflection point. Therefore, for point cloud data of the same target plane, the spatial position of each reflection point on its surface obtained from its coordinate information is continuous. That is, there will be no sudden change in depth. For example, as a two-dimensional planar pattern, the spatial position corresponding to the point cloud data of the entire surface of a marker image is continuous. However, as a three-dimensional structure, the spatial position corresponding to the point cloud data of the entire outer surface of a concave-convex structure will change in depth, that is, it is discontinuous.

[0076] As mentioned earlier, the first reflection intensity information is used to reflect the reflection intensity of each reflection point on the laser line. The reflection intensity is related not only to the spatial position of each reflection point on the object surface hit by the laser line projected by the laser device, but also to the grayscale value of the object surface. Reflection points hitting areas of the same or similar color on the same surface should have similar reflection intensities. For example, in the marker image, by setting grayscale differences between adjacent areas (such as setting different colors between adjacent areas), three continuous areas with varying reflection intensities are formed. Therefore, the reflection intensities within each grayscale area in the marker image are similar, while the reflection intensities between adjacent areas differ significantly. In other words, by combining spatial continuity and reflection intensity within a preset range to cluster the point cloud data, the point cloud data corresponding to the marker image can be clustered into three types of point cloud datasets.

[0077] Please refer to Figure 8, which shows a schematic diagram of point cloud data corresponding to an identifier image in one embodiment of this application, using the identifier image as... Figure 2 Taking the example shown, when the laser device projects a laser line onto the marked image 20, it will acquire an image as shown below. Figure 8 The point cloud data shown, corresponding to the black portion A2 of the labeled image 20, is clustered into a single point cloud dataset because it is spatially continuous and its reflection intensity is within a preset range (as shown in the image). Figure 8 The point cloud dataset on the left side of the image (corresponding to the white portion B2 of image 20) is clustered into another point cloud dataset because its spatial continuity and reflection intensity are within a preset range (as shown in the image). Figure 8 The point cloud dataset in the middle, corresponding to the black part C2 of the labeled image 20, is clustered into another point cloud dataset because its spatial continuity and reflection intensity are within a preset range (as shown in the image). Figure 8 (The point cloud dataset on the right side of the middle section).

[0078] Please continue reading. Figure 7 In step S122, the control device determines the spatial information and the second reflection intensity information of the point cloud dataset based on the coordinate information of each point cloud data in the point cloud dataset and the first reflection intensity information.

[0079] In one embodiment, the spatial information of the point cloud dataset includes position information and length information. The position information reflects the relative position of the point cloud dataset in space; that is, the relative positional relationship between different types of point cloud datasets can be determined based on their position information. For example, the coordinate information of a single point cloud data point in the dataset can be used as the position information of that dataset, such as the coordinate information of a point cloud data point in the middle position. Alternatively, position information can be generated based on the coordinate information of the point cloud data points, such as using the average of the coordinate information of all point cloud data points as the position information of the dataset. Position information can also be set for the point cloud dataset based on the scanning angle or sequence of the laser device, as long as the relative positional relationship between different types of point cloud datasets can be determined based on their position information.

[0080] The length information reflects the span of the point cloud dataset. In other words, the length information can be understood as the length of the geometric line segments formed by the spatial arrangement of each point cloud data point in the dataset based on its coordinate information. For example... Figure 8 As shown, the length information is the length of the line segments arranged in each point cloud data set.

[0081] In one embodiment, the second reflection intensity information is obtained based on the first reflection intensity information of the point cloud data in the point cloud dataset. The second reflection intensity information is used to reflect the reflection characteristics of the corresponding point cloud dataset. For example, the average value, variance, etc. of the first reflection intensity of all point cloud data in the point cloud dataset can be used as the second reflection intensity; alternatively, the first reflection intensity of a single point cloud data in the point cloud dataset can be used as the second reflection intensity information. This application does not impose any limitations on this.

[0082] According to the foregoing embodiments, after step S120, multiple point cloud datasets can be obtained, each point cloud dataset having spatial information reflecting its spatial characteristics and second reflection intensity information reflecting its reflection characteristics.

[0083] Please refer to section 4. In step S130, the control device matches the point cloud dataset based on the region information of the identified image to identify the workstation.

[0084] In one embodiment, the region information of the marker image is used to reflect the distribution characteristics of each region in which the marker image is formed, and the region information is configured to be pre-stored in a storage device. The storage device may be, for example, a storage device configured on the robot or a storage device configured on a remote server that can communicate remotely with the robot. The marker image may be the marker image described in any of the aforementioned workstation embodiments; the composition of the marker image will not be elaborated further here.

[0085] In one embodiment, the region information of the marker image includes width distribution information and intensity distribution information of each region of the marker image. In one example, the width distribution information of each region refers to the width of each region on the marker image in the scanning direction of the laser device.

[0086] Using the identification image as Figure 2 Taking the illustrated pattern as an example, the logo image has three regions: a black region A2, a white region B2, and a black region C2. Since these three regions are parallel rectangles with uniform widths, the width distribution information of each region is the width value of the black region A2, the width value of the white region B2, and the width value of the black region C2. Using the logo image as an example... Figure 3 Taking the pattern shown as an example, the laser scanning direction is in the middle area of ​​the square pattern. That is, the width distribution information of each area is the width value of area A3 on one side of the black part, the width value of area B3 in the white part, and the width value of area C3 on the other side of the black part.

[0087] In one example, the intensity distribution information for each region refers to the relative information of the reflection intensity corresponding to each region on the image. It is not necessarily the absolute value of the reflection intensity of each region, as long as it indicates the trend of reflection intensity change between adjacent regions. For example, the intensity distribution information for each region is represented as high or low. Figure 2 As shown in the example, the intensity distribution information for each region is: low, high, low; the intensity distribution information for each region can also be expressed as numerical values ​​reflecting the degree of intensity, for example, using... Figure 2 As shown in the example, the intensity distribution information for each region is 0, 1, 0, and this application does not impose any restrictions on this.

[0088] Therefore, in step S130, by matching each point cloud dataset with the region information of the labeled image, the point cloud dataset corresponding to the labeled image can be identified, thereby identifying the workstation. To avoid mismatches caused by matching multiple independent and unrelated point cloud datasets with the region information of consecutive regions of the labeled image in a piecemeal manner, for example... Figure 9 As shown, Figure 9 The diagram shown illustrates a mismatch method in one embodiment of this application. The point cloud data includes laser device scanning data, as shown below. Figure 9 The groove structure 30 shown has five surfaces scanned by the laser device: a first surface 301, a second surface 302, a third surface 303, a fourth surface 304, and a fifth surface 305. Each surface is segmented into its corresponding point cloud dataset. It is possible to match the discontinuous first surface 301, third surface 303, and fifth surface 305 with each region of the labeled image, which may result in matching errors.

[0089] In view of this, in some embodiments, step S130 includes: the control device determining a comparison dataset that satisfies a first matching condition and a second matching condition as a target dataset based on the region information of the identified image, so as to identify the workstation based on the target dataset.

[0090] The comparison dataset refers to multiple point cloud datasets that are spatially continuous and have the same number of regions as the labeled image. In other words, in this embodiment, the labeled image is considered as a whole, and only spatially continuous point cloud datasets with the same number of regions as the labeled image can be used as a whole (i.e., the comparison dataset) to match the region information of the labeled image.

[0091] In one embodiment, the comparison dataset is determined based on the positional information in the spatial information of each point cloud dataset, thereby allowing point cloud datasets that are spatially continuous and have the same number of regions as the labeled image to be used as a comparison dataset. It should be understood that since the comparison dataset is divided solely based on spatial continuity, different comparison datasets may include the same point cloud dataset. For example, if the labeled image has three continuous regions, and the point cloud data clustering forms four point cloud datasets—a first point cloud dataset, a second point cloud dataset, a third point cloud dataset, and a fourth point cloud dataset—and the first to fourth point cloud datasets are spatially continuous, then the first to third point cloud datasets can be used as one comparison dataset to match the region information of the labeled image, and the second to fourth point cloud datasets can be used as another comparison dataset to match the region information of the labeled image.

[0092] The first matching condition refers to the spatial information of each point cloud dataset in the comparison dataset being consistent with the width distribution information of each region of the labeled image; the second matching condition refers to the second reflection intensity information of each point cloud dataset in the comparison dataset being consistent with the intensity distribution information of each region. In other words, the comparison dataset can be used as the target dataset when it meets the two matching conditions, i.e., it is considered a set of point cloud data corresponding to the labeled image.

[0093] For example, the image is identified as such Figure 2As shown, its width distribution information includes the width values ​​of the black part A2, the white part B2, and the black part C2. The intensity distribution information is low, high, and low. There are two comparison datasets: a first comparison dataset consisting of the first to third datasets and a second comparison dataset consisting of the second to fourth datasets. If the length information of the first to third datasets in the first comparison dataset is consistent with the width values ​​of the black part A2, the white part B2, and the black part C2, respectively, and the reflection intensity information of the first to third datasets indicates a low, high, and low reflection intensity trend, then the first comparison dataset is determined to be the target dataset. The control device can identify the workstation based on the target dataset.

[0094] In some embodiments, the method for robot identification of a workstation further includes step S140, in which a control device determines the positional relationship of the workstation relative to the robot based on the target dataset, so as to control the robot to dock with the workstation. See also Figure 10 The figure shows a flowchart of a robot docking workstation in one embodiment of the present application. As shown, step 140 includes steps S141, S142, and S143.

[0095] In step S141, the control device selects a feature dataset based on the spatial information or second reflection intensity information of each point cloud dataset in the target dataset. In one embodiment, the control device selects the point cloud dataset at the middle position as the feature dataset based on the spatial information of each point cloud dataset in the target dataset. Figure 2 For example, the control device selects the point cloud dataset corresponding to the white part B2 of the identification image as the feature dataset.

[0096] In another embodiment, the control device selects the point cloud dataset with the strongest second reflection intensity information from each point cloud dataset in the target dataset as the feature dataset. Figure 2 As shown in the example, the second reflection intensity information of the point cloud dataset corresponding to the white part B2 is the strongest compared to the black parts A2 and C2. The control device selects the point cloud dataset corresponding to the white part B2 of the identification image as the feature dataset.

[0097] In step S142, the control device performs line segment fitting on the feature dataset to determine the center point and normal vector of the fitted line segment. Specifically, the control device can perform line segment fitting based on the coordinate information of each point cloud data in the feature dataset to obtain the line segment corresponding to the feature dataset, then calculate the center point of the line segment, and determine the normal vector of the line segment based on the center point.

[0098] In step S143, the control device controls the robot to dock with the workstation based on the positional relationship between the centerline and the normal vector relative to the robot. The positional relationship between the centerline and the normal vector relative to the robot represents the positional relationship between the workstation and the robot. Controlling the robot's movement based on this positional relationship enables the robot to dock with the workstation; that is, each service interface of the workstation can be matched one-to-one with the corresponding structure on the robot.

[0099] The positional relationship is determined based on point cloud data in the feature dataset and the coordinate transformation relationship between the laser device and the robot. In some embodiments, due to the accuracy of the laser device itself or operator installation issues, the coordinate transformation relationship between the laser device and the robot may deviate, thus causing a deviation in the positional relationship between the workstation and the robot determined in step S140.

[0100] In other embodiments, due to manufacturing process issues, the region of the feature dataset corresponding to the identification image is not located at the center of the workstation. Therefore, the determination of the positional relationship between the workstation and the robot based on the positional relationship between the center point and normal vector of the feature dataset and the robot will also have deviations, making it impossible for the robot to dock with the workstation. Specifically, the service interfaces of the workstation cannot be matched one-to-one with the corresponding structures on the robot, so that the workstation cannot provide services to the robot.

[0101] Therefore, in some embodiments, the method for robot identification of workstations further includes a step of determining error compensation parameters, wherein the error compensation parameters are used to compensate for the positional relationship of the workstation relative to the robot. It should be noted that this step can be part of the system calibration process, performed when the robot is initially deployed to form a robot system with the current workstation, or after the robot has been working in the current environment for a considerable period. Subsequently, when performing steps S110 to S140 as described in any of the foregoing embodiments, it is only necessary to incorporate the error compensation parameters in step S140 when determining the positional relationship of the workstation relative to the robot based on the target dataset.

[0102] In one embodiment, the step of determining the error compensation parameters includes: acquiring a target dataset when the robot docks with the workstation. The step of acquiring the target dataset includes steps S110 to S130 in any of the foregoing embodiments, that is, acquiring the target dataset by executing steps S110 to S130 when the robot docks with the workstation. Specifically, in the embodiment of initial robot deployment, the robot can be manually pushed into the workstation so that each service interface on the workstation corresponds to a specific structure on the robot. For example, the charging interface on the workstation is electrically connected to the electrode plates on the robot, and the water inlet on the workstation is connected to the water inlet on the robot. Then, the control device acquires the target dataset by executing steps S110 to S130 in any of the foregoing embodiments. For details, please refer to the foregoing description of steps S110 to S130, which will not be repeated here.

[0103] In one embodiment, the step of determining the error compensation parameters further includes: determining the error compensation parameters based on the target dataset. Specifically, in this embodiment, a feature dataset is selected based on the spatial information or second reflection intensity information of each point cloud dataset in the target dataset, and line segment fitting is performed on the feature dataset to determine the center point and normal vector of the fitted line segment; finally, the positional relationship between the center line and the normal vector relative to the robot is determined as the error compensation parameters. The descriptions of the selection of the feature dataset and line segment fitting, etc., can be found in the corresponding descriptions in steps S141 to S143 above, and will not be repeated here.

[0104] This application also discloses a robot for performing the robot identification workstation method described in any of the above embodiments. Please refer to... Figure 11 The figure shows a schematic diagram of the structure of a robot in one embodiment of this application. As shown, the robot 1 includes a laser device 10, a moving device 12, and a control device 11.

[0105] In one embodiment, the laser device 10 is horizontally positioned on top of the robot 1. This ensures that when the robot 1 controls the laser device 10 to rotate and project a laser line, it is not obstructed by the robot's body, allowing the laser device 10 to scan the surrounding environment to the maximum extent. Of course, in other embodiments, depending on the application scenario or the function provided, the laser device 10 may also be positioned at a certain tilt angle at the front or top of the robot 1; this application does not impose any limitations on this. For example, the laser device 10 can be configured as a laser sensor with a linear mode detection element or as a laser sensor with a non-linear mode detection element, thus adapting to a wider range of applications.

[0106] The mobile device 12 is disposed at the bottom of the robot 1 to drive the robot 1 to move. In some embodiments, the mobile device 12 includes a drive assembly and drive wheels disposed on opposite sides of the bottom of the robot 1. The drive wheels are driven by the drive assembly to drive the robot 1 to move. Specifically, the drive wheels are driven to cause the robot 1 to perform reciprocating motion, rotational motion, or curvilinear motion according to a planned movement trajectory, or to drive the robot 1 to adjust its posture, and to provide two contact points between the robot 1 and the walking surface. In other embodiments, the mobile device 12 also includes a driven wheel located in front of the drive wheel. The driven wheel and the drive wheel together maintain the balance of the robot 1 in motion.

[0107] The control device 11 is mounted on the robot 1 and is used to control the laser device 10 and the mobile device 12 to work together to perform the robot recognition workstation method disclosed in any of the foregoing embodiments of this application. The control device 11 can also control the robot 1 to perform work tasks, as well as to perform positioning, mapping, and navigation using navigation technology. In some embodiments, the control device 11 includes a memory and a processor, etc.

[0108] In this embodiment, the processor can be used to read and execute computer-readable instructions. Specifically, the processor may mainly include a controller, an arithmetic logic unit (ALU), and registers. The controller is primarily responsible for instruction decoding and issuing control signals for the operations corresponding to the instructions. The ALU is primarily responsible for performing fixed-point or floating-point arithmetic operations, shift operations, and logical operations, and can also perform address operations and conversions. Registers are primarily responsible for storing register operands and intermediate operation results temporarily stored during instruction execution. Specifically, the processor's hardware architecture may be an Application-Specific Integrated Circuit (ASIC), MIPS, ARM, or NP architecture, etc. The processor may include one or more processing units, such as an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors.

[0109] In this embodiment, the memory is coupled to the processor and is used to store various software programs and / or multiple sets of instructions. Specifically, the memory may include high-speed random access memory and may also include non-volatile memory, such as one or more disk storage devices, flash memory devices, or other non-volatile solid-state storage devices. The memory may store an operating system, such as uCOS, VxWorks, RTLinux, or other embedded operating systems. The memory may also store communication programs that can be used to communicate with smart terminals, one or more servers, or additional devices.

[0110] In some embodiments, this application also discloses a system for identifying a robot workstation, wherein the robot is equipped with a laser device, such as the robot disclosed in any of the foregoing embodiments of this application, and the workstation is provided with an identification image, wherein the identification image forms at least three regions with varying reflection intensity in the scanning direction of the laser device, and the workstation is, for example, the workstation disclosed in any of the foregoing embodiments of this application.

[0111] Please see Figure 12 The figure shows a schematic diagram of the system structure of a robot recognition workstation in one embodiment of this application. As shown in the figure, the system 3 of the robot recognition workstation includes an acquisition module 30, a clustering module 31, and a matching module 32.

[0112] The acquisition module 30 is used to acquire point cloud data of the surrounding environment scanned by the laser device; the point cloud data includes coordinate information and first reflection intensity information. In some embodiments, the process by which the acquisition module 30 acquires the point cloud data of the surrounding environment scanned by the laser device can be referred to the description of step S110 in any embodiment of the robot recognition workstation method disclosed in this application, and will not be repeated here.

[0113] The clustering module 31 is used to cluster the point cloud data based on the coordinate information and the first reflection intensity information to determine the spatial information and second reflection intensity information of each point cloud dataset formed by the clustering. In some embodiments, the clustering process of the clustering module 31 can be referred to the description of step S120 in any embodiment of the robot recognition workstation method disclosed in this application, and will not be repeated here.

[0114] The matching module 32 is used to match the region information of the identified image based on the point cloud dataset to identify the workstation. In some embodiments, the matching process of the matching module 32 can be referred to the description of step S130 in any embodiment of the robot workstation identification method disclosed in this application, and will not be repeated here.

[0115] In some embodiments, the system for the robot recognition workstation further includes a docking module (not shown), which is used to determine the positional relationship between the workstation and the robot based on the target dataset, so as to control the robot to dock with the workstation. In some embodiments, the operation process of the docking module can be referred to the description of step S140 in any embodiment of the robot recognition workstation method disclosed in this application, and will not be repeated here.

[0116] In this embodiment, the system of the robot recognition workstation is, for example, a recognition program / software loaded on a computer device. In this embodiment, the recognition program / software is a computer-executable program or a sequence of symbolic instructions or symbolic statements that can be converted into an executable program.

[0117] In some embodiments, this application also discloses a robot system, which includes a robot and a workstation. The robot may be, for example, the robot disclosed in any embodiment of this application, as detailed below. Figure 11 The corresponding descriptions are omitted here. The workstation may be, for example, the workstation disclosed in any embodiment of this application, as shown in the references... Figures 1 to 3 The details and their corresponding descriptions will not be repeated here.

[0118] This application also provides a computer-readable and writable storage medium for storing at least one program, which, when invoked, executes and implements the method for a robot recognition workstation described in any of the above embodiments.

[0119] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a mobile robot installed on the storage medium to execute all or part of the steps of the methods described in the various embodiments of this application.

[0120] In the embodiments provided in this application, the computer-readable and writable storage medium may include read-only memory, random access memory, EEPROM, CD-ROM or other optical disc storage devices, disk storage devices or other magnetic storage devices, flash memory, USB flash drive, portable hard drive, or any other medium capable of storing desired program code in the form of instructions or data structures and accessible by a computer. Additionally, any connection may be appropriately referred to as a computer-readable medium. For example, if instructions are transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of the medium. However, it should be understood that computer-readable and writable storage media and data storage media do not include connections, carrier waves, signals, or other transient media, but are intended for non-transient, tangible storage media. The disks and optical discs used in the application include compact discs (CDs), laser discs, optical discs, digital multifunction discs (DVDs), floppy disks, and Blu-ray discs, where disks typically copy data magnetically, while optical discs use lasers to copy data optically.

[0121] In one or more exemplary aspects, the functions described in the computer program of the robot recognition workstation method of this application can be implemented in hardware, software, firmware, or any combination thereof. When implemented in software, these functions can be stored or transmitted as one or more instructions or code onto a computer-readable medium. The steps of the methods or algorithms disclosed in this application can be embodied in processor-executable software modules, wherein the processor-executable software modules can reside on a tangible, non-transitory computer-readable and writable storage medium. The tangible, non-transitory computer-readable and writable storage medium can be any available medium accessible to a computer.

[0122] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Accordingly, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified function or operation, or by a combination of dedicated hardware and computer instructions.

[0123] In summary, the robot, its identification workstation method, system, robot, computer storage medium, workstation, and workstation system disclosed in this application identify the identification image by setting a two-dimensional marker image on the workstation. This marker image has at least three consecutive regions with contrasting reflective intensity in the scanning direction of the laser device mounted on the robot. This allows for identification of the marker image through a combination of spatial characteristics and reflective intensity characteristics. This method only requires setting a two-dimensional plane as the marker on the workstation, eliminating the need for complex structural design and simplifying the manufacturing process, thus significantly reducing production costs. Furthermore, using a two-dimensional plane as the marker greatly improves the robot's perception distance of the workstation, making it particularly suitable for robots operating in large areas. In addition, the method of identifying the marker image by combining spatial characteristics and reflective intensity characteristics in this application achieves high accuracy and avoids misidentification.

[0124] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A method for robot identification of workstations, characterized in that, The robot is equipped with a laser device, and the workstation is equipped with a marker image. The marker image forms at least three continuous regions with varying reflection intensity in the scanning direction of the laser device. The method includes: The laser device scans the surrounding environment to obtain point cloud data; the point cloud data includes coordinate information and first reflection intensity information. Clustering the point cloud data based on the coordinate information and the first reflection intensity information to determine the spatial information and second reflection intensity information of each point cloud dataset formed by the clustering; including: clustering point cloud data that are spatially continuous and whose reflection intensity is within a preset range into one type of point cloud dataset; and determining the spatial information and second reflection intensity information of the point cloud dataset based on the coordinate information and the first reflection intensity information of each point cloud data in the point cloud dataset; wherein, the spatial continuity is determined based on the coordinate information of the point cloud data; the reflection intensity being within a preset range is determined based on the first reflection intensity information of the point cloud data; the spatial information of the point cloud dataset includes position information and length information, the position information being used to reflect the relative position of the point cloud dataset in space, and the length information being used to reflect the span range of the point cloud dataset; The method of matching the point cloud dataset with the region information of the labeled image to identify the workstation includes: determining a comparison dataset that satisfies a first matching condition and a second matching condition as a target dataset based on the region information of the labeled image, and identifying the workstation based on the target dataset; wherein the region information of the labeled image is pre-stored in a storage device, including the width distribution information and intensity distribution information of each region of the labeled image; the comparison dataset refers to multiple point cloud datasets that are spatially continuous and have the same number of regions as the labeled image; the first matching condition is that the spatial information of each point cloud dataset in the comparison dataset is consistent with the width distribution information of each region of the labeled image; the second matching condition is that the second reflection intensity information of each point cloud dataset in the comparison dataset is consistent with the intensity distribution information of each region.

2. The method for robot identification workstation according to claim 1, characterized in that, The second reflection intensity information is obtained based on the first reflection intensity information of the point cloud data in the point cloud dataset.

3. The method for robot identification workstation according to claim 1, characterized in that, Also includes: The positional relationship between the workstation and the robot is determined based on the target dataset in order to control the robot to dock with the workstation.

4. The method for robot identification workstation according to claim 3, characterized in that, The steps of determining the positional relationship between the workstation and the robot based on the target dataset, and controlling the robot to dock with the workstation, include: Feature datasets are selected based on the spatial information or second reflection intensity information of each point cloud dataset in the target dataset; Line segment fitting is performed on the feature dataset to determine the center point and normal vector of the fitted line segment; Based on the positional relationship between the center point and the normal vector relative to the robot, the robot is controlled to dock with the workstation.

5. The method for robot identification workstation according to claim 1, characterized in that, Also includes: The step of determining error compensation parameters, wherein the error compensation parameters are used to compensate for the positional relationship of the workstation relative to the robot.

6. The method for robot identification workstation according to claim 1, characterized in that, Adjacent regions have a difference in gray level to create the variation in reflectance.

7. The method for robot identification workstation according to claim 1, characterized in that, In the scanning direction of the laser device, the marking image is formed into three continuous areas: black, white, and black.

8. The method for robot identification workstation according to claim 7, characterized in that, The logo image is composed of three parts arranged side by side: black, white, and black.

9. The method for robot identification workstation according to claim 7, characterized in that, The identification image is set so that the black part surrounds the white part in a square shape, so as to form three continuous areas with varying reflectivity in the scanning direction of the laser device.

10. The method for robot identification workstation according to claim 1, characterized in that, The steps for acquiring point cloud data of the surrounding environment scanned by the laser device include: The robot is controlled to move to a predetermined area based on a reference pose information; wherein, within the predetermined area, the laser device can scan the identification image; The laser device is controlled to scan the surrounding environment to obtain point cloud data including the marked image.

11. The method for robot identification workstation according to claim 1, characterized in that, The robot in question is a cleaning robot.

12. A system for identifying robot workstations, characterized in that, The robot is equipped with a laser device, and the workstation is equipped with a marker image. The marker image forms at least three continuous regions with varying reflection intensity in the scanning direction of the laser device. The system includes: The acquisition module is used to acquire point cloud data of the surrounding environment scanned by the laser device; the point cloud data includes coordinate information and first reflection intensity information; A clustering module is used to cluster the point cloud data based on the coordinate information and the first reflection intensity information to determine the spatial information and second reflection intensity information of each point cloud dataset formed by the clustering; including: clustering point cloud data that are spatially continuous and whose reflection intensity is within a preset range into one type of point cloud dataset; and determining the spatial information and second reflection intensity information of the point cloud dataset based on the coordinate information and the first reflection intensity information of each point cloud data in the point cloud dataset; wherein, the spatial continuity is determined based on the coordinate information of the point cloud data; the reflection intensity being within a preset range is determined based on the first reflection intensity information of the point cloud data; the spatial information of the point cloud dataset includes position information and length information, wherein the position information is used to reflect the relative position of the point cloud dataset in space, and the length information is used to reflect the span range of the point cloud dataset; A matching module is used to match the point cloud dataset based on the region information of the labeled image to identify the workstation; it includes: determining a comparison dataset that satisfies a first matching condition and a second matching condition as a target dataset based on the region information of the labeled image, so as to identify the workstation based on the target dataset; wherein, the region information of the labeled image is set to be pre-stored in a storage device, including the width distribution information and intensity distribution information of each region of the labeled image; the comparison dataset refers to multiple point cloud datasets that are spatially continuous and whose number is consistent with the number of regions of the labeled image; the first matching condition is that the spatial information of each point cloud dataset in the comparison dataset is consistent with the width distribution information of each region of the labeled image; the second matching condition is that the second reflection intensity information of each point cloud dataset in the comparison dataset is consistent with the intensity distribution information of each region.

13. A robot, characterized in that, include: A laser device is mounted on top of the robot to scan the surrounding environment; A mobile device is installed at the bottom of the robot to move the robot. A control device, disposed on the robot, is used to control the laser device and the mobile device to work together to perform the robot recognition workstation method as described in any one of claims 1-11.

14. A computer storage medium, characterized in that, The system stores at least one program that, when invoked, performs the method of the robot recognition workstation as described in any one of claims 1-11.

15. A workstation, characterized in that, include: The workstation body is equipped with a service interface, and the workstation provides services to the robot based on the service interface. The robot includes a laser device. An identification image is disposed on the workstation body and located on the surface where the service interface is located; wherein the identification image has at least three consecutive regions with contrasting reflectance in the scanning direction of the laser device; The identification image is used for scanning by a laser device mounted on the robot, so that the robot performs the robot identification workstation method as described in any one of claims 1-11.

16. A robot system, characterized in that, include: The robot as claimed in claim 13, and the workstation as claimed in claim 15.

Images