Method and system for detecting the quality of calibration of a robot laser device

Abstract

The present disclosure provides a method for detecting the calibration quality of a robot laser device, comprising: the robot laser device emitting laser light to at least irradiate a plane board to form a laser line segment; acquiring laser point cloud data of the laser line segment, acquiring image data of the laser line segment; acquiring position information of the laser point cloud data in the laser device coordinate system, and acquiring position information of the image data in the robot coordinate system; acquiring first spatial features and second spatial features of the laser point cloud data; acquiring first spatial features and second spatial features of the image data; acquiring a first matching degree of the first spatial features of the laser point cloud data and the first spatial features of the image data, and acquiring a second matching degree of the second spatial features of the laser point cloud data and the second spatial features of the image data; if the first matching degree meets a first preset condition and the second matching degree meets a second preset condition, it is determined that the external parameter calibration parameter is qualified. The present disclosure also provides a detection system.

Description

Technical Field

[0001] This disclosure relates to a method and system for detecting the calibration quality of a robotic laser device. Background Technology

[0002] In recent years, with the advancement of technology and the reduction of costs, various laser sensors have been used in a wide range of products, and new products are constantly emerging, such as various civilian and commercial robots and 3D laser scanners.

[0003] During the production of laser sensor products, errors or mistakes may occur during sensor module installation due to product structure or assembly. This can lead to discrepancies between the theoretical values ​​of the external parameters between the laser module and the robot as a whole. To address this issue, current technologies typically calibrate the external parameters during robot production. However, there is no effective method to verify the quality of the calibration itself afterward.

[0004] For example, Chinese patent document CN112731356A discloses a method for calibrating the extrinsic parameters of a multi-line lidar on an unmanned vehicle, including: acquiring the three-dimensional coordinates of the calibration point in both the vehicle coordinate system and the radar coordinate system; calculating the parameters of the three-dimensional coordinates based on a preset transformation formula to obtain the parameter calculation results; and determining the extrinsic parameters of the multi-line lidar based on the parameter calculation results. (Refer to this...) Figure 2 This calibration method requires setting multiple calibration targets on both walls to construct the calibration environment.

[0005] For example, Chinese patent document CN103837869B discloses a calibration method for a single-line lidar and CCD camera based on vector relationships. It extracts the point set information of the lidar scanning a V-shaped target in the lidar coordinate system, and obtains the direction vectors and intersection coordinates of the lines in two different planes of the target through line fitting. In the camera coordinate system, it uses a CCD camera to capture images, and processes the image information to obtain the target plane equation and the plane equation passing through the origin and intersecting the lidar scanning line. It then establishes the equation of the line scanned by the lidar, further obtaining the direction vectors and intersection coordinates of the lines. Finally, it completes the calibration based on the relationship between the direction vectors and intersections of the lines corresponding to different coordinate systems. (Refer to this...) Figure 2 Similarly, it requires constructing black and white checkerboards on both planes to create the calibration environment.

[0006] For example, Chinese patent document CN109375195B discloses a rapid calibration method for the extrinsic parameters of a multi-line lidar based on orthogonal normal vectors. The method involves the following steps: selecting a scene with a flat ground and a corner wall; parking an unmanned vehicle equipped with a multi-line lidar facing one of the walls; selecting radar data point sets illuminating three surfaces, labeled P1, P2, and P3; calculating the normal vectors I1, I2, and I3 for each data point set; calculating the normal vector set W1, W2, and W3 of the wall corresponding to the data point set in the vehicle coordinate system; labeling NI = [I1, I2, I3] and NW = [W1, W2, W3]; and performing singular value decomposition on H to obtain the rotation matrix R. (Refer to its...) Figure 2 It also constructs a calibration scene based on two walls.

[0007] For example, Chinese patent document CN112147599A discloses a continuous-time extrinsic parameter calibration method for 3D LiDAR and inertial sensors based on spline functions. The first stage is to preprocess the 3D laser point cloud in the calibration data based on a known environmental map. The second stage is to model the motion trajectory of the high-frequency inertial sensor as a continuous trajectory using spline functions, obtain the pose of the inertial sensor at any time based on the spline function, introduce extrinsic parameters between the 3D LiDAR and the inertial sensor, constrain the laser points, and construct an optimization problem for solution. Summary of the Invention

[0008] This disclosure provides a method and system for detecting the calibration quality of a robotic laser device.

[0009] According to one aspect of this disclosure, a method for detecting the calibration quality of a robotic laser device is provided, comprising:

[0010] S102, The robotic laser device emits a laser to illuminate at least the planar plate to form a laser line segment;

[0011] S104. Obtain the laser point cloud data of the laser line segment and the image data of the laser line segment;

[0012] S106. Obtain the position information of the laser point cloud data in the laser device coordinate system, and obtain the position information of the image data in the robot coordinate system;

[0013] S108. Based on the external parameter calibration parameters of the laser device, the position information of the laser point cloud data in the laser device coordinate system is converted into the position information in the robot coordinate system to obtain the first spatial feature and the second spatial feature of the laser point cloud data; based on the position information of the image data in the robot coordinate system, the first spatial feature and the second spatial feature of the image data are obtained.

[0014] S110. Obtain the first matching degree between the first spatial feature of the laser point cloud data and the first spatial feature of the image data, and obtain the second matching degree between the second spatial feature of the laser point cloud data and the second spatial feature of the image data.

[0015] S112. If the first matching degree meets the first preset condition and the second matching degree meets the second preset condition, then the external parameter calibration parameter is determined to be qualified; if the first matching degree does not meet the first preset condition or the second matching degree does not meet the second preset condition, then the external parameter calibration parameter is determined to be unqualified.

[0016] According to at least one embodiment of the present disclosure, a method for detecting the calibration quality of a robotic laser device is provided, wherein the robotic laser device emits laser light to illuminate a plurality of planar plates to form at least two laser line segments, wherein at least two planar plates are not parallel and have a common edge.

[0017] According to at least one embodiment of the present disclosure, a method for detecting the calibration quality of a robotic laser device is provided, wherein the robotic laser device emits laser light to illuminate three planar plates to form three laser line segments, wherein the three planar plates are perpendicular to each other.

[0018] A method for detecting the calibration quality of a robotic laser device according to at least one embodiment of this disclosure, comprising obtaining the position information of the laser point cloud data in the laser device coordinate system and obtaining the position information of the image data in the robot coordinate system, including:

[0019] Acquire the position information of the two endpoints of the laser point cloud data of the laser line segment in the coordinate system of the laser device, as well as the position information of two or more intermediate points between the two endpoints;

[0020] Acquire the position information of the two endpoints of the laser line segment in the robot coordinate system, as well as the position information of two or more intermediate points between the two endpoints.

[0021] A method for detecting the calibration quality of a robotic laser device according to at least one embodiment of the present disclosure, wherein the first spatial feature is a linear spatial feature and the second spatial feature is a point spatial feature.

[0022] According to at least one embodiment of the present disclosure, a method for detecting the calibration quality of a robotic laser device, wherein the number of midpoints of the laser line segment obtained based on laser point cloud data is the same as the number of midpoints of the laser line segment obtained based on image data.

[0023] A method for detecting the calibration quality of a robotic laser device according to at least one embodiment of the present disclosure, comprising obtaining a first matching degree between a first spatial feature of laser point cloud data and a first spatial feature of image data, and obtaining a second matching degree between a second spatial feature of laser point cloud data and a second spatial feature of image data, including:

[0024] The first matching degree is obtained based on the deviation between the first spatial features of laser point cloud data and the first spatial features of image data.

[0025] The second matching degree is obtained based on the deviation between the second spatial features of the laser point cloud data and the second spatial features of the image data.

[0026] According to another aspect of this disclosure, a method for detecting the calibration quality of a robotic laser device is provided, comprising:

[0027] S202, The robotic laser device emits a laser to illuminate at least the planar plate to form a laser area;

[0028] S204. Obtain laser point cloud data of the laser region and image data of the laser region;

[0029] S206. Obtain the position information of the laser point cloud data in the laser device coordinate system, and obtain the position information of the image data in the robot coordinate system;

[0030] S208. Based on the external parameter calibration parameters of the laser device, the position information of the laser point cloud data in the laser device coordinate system is converted into position information in the robot coordinate system to obtain the first spatial feature and the second spatial feature of the laser point cloud data; based on the position information of the image data in the robot coordinate system, the first spatial feature and the second spatial feature of the image data are obtained.

[0031] S210. Obtain the first matching degree between the first spatial feature of the laser point cloud data and the first spatial feature of the image data, and obtain the second matching degree between the second spatial feature of the laser point cloud data and the second spatial feature of the image data.

[0032] S212. If the first matching degree meets the first preset condition and the second matching degree meets the second preset condition, then the external parameter calibration parameter is determined to be qualified; if the first matching degree does not meet the first preset condition or the second matching degree does not meet the second preset condition, then the external parameter calibration parameter is determined to be unqualified.

[0033] A method for detecting the calibration quality of a robotic laser device according to at least one embodiment of the present disclosure, wherein the robotic laser device emits laser light to irradiate a plurality of planar plates to form at least two laser regions, wherein the at least two planar plates are not parallel and have a common edge.

[0034] According to at least one embodiment of the present disclosure, a method for detecting the calibration quality of a robotic laser device is provided, wherein the robotic laser device emits laser light to illuminate three planar plates to form three laser regions, wherein the three planar plates are perpendicular to each other.

[0035] A method for detecting the calibration quality of a robotic laser device according to at least one embodiment of this disclosure, comprising obtaining the position information of the laser point cloud data in the laser device coordinate system and obtaining the position information of the image data in the robot coordinate system, including:

[0036] Acquire the position information of the two endpoints of the arc-shaped line segment of the edge contour of the laser point cloud data in the laser device coordinate system, as well as the position information of two or more intermediate points between the two endpoints;

[0037] Acquire the position information of the two endpoints of the arc-shaped edge contour line segment of the laser line segment in the robot coordinate system, as well as the position information of two or more intermediate points between the two endpoints.

[0038] A method for detecting the calibration quality of a robotic laser device according to at least one embodiment of the present disclosure, wherein the first spatial feature is a linear spatial feature and the second spatial feature is a point spatial feature.

[0039] According to at least one embodiment of the present disclosure, a method for detecting the calibration quality of a robotic laser device, wherein the number of midpoints of the edge contour arc segment obtained based on laser point cloud data is the same as the number of midpoints of the edge contour arc segment obtained based on image data.

[0040] A method for detecting the calibration quality of a robotic laser device according to at least one embodiment of the present disclosure, comprising obtaining a first matching degree between a first spatial feature of laser point cloud data and a first spatial feature of image data, and obtaining a second matching degree between a second spatial feature of laser point cloud data and a second spatial feature of image data, including:

[0041] The first matching degree is obtained based on the deviation between the first spatial features of laser point cloud data and the first spatial features of image data.

[0042] The second matching degree is obtained based on the deviation between the second spatial features of the laser point cloud data and the second spatial features of the image data.

[0043] According to another aspect of this disclosure, an apparatus for detecting the calibration quality of a robotic laser device is provided, comprising:

[0044] A laser point cloud data acquisition module acquires laser point cloud data of a laser line segment;

[0045] An image data acquisition module acquires image data of the laser line segment;

[0046] The first position information extraction module obtains the position information of the laser point cloud data in the coordinate system of the laser device.

[0047] The second position information extraction module acquires the position information of the image data in the robot coordinate system.

[0048] A laser point cloud data spatial feature acquisition module, which converts the position information of the laser point cloud data in the laser device coordinate system into the position information in the robot coordinate system based on the external parameter calibration parameters of the laser device, so as to obtain the first spatial feature and the second spatial feature of the laser point cloud data.

[0049] An image data spatial feature acquisition module, wherein the image data spatial feature acquisition module acquires a first spatial feature and a second spatial feature of the image data based on the position information of the image data in the robot coordinate system;

[0050] The matching degree acquisition module acquires the first matching degree between the first spatial feature of the laser point cloud data and the first spatial feature of the image data, and acquires the second matching degree between the second spatial feature of the laser point cloud data and the second spatial feature of the image data.

[0051] The judgment module makes judgments based on the following judgment logic: if the first matching degree meets the first preset condition and the second matching degree meets the second preset condition, then the external parameter calibration parameter is determined to be qualified; if the first matching degree does not meet the first preset condition or the second matching degree does not meet the second preset condition, then the external parameter calibration parameter is determined to be unqualified.

[0052] The laser line segment is formed by the laser emitted by the robot's laser device irradiating the flat plate.

[0053] According to another aspect of this disclosure, an apparatus for detecting the calibration quality of a robotic laser device is provided, comprising:

[0054] A laser point cloud data acquisition module acquires laser point cloud data of the laser region.

[0055] An image data acquisition module acquires image data of the laser region;

[0056] The first position information extraction module obtains the position information of the laser point cloud data in the coordinate system of the laser device.

[0057] The second position information extraction module acquires the position information of the image data in the robot coordinate system.

[0058] A laser point cloud data spatial feature acquisition module, which converts the position information of the laser point cloud data in the laser device coordinate system into the position information in the robot coordinate system based on the external parameter calibration parameters of the laser device, so as to obtain the first spatial feature and the second spatial feature of the laser point cloud data.

[0059] An image data spatial feature acquisition module, wherein the image data spatial feature acquisition module acquires a first spatial feature and a second spatial feature of the image data based on the position information of the image data in the robot coordinate system;

[0060] The matching degree acquisition module acquires the first matching degree between the first spatial feature of the laser point cloud data and the first spatial feature of the image data, and acquires the second matching degree between the second spatial feature of the laser point cloud data and the second spatial feature of the image data.

[0061] The judgment module makes judgments based on the following judgment logic: if the first matching degree meets the first preset condition and the second matching degree meets the second preset condition, then the external parameter calibration parameter is determined to be qualified; if the first matching degree does not meet the first preset condition or the second matching degree does not meet the second preset condition, then the external parameter calibration parameter is determined to be unqualified.

[0062] The laser region is the area formed by the laser emitted by the robot's laser device irradiating the flat plate.

[0063] According to another aspect of this disclosure, an auxiliary device for calibration quality inspection of a robotic laser device is provided, comprising:

[0064] Support device;

[0065] The platform is mounted on the support device or is integrally formed with the support device;

[0066] A positioning device is disposed in a first area of ​​the platform for positioning the robot to be inspected;

[0067] A planar plate device is disposed in the second region of the platform to receive lasers emitted by the robot to be tested, such that the lasers emitted by the robot form laser lines or laser regions on the planar plate device, and the robot to be tested can collect laser point cloud data of the laser lines or laser regions.

[0068] According to at least one embodiment of the auxiliary device of this disclosure, a second region of the platform is provided with at least one positioning line region for positioning the planar plate device, wherein the positioning lines of the positioning line region are parallel to each other and are equally spaced.

[0069] According to at least one embodiment of the auxiliary device of this disclosure, the positioning line is formed by a through-hole groove or a blind-hole groove.

[0070] According to at least one embodiment of the auxiliary device of this disclosure, the second region of the platform is provided with two positioning line regions, and the two positioning line regions are symmetrically arranged about an axis of symmetry, and the axis of symmetry passes through the projection of the geometric center of the positioning device onto the first region.

[0071] According to at least one embodiment of the auxiliary device of this disclosure, the positioning line region is a rectangular region.

[0072] According to at least one embodiment of the auxiliary device of this disclosure, the positioning device includes a left and right positioning component and a front and back positioning component. The left and right positioning component is used to position the left and right edges of the robot to be detected, and the front and back positioning component is used to position the front and back edges of the robot to be detected.

[0073] According to at least one embodiment of the auxiliary device of the present disclosure, the left and right positioning components include a positioning groove disposed on the left edge of the positioning device and having an edge, and the front and rear positioning components include a positioning bracket disposed on the front edge of the positioning device and a positioning protrusion disposed on the rear edge.

[0074] According to at least one embodiment of the auxiliary device of this disclosure, the planar plate device comprises at least two non-parallel planar plates having a common edge.

[0075] According to at least one embodiment of the auxiliary device of this disclosure, the planar plate device comprises three mutually perpendicular planar plates.

[0076] According to at least one embodiment of the auxiliary device of the present disclosure, the planar plate device has a first planar plate, a second planar plate, a fourth planar plate and two third planar plates, wherein the second planar plate and the fourth planar plate are parallel to each other and both are perpendicular to the first planar plate, and the two third planar plates are parallel to each other and both are perpendicular to the first planar plate, wherein the surface of the first planar plate faces the positioning device.

[0077] According to another aspect of this disclosure, a detection system for detecting the calibration quality of a robotic laser device is provided, comprising:

[0078] This disclosure includes auxiliary devices according to any one embodiment;

[0079] An image acquisition device is positioned directly above the positioning device, and the projection of the geometric center of the image acquisition device onto the platform coincides with the projection of the geometric center of the positioning device onto the platform. The image acquisition device is capable of acquiring image data of the laser line segment or the laser region.

[0080] The detection system according to at least one embodiment of the present disclosure further includes:

[0081] The data processing device is capable of acquiring laser point cloud data of laser line segments or laser regions collected by the robot to be detected, and is also capable of acquiring image data of laser line segments or laser regions collected by the image acquisition device.

[0082] According to at least one embodiment of the detection system of the present disclosure, the data processing device includes a memory and a processor, wherein the memory stores in the form of program instructions an apparatus for detecting the calibration quality of a robotic laser device according to any embodiment of the present disclosure.

[0083] According to another aspect of this disclosure, an electronic device is provided, comprising: a memory storing execution instructions; and a processor executing the execution instructions stored in the memory, causing the processor to perform a method for detecting the calibration quality of a robotic laser device according to any embodiment of this disclosure. Attached Figure Description

[0084] The accompanying drawings illustrate exemplary embodiments of the present disclosure and, together with the description thereof, serve to explain the principles of the present disclosure. These drawings are included to provide a further understanding of the present disclosure and are incorporated in and constitute a part of this specification.

[0085] Figure 1 A flowchart illustrating a method for detecting the calibration quality of a robotic laser device according to one embodiment of this disclosure is shown.

[0086] Figure 2 A cleaning robot with a laser device is shown as one embodiment of the present disclosure.

[0087] Figure 3 A detection system according to one embodiment of the present disclosure is shown.

[0088] Figure 4A schematic diagram of the structure of a planar plate device according to one embodiment of the present disclosure is shown.

[0089] Figure 5 The laser segment 01, laser segment 02, and laser segment 03 formed on three planar plates in this embodiment are shown.

[0090] Figure 6 A flowchart illustrating a method for detecting the calibration quality of a robotic laser device according to yet another embodiment of this disclosure is shown.

[0091] Figure 7 This is a schematic block diagram of a device for detecting the calibration quality of a robot laser device using a hardware implementation of a processing system, according to one embodiment of this disclosure.

[0092] Explanation of reference numerals in the attached figures

[0093] 100 Detection System

[0094] 110 Support device

[0095] 111 Platform

[0096] 112 Positioning Line Area

[0097] 120 positioning device

[0098] 121 Positioning slot

[0099] 122 Positioning Bracket

[0100] 123 Positioning Protrusion

[0101] 130 Image Acquisition Device

[0102] 140 Flat plate device

[0103] 141 First Plane Plate

[0104] 142 Second Plane Plate

[0105] 143 Third Plane Plate

[0106] 144 Fourth Plane Plate

[0107] 150 Data Processing Unit

[0108] 200 robots

[0109] 210 Laser Device

[0110] 1000 A device for detecting the calibration quality of robotic laser devices

[0111] 1002 Laser Point Cloud Data Acquisition Module

[0112] 1004 Image Data Acquisition Module

[0113] 1006 First Location Information Extraction Module

[0114] 1008 Second Location Information Extraction Module

[0115] 1010 Laser Point Cloud Data Spatial Feature Acquisition Module

[0116] 1012 Image Data Spatial Feature Acquisition Module

[0117] 1014 Matching Degree Acquisition Module

[0118] 1016 Judgment Module

[0119] 1100 bus

[0120] 1200 processor

[0121] 1300 memory

[0122] 1400 Other circuits. Detailed Implementation

[0123] The present disclosure will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the disclosure. Furthermore, it should be noted that, for ease of description, only the parts relevant to the present disclosure are shown in the accompanying drawings.

[0124] It should be noted that, where there is no conflict, the embodiments and features described in this disclosure can be combined with each other. The technical solutions of this disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0125] Unless otherwise stated, the exemplary implementations / embodiments shown are to be understood as providing exemplary features of various details that provide ways in which the technical concepts of this disclosure can be implemented in practice. Therefore, unless otherwise stated, the features of various implementations / embodiments may be additionally combined, separated, interchanged and / or rearranged without departing from the technical concepts of this disclosure.

[0126] The use of crosshairs and / or shading in the accompanying drawings is generally used to clarify the boundaries between adjacent components. Thus, unless otherwise stated, the presence or absence of crosshairs or shading does not convey or indicate any preference or requirement for the specific material, material properties, dimensions, proportions, commonalities between the illustrated components, or any other characteristics, properties, etc., of the components. Furthermore, in the accompanying drawings, the dimensions and relative dimensions of components may be exaggerated for clarity and / or descriptive purposes. When exemplary embodiments can be implemented differently, a specific process sequence may be performed in a different order than that described. For example, two consecutively described processes may be performed substantially simultaneously or in the reverse order of their description. Furthermore, the same reference numerals denote the same components.

[0127] When a component is referred to as being "on" or "above" another component, "connected to," or "joined to" another component, the component may be directly on, directly connected to, or directly joined to the other component, or there may be intermediate components. However, when a component is referred to as being "directly on" another component, "directly connected to," or "directly joined to" another component, there are no intermediate components. Therefore, the term "connection" can refer to a physical connection, an electrical connection, etc., and may or may not have intermediate components.

[0128] The terminology used herein is for the purpose of describing particular embodiments and is not intended to be limiting. As used herein, unless the context clearly indicates otherwise, the singular forms “a” and “the” are intended to include the plural forms as well. Furthermore, when the terms “comprising” and / or “including” and variations thereof are used in this specification, it indicates the presence of the stated features, integrals, steps, operations, parts, components, and / or groups thereof, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, parts, components, and / or groups thereof. It should also be noted that, as used herein, the terms “substantially,” “about,” and other similar terms are used as approximate terms rather than as terms of degree, thus explaining the inherent biases in measurements, calculated values, and / or provided values ​​that would be recognized by one of ordinary skill in the art.

[0129] The following text combines Figures 1 to 7 The present disclosure provides a detailed description of the method, auxiliary equipment, and testing system for detecting the calibration quality of a robotic laser device.

[0130] Figure 1 A flowchart illustrating a method for detecting the calibration quality of a robotic laser device according to one embodiment of this disclosure is shown.

[0131] refer to Figure 1The method S100 for detecting the calibration quality of a robot laser device in this embodiment includes:

[0132] S102, The robotic laser device emits a laser to illuminate at least the planar plate to form a laser line segment;

[0133] S104. Obtain laser point cloud data of the laser line segment and image data of the laser line segment;

[0134] S106. Obtain the position information of the laser point cloud data in the laser device coordinate system, and obtain the position information of the image data in the robot coordinate system;

[0135] S108. Based on the external parameter calibration parameters (e.g., external parameter calibration matrix) of the laser device, the position information of the laser point cloud data in the laser device coordinate system is converted into the position information in the robot coordinate system to obtain the first spatial feature and the second spatial feature of the laser point cloud data; based on the position information of the image data in the robot coordinate system, the first spatial feature and the second spatial feature of the image data are obtained.

[0136] S110. Obtain the first matching degree between the first spatial feature of the laser point cloud data and the first spatial feature of the image data, and obtain the second matching degree between the second spatial feature of the laser point cloud data and the second spatial feature of the image data.

[0137] S112. If the first matching degree meets the first preset condition and the second matching degree meets the second preset condition, the external parameter calibration parameter is deemed qualified; if the first matching degree does not meet the first preset condition or the second matching degree does not meet the second preset condition, the external parameter calibration parameter is deemed unqualified.

[0138] The laser emitted by the laser device described in this embodiment is located in the same plane, so that when the laser shines on an object, it is linear. For example, when it shines on a plane, it will form a laser line on the plane.

[0139] The robot in this disclosure can be a cleaning robot, such as the disc-type cleaning robot in the prior art. Figure 2 A cleaning robot 200 according to one embodiment of the present disclosure is shown, which has a laser device 210, which may be a laser rangefinder (LDS laser rangefinder). In some embodiments, the laser device 210 is rotatably disposed on the cleaning robot 200 and exposed from the upper housing.

[0140] Due to structural limitations of the cleaning robot 200, the laser device coordinate system of the laser device 210 is different from the robot coordinate system of the cleaning robot 200. The data obtained by the laser device 210 after ranging (e.g., obstacle distance) needs to be converted to the robot coordinate system through external parameter calibration parameters. The robot coordinate system generally takes the projection of the geometric center of the cleaning robot onto the ground as the origin, with the x-direction being the front of the robot, the y-direction being the left of the robot, and the z-direction being the top of the robot.

[0141] Therefore, the cleaning robot needs to be calibrated at the time of leaving the factory to obtain external parameter calibration parameters (the specific parameters of the ground can be obtained by existing methods, and this disclosure does not make any special limitation on them). However, after the external parameter calibration parameters are obtained, it is generally difficult to detect the calibration quality in the prior art. In particular, for some laser devices 210, which can rotate to measure the distance of obstacles in different areas, some embodiments of the laser device 210 can emit vertical laser lines and horizontal laser lines. While measuring the distance of obstacles, it can also measure the size of obstacles. The detection of calibration quality becomes particularly important and affects the accuracy of the laser device 210 in detecting obstacles.

[0142] The method S100 for detecting the calibration quality of a robotic laser device disclosed herein can be based on Figure 3 The detection system 100 shown is implemented.

[0143] refer to Figure 3 The detection system 100 of the preferred embodiment of this disclosure includes a robot positioning device 120 and a planar plate device 140 having a preset positional relationship with the robot positioning device 120. The planar plate device 140 receives vertical and / or horizontal linear lasers emitted by the laser device 210, thereby forming laser line segments on at least one planar plate of the planar plate device 140.

[0144] The detection system 100 disclosed herein also includes an image acquisition device 130, which may be a CCD image sensor, etc. This disclosure does not specifically limit the specific type / model of the image sensor 130.

[0145] Preferably, when the cleaning robot 200 is positioned on the robot positioning device 120, the projection of the geometric center of the image acquisition device 130 onto the ground or onto the support plate of the positioning device 120 coincides with the projection of the geometric center of the cleaning robot onto the ground or onto the support plate of the positioning device 120, so that the coordinate system of the image acquisition device and the robot coordinate system differ only in the z-axis. Based on this difference, the coordinate system of the image acquisition device and the robot coordinate system can be easily converted.

[0146] Continue to refer to Figure 3 The detection system 100 of this disclosure also includes a data processing device 150 (e.g., a computer with a memory and a processor). The data processing device 150 acquires laser point cloud data of the laser line segment collected by the laser device 210 of the cleaning robot 200, acquires image data of the laser line segment collected by the image acquisition device 130, and executes the following steps based on program instructions:

[0147] Obtain the position information of laser point cloud data in the laser device coordinate system, and obtain the position information of image data in the robot coordinate system;

[0148] Based on the external parameter calibration parameters (e.g., external parameter calibration matrix) of the laser device, the position information of the laser point cloud data in the laser device coordinate system is converted into the position information in the robot coordinate system to obtain the first spatial feature and the second spatial feature of the laser point cloud data; based on the position information of the image data in the robot coordinate system, the first spatial feature and the second spatial feature of the image data are obtained.

[0149] The program instructions can be stored in the memory of the data processing device 150, and the above processing steps are implemented when the program instructions are executed by the processor of the data processing device 150.

[0150] In some embodiments of this disclosure, the cleaning robot 200 can establish a communication connection (preferably a wireless communication connection) with the data processing device 150 to transmit the laser point cloud data collected by the laser device 210 to the data processing device 150, and the image acquisition device 130 can establish a communication connection (preferably a wired communication connection) with the data processing device 150 to transmit the image data of the laser line segment collected by the image acquisition device 130 to the data processing device 150.

[0151] This disclosure further obtains two matching degrees by using two spatial features of laser point cloud data of laser line segments in the same coordinate system (robot coordinate system) and two spatial features of image data of laser line segments, thereby detecting the calibration effect of the laser device.

[0152] Furthermore, if the first matching degree meets the first preset condition and the second matching degree meets the second preset condition, the external parameter calibration parameter is deemed qualified; if the first matching degree does not meet the first preset condition or the second matching degree does not meet the second preset condition, the external parameter calibration parameter is deemed unqualified.

[0153] In some embodiments of the present disclosure, a method for detecting the calibration quality of a robotic laser device involves the robotic laser device emitting laser light to illuminate multiple planar plates to form at least two laser line segments, wherein at least two planar plates are not parallel and have a common edge.

[0154] For example, when a laser device emits a horizontal fan-shaped laser beam, causing this horizontal fan-shaped laser beam to illuminate a non-parallel planar plate that shares a common edge (e.g. Figure 4 The first planar plate 141 and (one or two) third planar plates 143 form two or more laser line segments, thereby detecting the calibration effect of the laser device based on the laser point cloud data and image data of the two or more laser line segments.

[0155] In this embodiment, the external parameter calibration parameters are deemed qualified only when both the first and second matching degrees of multiple laser line segments meet the matching degree conditions described above; otherwise, they are deemed unqualified.

[0156] In this embodiment, the laser device can also emit a vertical fan-shaped laser beam, which illuminates a non-parallel planar plate sharing a common surface (e.g., Figure 4 The first planar plate 141 and the second planar plate 142, or Figure 4 The first planar plate 141, the second planar plate 142 and the fourth planar plate 144 in the process form two or more laser line segments, thereby detecting the calibration effect of the laser device based on the laser point cloud data and image data of the two or more laser line segments.

[0157] In some embodiments of this disclosure, the robotic laser device emits laser light to illuminate three planar plates to form three laser lines, wherein the three planar plates are perpendicular to each other.

[0158] In this embodiment, the laser emission angle of the laser device 210 can be adjusted so that the fan-shaped laser emitted by the laser device 210 can simultaneously irradiate three planar plates and form laser line segments on each of the three planar plates. The calibration effect of the laser device can then be detected based on the laser point cloud data and image data of the three laser line segments, thereby further improving the accuracy of the detection.

[0159] Figure 5 The laser segment 01, laser segment 02, and laser segment 03 formed on three planar plates in this embodiment are shown.

[0160] Combination Figure 4 and Figure 5In some embodiments of this disclosure, the planar plate device 140 has a first planar plate 141, a third planar plate 143, and a fourth planar plate 144 that are perpendicular to each other, providing three planar plates. In other embodiments of this disclosure, the planar plate device 140 has a first planar plate 141, a second planar plate 142, a fourth planar plate 144, and two third planar plates 143, wherein the second planar plate 142 and the fourth planar plate 144 are parallel to each other and both are perpendicular to the first planar plate 141, and the two third planar plates 143 are parallel to each other and both are perpendicular to the first planar plate 141, wherein the surface of the first planar plate 141 faces the laser device 210.

[0161] In some embodiments of this disclosure, obtaining the position information of laser point cloud data in the laser device coordinate system and obtaining the position information of image data in the robot coordinate system includes:

[0162] Acquire the position information of the two endpoints of the laser point cloud data of the laser line segment in the coordinate system of the laser device, as well as the position information of two or more intermediate points between the two endpoints;

[0163] Acquire the position information of the two endpoints of the laser line segment in the robot coordinate system, as well as the position information of two or more intermediate points between the two endpoints.

[0164] In this embodiment, the location information of the laser point cloud data of the laser line segment can be obtained by using the laser point cloud processing algorithm in the prior art, and the location information of the image data of the laser line segment can be obtained by using the image processing algorithm in the prior art. This disclosure does not make any special limitation in this regard.

[0165] In the method for detecting the calibration quality of the robotic laser device disclosed herein, the first spatial feature is the spatial feature of a line, and the second spatial feature is the spatial feature of a point.

[0166] In some embodiments of this disclosure, the spatial characteristics of the line described above are the slope of the laser line segment, and the spatial characteristics of the point described above are the coordinates of the midpoint of the laser line segment.

[0167] According to a preferred embodiment of the present disclosure, the method for detecting the calibration quality of a robotic laser device involves obtaining the same number of midpoints of laser line segments based on laser point cloud data as obtaining the same number of midpoints of laser line segments based on image data.

[0168] A method for detecting the calibration quality of a robotic laser device according to some embodiments of this disclosure, comprising obtaining a first matching degree between a first spatial feature of laser point cloud data and a first spatial feature of image data, and obtaining a second matching degree between a second spatial feature of laser point cloud data and a second spatial feature of image data, including:

[0169] The first matching degree is obtained based on the deviation between the first spatial features of laser point cloud data and the first spatial features of image data;

[0170] The second matching degree is obtained by the deviation between the second spatial features of laser point cloud data and the second spatial features of image data.

[0171] In some embodiments of this disclosure, the first spatial feature is the slope of the laser line segment, and the second spatial feature is the coordinates of the midpoint of the laser line segment. The first matching degree described above can be obtained based on the deviation between the slope of the laser line segment obtained from laser point cloud data and the slope of the laser line segment obtained from image data. The second matching degree described above can be obtained based on the deviation between the coordinates of the midpoint of the laser line segment obtained from laser point cloud data and the coordinates of the midpoint of the laser line segment obtained from image data.

[0172] Figure 6 A flowchart illustrating a method for detecting the calibration quality of a robotic laser device according to yet another embodiment of this disclosure is shown.

[0173] refer to Figure 6 The method S200 for detecting the calibration quality of the robot laser device in this embodiment includes:

[0174] S202, The robotic laser device emits a laser to illuminate at least the planar plate to form a laser area;

[0175] S204. Obtain laser point cloud data of the laser region and image data of the laser region;

[0176] S206. Obtain the position information of the laser point cloud data in the laser device coordinate system, and obtain the position information of the image data in the robot coordinate system;

[0177] S208. Based on the external parameter calibration parameters (e.g., external parameter calibration matrix) of the laser device, the position information of the laser point cloud data in the laser device coordinate system is converted into the position information in the robot coordinate system to obtain the first spatial feature and the second spatial feature of the laser point cloud data; based on the position information of the image data in the robot coordinate system, the first spatial feature and the second spatial feature of the image data are obtained.

[0178] S210. Obtain the first matching degree between the first spatial feature of the laser point cloud data and the first spatial feature of the image data, and obtain the second matching degree between the second spatial feature of the laser point cloud data and the second spatial feature of the image data.

[0179] S212. If the first matching degree meets the first preset condition and the second matching degree meets the second preset condition, the external parameter calibration parameter is deemed qualified; if the first matching degree does not meet the first preset condition or the second matching degree does not meet the second preset condition, the external parameter calibration parameter is deemed unqualified.

[0180] In some embodiments of the laser device 210, distance and position detection of obstacles are performed based on the emitted conical laser beam. In the method S200 of this embodiment for detecting the calibration quality of the robot laser device, the laser irradiates the planar plate and forms a laser area instead of a laser line segment. It can be a circular laser area or a laser area of ​​a part of a circle.

[0181] In a method S200 for detecting the calibration quality of a robotic laser device according to some embodiments of this disclosure, the robotic laser device emits a laser to irradiate multiple planar plates to form at least two laser regions, wherein the at least two planar plates are not parallel and have a common edge.

[0182] In the method S200 of some embodiments of the present disclosure for detecting the calibration quality of a robotic laser device, the robotic laser device emits laser light to irradiate three planar plates to form three laser regions, wherein the three planar plates are perpendicular to each other.

[0183] In the method S200 for detecting the calibration quality of a robot laser device according to some embodiments of this disclosure, the method includes acquiring the position information of laser point cloud data in the laser device coordinate system and acquiring the position information of image data in the robot coordinate system, including:

[0184] Acquire the position information of the two endpoints of the arc-shaped line segment of the edge contour of the laser point cloud data in the laser device coordinate system, as well as the position information of two or more intermediate points between the two endpoints;

[0185] Acquire the position information of the two endpoints of the arc-shaped edge contour line segment of the laser line segment in the robot coordinate system, as well as the position information of two or more intermediate points between the two endpoints.

[0186] In the method S200 for detecting the calibration quality of a robot laser device according to some embodiments of this disclosure, the first spatial feature is a line spatial feature and the second spatial feature is a point spatial feature.

[0187] In the method S200 for detecting the calibration quality of a robotic laser device according to some embodiments of this disclosure, the number of midpoints of the edge contour arc segment obtained based on laser point cloud data is the same as the number of midpoints of the edge contour arc segment obtained based on image data.

[0188] In the method S200 for detecting the calibration quality of a robotic laser device according to some embodiments of this disclosure, obtaining a first matching degree between the first spatial features of laser point cloud data and the first spatial features of image data, and obtaining a second matching degree between the second spatial features of laser point cloud data and the second spatial features of image data, includes:

[0189] The first matching degree is obtained based on the deviation between the first spatial features of laser point cloud data and the first spatial features of image data;

[0190] The second matching degree is obtained by the deviation between the second spatial features of laser point cloud data and the second spatial features of image data.

[0191] In some embodiments of this disclosure, the first spatial feature is the curvature of the edge contour arc segment, and the second spatial feature is the coordinates of the midpoint of the edge contour arc segment. The first matching degree described above can be obtained based on the deviation between the curvature of the edge contour arc segment obtained from laser point cloud data and the curvature of the edge contour arc segment obtained from image data. The second matching degree described above can be obtained based on the deviation between the midpoint coordinates of the edge contour arc segment obtained from laser point cloud data and the midpoint coordinates of the edge contour arc segment obtained from image data.

[0192] This disclosure also provides a device for detecting the calibration quality of a robotic laser device.

[0193] An apparatus 1000 for detecting the calibration quality of a robotic laser device according to one embodiment of the present disclosure includes:

[0194] Laser point cloud data acquisition module 1002 acquires laser point cloud data of laser line segments;

[0195] Image data acquisition module 1004 acquires image data of the laser line segment;

[0196] The first position information extraction module 1006 acquires the position information of the laser point cloud data in the coordinate system of the laser device.

[0197] The second position information extraction module 1008 acquires the position information of the image data in the robot coordinate system.

[0198] The laser point cloud data spatial feature acquisition module 1010 converts the position information of the laser point cloud data in the laser device coordinate system into the position information in the robot coordinate system based on the external parameter calibration parameters (e.g., external parameter calibration matrix) of the laser device, so as to obtain the first spatial feature and the second spatial feature of the laser point cloud data.

[0199] Image data spatial feature acquisition module 1012 acquires first spatial features and second spatial features of image data based on the position information of image data in robot coordinate system;

[0200] The matching degree acquisition module 1014 acquires the first matching degree between the first spatial feature of the laser point cloud data and the first spatial feature of the image data, and acquires the second matching degree between the second spatial feature of the laser point cloud data and the second spatial feature of the image data.

[0201] The judgment module 1016 makes judgments based on the following judgment logic: if the first matching degree meets the first preset condition and the second matching degree meets the second preset condition, then the external parameter calibration parameter is determined to be qualified; if the first matching degree does not meet the first preset condition or the second matching degree does not meet the second preset condition, then the external parameter calibration parameter is determined to be unqualified.

[0202] Among them, the laser line segment is the laser line segment formed by the laser emitted by the robot's laser device irradiating the flat plate.

[0203] The device 1000 for detecting the calibration quality of the robot laser device in this embodiment can be implemented based on a computer software architecture (see reference). Figure 7 ).

[0204] An apparatus 1000 for detecting the calibration quality of a robotic laser device according to another embodiment of the present disclosure includes:

[0205] Laser point cloud data acquisition module 1002 acquires laser point cloud data of the laser region;

[0206] Image data acquisition module 1004 acquires image data of the laser area;

[0207] The first position information extraction module 1006 acquires the position information of the laser point cloud data in the coordinate system of the laser device.

[0208] The second position information extraction module 1008 acquires the position information of the image data in the robot coordinate system.

[0209] The laser point cloud data spatial feature acquisition module 1010 converts the position information of the laser point cloud data in the laser device coordinate system into the position information in the robot coordinate system based on the external parameter calibration parameters (e.g., external parameter calibration matrix) of the laser device, so as to obtain the first spatial feature and the second spatial feature of the laser point cloud data.

[0210] Image data spatial feature acquisition module 1012 acquires first spatial features and second spatial features of image data based on the position information of image data in robot coordinate system;

[0211] The matching degree acquisition module 1014 acquires the first matching degree between the first spatial feature of the laser point cloud data and the first spatial feature of the image data, and acquires the second matching degree between the second spatial feature of the laser point cloud data and the second spatial feature of the image data.

[0212] The judgment module 1016 makes judgments based on the following judgment logic: if the first matching degree meets the first preset condition and the second matching degree meets the second preset condition, then the external parameter calibration parameter is determined to be qualified; if the first matching degree does not meet the first preset condition or the second matching degree does not meet the second preset condition, then the external parameter calibration parameter is determined to be unqualified.

[0213] The laser area is the area formed by the laser emitted by the robot's laser device illuminating the flat plate.

[0214] Figure 7 This is a schematic block diagram of a device 1000 for detecting the calibration quality of a robot laser device using a hardware implementation of a processing system, according to one embodiment of this disclosure.

[0215] The apparatus may include corresponding modules that perform one or more steps in the flowchart above. Therefore, each or more steps in the flowchart above can be performed by a corresponding module, and the apparatus may include one or more of these modules. A module may be one or more hardware modules specifically configured to perform a corresponding step, or implemented by a processor configured to perform a corresponding step, or stored in a computer-readable medium for implementation by a processor, or implemented through some combination thereof.

[0216] This hardware architecture can be implemented using a bus architecture. The bus architecture can include any number of interconnect buses and bridges, depending on the specific application and overall design constraints of the hardware. Bus 1100 connects various circuits, including one or more processors 1200, memory 1300, and / or hardware modules. Bus 1100 can also connect various other circuits 1400, such as peripherals, voltage regulators, power management circuits, external antennas, etc.

[0217] Bus 1100 can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Component (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, only one connection line is used in this diagram, but this does not imply that there is only one bus or only one type of bus.

[0218] Any process or method description in the flowcharts or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of this disclosure includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of this disclosure pertain. The processor performs the various methods and processes described above. For example, the method embodiments of this disclosure may be implemented as software programs tangibly contained in a machine-readable medium, such as memory. In some embodiments, part or all of the software program may be loaded and / or installed via memory and / or a communication interface. When the software program is loaded into memory and executed by the processor, one or more steps of the methods described above may be performed. Alternatively, in other embodiments, the processor may be configured to perform one of the methods described above by any other suitable means (e.g., by means of firmware).

[0219] The logic and / or steps represented in the flowchart or otherwise described herein may be specifically implemented in any readable storage medium for use by, or in conjunction with, an instruction execution system, apparatus or device (such as a computer-based system, a processor-included system or other system that can fetch and execute instructions from, an instruction execution system, apparatus or device).

[0220] For the purposes of this specification, a "readable storage medium" can be any means capable of containing, storing, communicating, propagating, or transmitting a program for use by or in conjunction with an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and portable read-only memory (CDROM). Furthermore, a readable storage medium can even be paper or other suitable media on which a program can be printed, since a program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in memory.

[0221] It should be understood that various parts of this disclosure can be implemented in hardware, software, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0222] Those skilled in the art will understand that all or part of the steps of the methods described above can be implemented by a program instructing related hardware. The program can be stored in a readable storage medium, and when executed, the program includes one or a combination of the steps of the method implementation.

[0223] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into a single processing module, or each unit can exist physically separately, or two or more units can be integrated into a single module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a readable storage medium. The storage medium can be a read-only memory, a disk, or an optical disk, etc.

[0224] Refer again Figure 3 and Figure 4 This disclosure also provides auxiliary equipment for calibration quality inspection of robotic laser devices, including:

[0225] Support device 110;

[0226] Platform 111 is mounted on or integrally formed with support device 110;

[0227] Positioning device 120 is disposed in a first area of ​​the platform for positioning a robot to be inspected (e.g., a cleaning robot);

[0228] The planar plate device 140 is set in the second area of ​​the platform 111 to receive the laser emitted by the robot to be tested, so that the laser emitted by the robot forms laser line segments or laser areas on the planar plate device 140, and the robot to be tested can collect laser point cloud data of the laser line segments or laser areas.

[0229] For the auxiliary equipment of the above embodiment, the second region of the platform 111 is provided with at least one positioning line region 112 to position the planar plate device 140, and the positioning lines of the positioning line region 112 are parallel to each other and have the same spacing.

[0230] For the auxiliary devices of the above embodiments, preferably, the positioning line is formed by a through-hole groove or a blind-hole groove.

[0231] In some embodiments of the auxiliary device disclosed herein, the second region of the platform 111 is provided with two positioning line regions 112, and the two positioning line regions 112 are symmetrically arranged about a symmetry axis, and the symmetry axis passes through the projection of the geometric center of the positioning device 120 into the first region.

[0232] According to the preferred embodiment of the auxiliary device of this disclosure, the positioning line area 112 is a rectangular area.

[0233] In some embodiments of this disclosure, the positioning device 120 includes a left and right positioning component and a front and back positioning component. The left and right positioning component is used to position the left and right edges of the robot to be detected, and the front and back positioning component is used to position the front and back edges of the robot to be detected.

[0234] In some embodiments of this disclosure, the left and right positioning components include a positioning groove 121 (e.g., capable of accommodating a robot wheel) disposed on the left edge of the positioning device 120, and the front and rear positioning components include a positioning bracket 122 disposed on the front edge of the positioning device 120 and a positioning protrusion 123 disposed on the rear edge.

[0235] For the auxiliary devices of the above embodiments, preferably, the planar plate device 140 includes at least two non-parallel planar plates that share a common edge.

[0236] For the auxiliary devices of the above embodiments, preferably, the planar plate device 140 includes three mutually perpendicular planar plates.

[0237] In some embodiments of this disclosure, the planar plate device 140 has a first planar plate 141, a second planar plate 142, a fourth planar plate 144, and two third planar plates 143, wherein the second planar plate 142 and the fourth planar plate 144 are parallel to each other and both are perpendicular to the first planar plate 141, and the two third planar plates 143 are parallel to each other and both are perpendicular to the first planar plate 141, wherein the surface of the first planar plate 141 faces the positioning device 120.

[0238] The auxiliary device provided in this disclosure can position the robot 200 and the flat panel device to be inspected, and the distance between the robot and the flat panel device can be adjusted based on the positioning line area to adapt to the inspection of the robot's laser device.

[0239] This disclosure also provides a testing system 100 for detecting the calibration quality of a robotic laser device, see reference. Figure 3 ,include:

[0240] This disclosure includes auxiliary devices according to any one embodiment;

[0241] Image acquisition device 130 is held directly above positioning device 120. The projection of the geometric center of image acquisition device 130 onto platform 111 coincides with the projection of the geometric center of positioning device 120 onto platform 111. Image acquisition device 130 is capable of acquiring image data of laser line segments or laser areas.

[0242] In some embodiments of this disclosure, the detection system 100 further includes:

[0243] The data processing device 150 is capable of acquiring laser point cloud data of laser line segments or laser regions collected by the robot to be inspected, and is also capable of acquiring image data of laser line segments or laser regions collected by the image acquisition device 130.

[0244] The data processing device 150 of the detection system 100 of this disclosure includes a memory and a processor. The memory stores, in the form of program instructions, a device 1000 for detecting the calibration quality of a robot laser device according to any embodiment of this disclosure.

[0245] This disclosure also provides an electronic device, including:

[0246] The memory stores the instructions to be executed.

[0247] The processor executes execution instructions stored in the memory, causing the processor to perform a method for detecting the calibration quality of a robotic laser device according to any embodiment of the present disclosure.

[0248] In the description of this specification, the references to terms such as "one embodiment / mode," "some embodiments / modes," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment / mode or example is included in at least one embodiment / mode or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment / mode or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments / modes or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments / modes or examples described in this specification, as well as the features of different embodiments / modes or examples.

[0249] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0250] Those skilled in the art should understand that the above embodiments are merely for illustrating the present disclosure and are not intended to limit the scope of the disclosure. Those skilled in the art can make other changes or modifications based on the above disclosure, and these changes or modifications still fall within the scope of the present disclosure.

Claims

1. A method for detecting the calibration quality of a robotic laser device, characterized in that, include: The robotic laser device emits a laser to illuminate at least the planar plate, forming a laser line segment. Acquire the laser point cloud data of the laser line segment, and acquire the image data of the laser line segment; Obtain the position information of the laser point cloud data in the laser device coordinate system, and obtain the position information of the image data in the robot coordinate system; Based on the external parameter calibration parameters of the laser device, the position information of the laser point cloud data in the laser device coordinate system is converted into the position information in the robot coordinate system to obtain the first spatial feature and the second spatial feature of the laser point cloud data. Based on the position information of the image data in the robot coordinate system, the first spatial feature and the second spatial feature of the image data are obtained; Obtain the first degree of matching between the first spatial feature of the laser point cloud data and the first spatial feature of the image data; obtain the second degree of matching between the second spatial feature of the laser point cloud data and the second spatial feature of the image data. as well as If the first matching degree meets the first preset condition and the second matching degree meets the second preset condition, then the external parameter calibration parameter is determined to be qualified. If the first matching degree does not meet the first preset condition or the second matching degree does not meet the second preset condition, then the external parameter calibration parameter is determined to be unqualified.

2. The method for detecting the calibration quality of a robotic laser device according to claim 1, characterized in that, The robotic laser device emits laser light to illuminate multiple planar plates to form at least two laser line segments, wherein at least two planar plates are not parallel and have a common edge.

3. The method for detecting the calibration quality of a robotic laser device according to claim 1, characterized in that, The robot's laser device emits laser light to illuminate three planar plates, forming three laser lines, with the three planar plates perpendicular to each other.

4. The method for detecting the calibration quality of a robotic laser device according to claim 1, characterized in that, Obtaining the position information of the laser point cloud data in the laser device coordinate system and the position information of the image data in the robot coordinate system includes: Acquire the position information of the two endpoints of the laser point cloud data of the laser line segment in the coordinate system of the laser device, as well as the position information of two or more intermediate points between the two endpoints; and Acquire the position information of the two endpoints of the laser line segment in the robot coordinate system, as well as the position information of two or more intermediate points between the two endpoints.

5. The method for detecting the calibration quality of a robotic laser device according to claim 4, characterized in that, The first spatial feature is the spatial feature of a line, and the second spatial feature is the spatial feature of a point.

6. The method for detecting the calibration quality of a robotic laser device according to claim 4, characterized in that, The number of midpoints of the laser line segment obtained based on laser point cloud data is the same as the number of midpoints of the laser line segment obtained based on image data.

7. The method for detecting the calibration quality of a robotic laser device according to claim 1, characterized in that, Obtaining a first degree of matching between the first spatial features of the laser point cloud data and the first spatial features of the image data, and obtaining a second degree of matching between the second spatial features of the laser point cloud data and the second spatial features of the image data, including: The first matching degree is obtained based on the deviation between the first spatial features of the laser point cloud data and the first spatial features of the image data; and The second matching degree is obtained based on the deviation between the second spatial features of the laser point cloud data and the second spatial features of the image data.

8. A method for detecting the calibration quality of a robotic laser device, characterized in that, include: The robotic laser device emits a laser to illuminate at least the flat plate, forming a laser area. Acquire laser point cloud data of the laser region and image data of the laser region; Obtain the position information of the laser point cloud data in the laser device coordinate system, and obtain the position information of the image data in the robot coordinate system; Based on the external parameter calibration parameters of the laser device, the position information of the laser point cloud data in the laser device coordinate system is converted into the position information in the robot coordinate system to obtain the first spatial feature and the second spatial feature of the laser point cloud data. Based on the position information of the image data in the robot coordinate system, the first spatial feature and the second spatial feature of the image data are obtained; Obtain the first degree of matching between the first spatial feature of the laser point cloud data and the first spatial feature of the image data; obtain the second degree of matching between the second spatial feature of the laser point cloud data and the second spatial feature of the image data. as well as If the first matching degree meets the first preset condition and the second matching degree meets the second preset condition, then the external parameter calibration parameter is determined to be qualified. If the first matching degree does not meet the first preset condition or the second matching degree does not meet the second preset condition, then the external parameter calibration parameter is determined to be unqualified.

9. The method for detecting the calibration quality of a robotic laser device according to claim 8, characterized in that, The robotic laser device emits laser light to illuminate multiple planar plates to form at least two laser regions, wherein at least two planar plates are not parallel and have a common edge.

10. The method for detecting the calibration quality of a robotic laser device according to claim 8, characterized in that, The robot's laser device emits laser light to illuminate three planar plates, forming three laser zones, wherein the three planar plates are perpendicular to each other.

11. The method for detecting the calibration quality of a robotic laser device according to claim 8, characterized in that, Obtaining the position information of the laser point cloud data in the laser device coordinate system and the position information of the image data in the robot coordinate system includes: Acquire the position information of the two endpoints of the arc-shaped line segment representing the edge contour of the laser point cloud data in the laser device coordinate system, as well as the position information of two or more intermediate points between the two endpoints; and Acquire the position information of the two endpoints of the arc-shaped edge contour line segment of the laser line segment in the robot coordinate system, as well as the position information of two or more intermediate points between the two endpoints.

12. The method for detecting the calibration quality of a robotic laser device according to claim 11, characterized in that, The first spatial feature is the spatial feature of a line, and the second spatial feature is the spatial feature of a point.

13. The method for detecting the calibration quality of a robotic laser device according to claim 11, characterized in that, The number of midpoints of the arc-shaped edge contour segment obtained based on laser point cloud data is the same as the number of midpoints of the arc-shaped edge contour segment obtained based on image data.

14. The method for detecting the calibration quality of a robotic laser device according to claim 8, characterized in that, Obtaining a first degree of matching between the first spatial features of the laser point cloud data and the first spatial features of the image data, and obtaining a second degree of matching between the second spatial features of the laser point cloud data and the second spatial features of the image data, including: The first matching degree is obtained based on the deviation between the first spatial features of the laser point cloud data and the first spatial features of the image data; and The second matching degree is obtained based on the deviation between the second spatial features of the laser point cloud data and the second spatial features of the image data.

15. A device for detecting the calibration quality of a robotic laser device, characterized in that, include: A laser point cloud data acquisition module acquires laser point cloud data of a laser line segment; An image data acquisition module acquires image data of the laser line segment; The first position information extraction module obtains the position information of the laser point cloud data in the coordinate system of the laser device. The second position information extraction module acquires the position information of the image data in the robot coordinate system. A laser point cloud data spatial feature acquisition module, which converts the position information of the laser point cloud data in the laser device coordinate system into the position information in the robot coordinate system based on the external parameter calibration parameters of the laser device, so as to obtain the first spatial feature and the second spatial feature of the laser point cloud data. An image data spatial feature acquisition module, wherein the image data spatial feature acquisition module acquires a first spatial feature and a second spatial feature of the image data based on the position information of the image data in the robot coordinate system; The matching degree acquisition module acquires the first matching degree between the first spatial feature of the laser point cloud data and the first spatial feature of the image data, and acquires the second matching degree between the second spatial feature of the laser point cloud data and the second spatial feature of the image data. as well as The judgment module makes a judgment based on the following judgment logic: if the first matching degree meets the first preset condition and the second matching degree meets the second preset condition, then the external parameter calibration parameter is determined to be qualified. If the first matching degree does not meet the first preset condition or the second matching degree does not meet the second preset condition, then the external parameter calibration parameter is determined to be unqualified. The laser line segment is formed by the laser emitted by the robot's laser device irradiating the flat plate.

16. A device for detecting the calibration quality of a robotic laser device, characterized in that, include: A laser point cloud data acquisition module acquires laser point cloud data of the laser region. An image data acquisition module acquires image data of the laser region; The first position information extraction module obtains the position information of the laser point cloud data in the coordinate system of the laser device. The second position information extraction module acquires the position information of the image data in the robot coordinate system. A laser point cloud data spatial feature acquisition module, which converts the position information of the laser point cloud data in the laser device coordinate system into the position information in the robot coordinate system based on the external parameter calibration parameters of the laser device, so as to obtain the first spatial feature and the second spatial feature of the laser point cloud data. An image data spatial feature acquisition module, wherein the image data spatial feature acquisition module acquires a first spatial feature and a second spatial feature of the image data based on the position information of the image data in the robot coordinate system; The matching degree acquisition module acquires the first matching degree between the first spatial feature of the laser point cloud data and the first spatial feature of the image data, and acquires the second matching degree between the second spatial feature of the laser point cloud data and the second spatial feature of the image data. as well as The judgment module makes a judgment based on the following judgment logic: if the first matching degree meets the first preset condition and the second matching degree meets the second preset condition, then the external parameter calibration parameter is determined to be qualified. If the first matching degree does not meet the first preset condition or the second matching degree does not meet the second preset condition, then the external parameter calibration parameter is determined to be unqualified. The laser region is the area formed by the laser emitted by the robot's laser device irradiating the flat plate.

17. A detection system for detecting the calibration quality of a robotic laser device, characterized in that, include: An auxiliary device includes: a support device; a platform disposed on or integrally formed with the support device; a positioning device disposed in a first area of ​​the platform for positioning a robot to be inspected; and a planar plate device disposed in a second area of ​​the platform for receiving laser emitted by the robot to be inspected, such that the laser emitted by the robot forms laser lines or laser areas on the planar plate device, and the robot to be inspected is able to collect laser point cloud data of the laser lines or laser areas. An image acquisition device is held directly above the positioning device, and the projection of the geometric center of the image acquisition device onto the platform coincides with the projection of the geometric center of the positioning device onto the platform. The image acquisition device is capable of acquiring image data of the laser line segment or the laser region. The data processing device is capable of acquiring laser point cloud data of laser line segments or laser regions collected by the robot to be detected, and is also capable of acquiring image data of laser line segments or laser regions collected by the image acquisition device. The data processing device includes a memory and a processor, wherein the memory stores the device of claim 15 or 16 in the form of program instructions.

18. The detection system according to claim 17, characterized in that, The second area of ​​the platform is provided with at least one positioning line area for positioning the planar plate device, wherein the positioning lines of the positioning line area are parallel to each other and are equally spaced.

19. The detection system according to claim 18, characterized in that, The positioning line is formed by a through-hole groove or a blind-hole groove.

20. The detection system according to claim 18, characterized in that, The second region of the platform is provided with two positioning line regions, and the two positioning line regions are symmetrically arranged about a symmetry axis, and the symmetry axis passes through the projection of the geometric center of the positioning device onto the first region.

21. The detection system according to claim 18, characterized in that, The positioning line area is a rectangular area.

22. The detection system according to claim 17, characterized in that, The positioning device includes a left and right positioning component and a front and back positioning component. The left and right positioning component is used to locate the left and right edges of the robot to be detected, and the front and back positioning component is used to locate the front and back edges of the robot to be detected.

23. The detection system according to claim 22, characterized in that, The left and right positioning components include a positioning groove disposed on the left edge of the positioning device and a positioning groove with an edge, and the front and rear positioning components include a positioning bracket disposed on the front edge of the positioning device and a positioning protrusion disposed on the rear edge.

24. The detection system according to claim 17, characterized in that, The planar plate device comprises at least two non-parallel planar plates that share a common edge.

25. The detection system according to claim 24, characterized in that, The planar plate device comprises three mutually perpendicular planar plates.

26. The detection system according to claim 24, characterized in that, The planar plate device has a first planar plate, a second planar plate, a fourth planar plate, and two third planar plates. The second and fourth planar plates are parallel to each other and both are perpendicular to the first planar plate. The two third planar plates are parallel to each other and both are perpendicular to the first planar plate. The surface of the first planar plate faces the positioning device.

27. An electronic device, characterized in that, include: The memory stores execution instructions; as well as A processor that executes execution instructions stored in the memory, causing the processor to perform the method of any one of claims 1 to 14.

Images