WO2018213980A1 - Robot calibration method, system, and calibration board - Google Patents

Robot calibration method, system, and calibration board Download PDF

Info

Publication number
WO2018213980A1
WO2018213980A1 PCT/CN2017/085331 CN2017085331W WO2018213980A1 WO 2018213980 A1 WO2018213980 A1 WO 2018213980A1 CN 2017085331 W CN2017085331 W CN 2017085331W WO 2018213980 A1 WO2018213980 A1 WO 2018213980A1
Authority
WO
WIPO (PCT)
Prior art keywords
robot
calibration
point
shape variable
calibration plate
Prior art date
Application number
PCT/CN2017/085331
Other languages
French (fr)
Chinese (zh)
Inventor
阳光
Original Assignee
深圳配天智能技术研究院有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳配天智能技术研究院有限公司 filed Critical 深圳配天智能技术研究院有限公司
Priority to CN201780034036.3A priority Critical patent/CN109311151B/en
Priority to PCT/CN2017/085331 priority patent/WO2018213980A1/en
Publication of WO2018213980A1 publication Critical patent/WO2018213980A1/en

Links

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B25HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25JMANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00Programme-controlled manipulators

Definitions

  • the invention relates to the technical field of robot coordinate setting, in particular to a calibration method, a system and a calibration plate of a robot.
  • robots have played an increasingly important role in production in manufacturing industries around the world.
  • robots In order to make industrial robots more capable of more complex work, robots not only need better control systems, but also need to be more aware of environmental changes.
  • robot vision has become the most important robot sensing device with its large amount of information and high information integrity.
  • the robot can perform precise welding of the electronic components of the circuit board.
  • the robot can position the workpiece or the working surface by using the camera in the vision system, and calculate the relative position of the working scene relative to the robot to assist the robot to complete the work.
  • the use of the vision system to calculate the conversion relationship between the visual coordinate system and the robot coordinate system has become an important research topic for the development of robots.
  • Obtaining the conversion relationship between the more accurate coordinate systems is the premise for solving the high-precision operation of the robot.
  • existing robots usually manually move the robot directly to the calibration point of the vision system to enable the robot to calculate the conversion relationship between the visual coordinate system and the robot coordinate system using the visual system, but the artificial comparison method cannot guarantee the two.
  • the calibration point of the comparison is the same point. In this way, there is usually a large human error, which leads to a large error in the obtained conversion relationship.
  • the object of the present invention is to provide a calibration method, a system and a calibration plate for a robot, which can improve the accuracy of the conversion relationship between the robot coordinate system and the visual coordinates.
  • the present invention provides a calibration method for a robot, including a calibration plate, the calibration plate includes a checkerboard, and an intersection of a vertical line and a horizontal line on the checkerboard is a corner point on the checkerboard.
  • the vertical line and the horizontal line are boundary lines of the grid, and the calibration method includes:
  • the position of the calibration point is determined according to the shape variable, and the calibration of the robot is completed.
  • the predetermined area is determined by at least four reference points, wherein determining the at least four reference points comprises:
  • At least one reference point is respectively determined in four directions of the boundary line to determine at least four reference points constituting the predetermined area.
  • the initial position point of the front end of the robot is taken as an origin, and at least one reference point is respectively determined in four directions of the boundary line to determine at least four reference points constituting the predetermined area, including:
  • the shape variable with the smallest value is extracted from the shape variable, and the position of the robot front end corresponding to the smallest shape variable is the reference point.
  • controlling the robot front end moves according to a preset rule in a predetermined area on the calibration plate provided with the flexible film, including:
  • the front end of the robot is controlled to move at its minimum moving distance until it is spread over the area.
  • determining the location of the calibration point according to the shape variable comprises:
  • the position of the calibration point is determined based on the shape variable having the smallest value.
  • determining the location of the calibration point according to the shape variable with the smallest value including:
  • the position point corresponding to the shape variable having the smallest value is used as the position of the calibration point.
  • the present invention provides a calibration system for a robot, the calibration system comprising: a calibration plate provided with a flexible film, and a visual device, a processor and a memory connected by a bus;
  • the memory is configured to store a preset movement rule of the robot and an execution instruction of the processor
  • the visual device is configured to detect the calibration plate
  • the processor is configured to perform the following actions:
  • the position of the calibration point is determined according to the shape variable, and the calibration of the robot is completed.
  • the predetermined area is determined by at least four reference points, wherein determining the at least four reference points comprises:
  • At least one reference point is respectively determined in four directions of the boundary line to determine at least four reference points constituting the predetermined area.
  • the initial position point of the front end of the robot is taken as an origin, and at least one reference point is respectively determined in four directions of the boundary line to determine at least four reference points constituting the predetermined area, including:
  • the shape variable with the smallest value is extracted from the shape variable, and the position of the robot front end corresponding to the smallest shape variable is the reference point.
  • the controlling the robot front end to move according to a preset rule in a predetermined area on the calibration plate provided with the flexible film including:
  • the front end of the robot is controlled to move at its minimum moving distance until it is spread over the area.
  • the determining, by the processor, the location of the calibration point according to the shape variable including:
  • the position of the calibration point is determined based on the shape variable having the smallest value.
  • the determining, by the processor, the location of the calibration point according to the shape variable with the smallest value including:
  • the position point corresponding to the shape variable having the smallest value is used as the position of the calibration point.
  • the invention provides a calibration plate, the calibration plate comprising:
  • a calibration plate is provided, and a flexible film is disposed on the calibration plate.
  • the calibration plate block is a checkerboard.
  • a plurality of identification points for positioning the front end contacts of the robot are arranged near the corners of the checkerboard.
  • the flexible film is a flexible film whose surface reflects infrared.
  • the present invention controls the front end of the robot to move according to a preset rule in a predetermined area of the calibration plate provided with the flexible film, the predetermined area including the corner point; during the moving process The predetermined area of the calibration plate is detected, and a shape variable of a boundary line caused by the front end of the robot is calculated for each movement; the position of the calibration point is determined according to the deformation variable, and the calibration of the robot is completed.
  • the position of the relatively accurate calibration point can be calculated, thereby improving the accuracy of the conversion relationship between the robot coordinate system and the visual coordinate.
  • FIG. 1 is a schematic flow chart of a first embodiment of a calibration method of a robot according to the present invention
  • FIG. 2 is a schematic flow chart of an embodiment of a method for determining a predetermined area in the first embodiment of the calibration method shown in FIG. 1;
  • 3a-3b are schematic views showing deformation of a flexible film on a calibration plate in the first embodiment of the calibration method shown in FIG. 1;
  • 4a-4c are schematic structural views of a first embodiment of a calibration method of a robot according to the present invention.
  • FIG. 5 is a schematic diagram of a trajectory of the movement of the front end of the robot in step S102 in the first embodiment of the calibration method shown in FIG. 1;
  • FIG. 5 is a schematic diagram of a trajectory of the movement of the front end of the robot in step S102 in the first embodiment of the calibration method shown in FIG. 1;
  • FIG. 6 is a schematic flowchart of step S103 in the first embodiment of the method shown in FIG. 1;
  • Figure 7 is a functional block diagram of a first embodiment of a calibration system for a robot of the present invention.
  • Figure 8 is a schematic structural view of an embodiment of a calibration plate of the present invention.
  • 9a-9b are schematic views showing the structure of another embodiment of the calibration plate of the present invention.
  • the unified robot coordinate system and the visual coordinate system are manually moved to move the front end of the robot to the corner point of the calibration plate under the vision system. Since the coordinates of the corner points of the calibration plate under the vision system are known, Assign the coordinates of the corner points of the calibration plate to the front end of the robot to complete the calibration of the robot.
  • the manipulator moves the front end of the robot to the corner of the calibration plate under the vision system. There is often a large error. It is difficult to judge whether the front end of the robot actually falls on the corner of the calibration plate by the naked eye, resulting in the calibration of the front end of the robot. The error is large.
  • the calibration plate is detected to determine the position of the front end of the robot closest to the corner of the calibration plate, thereby improving the accuracy of the calibration robot.
  • FIG. 1 is a schematic flowchart of a first embodiment of a calibration method for a robot according to the present invention. The method includes the following steps:
  • the calibration in this embodiment is a calibration plate provided with a flexible film, and the calibration plate is a checkerboard.
  • the boundary line of the lattice on the checkerboard is divided into a vertical line and a horizontal line, and the corner point of the checkerboard is the intersection of the vertical line and the horizontal line. .
  • the corner points on the calibration board are the intersections of the black and white grids on the checkerboard, and the intersection of the black and white grids is the boundary line. Since the flexible film is disposed on the calibration plate, when the front end of the robot contacts the calibration plate, a corresponding pressure is generated on the flexible film on the surface of the calibration plate, resulting in deformation of the flexible film.
  • the deformed flexible film magnifies the reflected image of the calibration plate directly below the front end of the robot. If the position of the front end of the robot in contact with the calibration plate is close to the boundary line, the deformation of the boundary line can be obtained from the reflected image of the acquired calibration plate by the deformation and amplification of the flexible film.
  • the checkerboard of the black and white grids is only in a specific real-time manner in the checkerboard of the present application.
  • the calibration board can have a checkerboard of vertical and horizontal lines, and the corner point is The intersection of the vertical line and the horizontal line on the checkerboard, wherein the vertical line and the horizontal line are the boundary lines of each grid on the checkerboard.
  • the checkerboard may also be a checkerboard of all black squares or both are white. The checkerboard, or any other checkerboard of any color.
  • the front end of the control robot is moved by its minimum moving distance until the predetermined area is traversed to determine the calibration point in the predetermined area.
  • the predetermined area is determined by at least four reference points. Therefore, in the embodiment, the at least four reference points need to be determined.
  • determining the predetermined area in step S101 includes the following steps:
  • S1011 The robot front end is moved in four directions extending along the boundary line with the initial position of the robot front end as the origin.
  • This position is the initial position of the front end of the robot.
  • the initial position of the front end of the robot on the calibration plate is taken as the origin, and the boundary line on the calibration plate is seen. A ray that extends in four different directions at the origin.
  • the front end of the robot is sequentially controlled to move in a direction in which one of the boundary lines extends. Since the obtained reference calibration point is used to finalize the calibration point, and the determined calibration point needs to be as close as possible to the corner point on the calibration plate, the front end of the robot is controlled when the front end of the control robot moves in the direction in which the boundary line extends. It is a direction extending along the boundary line and gradually moves on both sides of the boundary line. In order to improve the accuracy of the acquired reference calibration point, the front end of the robot is gradually moved on both sides of the boundary line with its minimum moving step.
  • s1 and s2 are black and white grids on the checkerboard, respectively, and the front end 11 of the robot contacts the calibration plate to generate pressure on the flexible film 10, causing the flexible film 10 to deform.
  • FIG. 3a if the position of the robot front end 10 on the calibration plate 12 is close to the boundary line between the black grid s1 and the white grid s2, the boundary image of the obtained calibration plate 12 is deformed, specifically In the reflected image of the calibration plate 12, it can be seen that the boundary line is convex toward the side of the position of the robot front end 11 on the calibration plate 12, and the apex of the protrusion corresponds to the position of the robot front end 11 on the calibration plate 12. .
  • the contact position of the robot front end 11 and the calibration plate 12 falls exactly above the boundary line, the deformation of the boundary line is not seen from the obtained reflection image of the calibration plate 12; The reflected image can obtain the contact position of the robot front end 11 with the calibration plate 12.
  • the front end of the robot since in the process of moving the front end of the robot, it is not known which movement causes the front end of the robot to be closest to the boundary line; then, in the direction extending along the boundary line, the front end of the robot is moved once for each time.
  • the reflected image of the calibration plate Through each acquired image of the calibration plate, the deformation of the boundary line in the reflection image of the calibration plate caused by the front end of the robot is obtained each time the front end of the robot is moved.
  • the shape variable of the boundary line is the degree of the protrusion. Further, since the vertex of the protrusion corresponds to the position of the front end of the robot on the calibration plate, the shape variable of the boundary line is the distance from the vertex of the protrusion to the original position of the boundary line. This distance is the distance from the position of the front end of the robot on the calibration plate to the boundary line.
  • the deformation of the boundary line of the calibration image of the calibration plate is caused by the front end of the robot pressing the flexible film, and the distance between the front end of the robot and the boundary line of the robot on the calibration plate is calculated. the distance.
  • the shape variable with the smallest value is extracted from the shape variable calculated in the reflection image of the calibration plate acquired by each mobile robot front end.
  • the position of the robot front end corresponding to the smallest value is closest to the boundary line on the calibration plate, and the position of the corresponding robot front end on the calibration plate is used as a reference point.
  • the shape variable is the distance from the vertex of the convex to the boundary line in the reflected image of the calibration plate
  • the smallest variable is the minimum of the distance from the vertex of the convex to the boundary line in the reflected image of the calibration plate. According to the above analysis, the shape variable with the smallest value corresponds to the position of the robot front end closest to the boundary line on the calibration plate, and the position is taken as a reference point determined in the direction.
  • Steps S1011 to S1014 are repeated in the remaining three directions in which the boundary line extends to complete at least four reference points in the four directions in which the boundary line extends, and at least four reference points can be determined according to the determined at least four reference points.
  • the predetermined area in this embodiment is determined.
  • step S1011 to step S1014 Since at least four reference points determined by step S1011 to step S1014 are both near the corner point and close to the boundary line, the range of the calibration point determined by the robot front end can be further narrowed by the four reference points near the corner point.
  • each reference point is connected with the closest reference point on both sides thereof to determine a predetermined area, it can be understood that the corner point of the calibration board is within the area.
  • step S1011 the front end of the robot is moved to a position near the corner point A, and the position is used as an initial position point of the robot front end, and the initial position point is used as an origin, and the front end of the control robot is started from the origin, along the boundary line a.
  • the direction of the extension moves in the vicinity of the boundary line a, and the reference point B is determined through steps S1012 to S1014; and the steps S1011 to S1014 are repeated in the direction in which the boundary lines b, c, and d extend, respectively, to determine the reference points C, D, respectively.
  • reference points B, C, D, E are sequentially connected to determine a predetermined area enclosed by the broken line in Fig. 4b, and the corner point A of the calibration plate is in the area.
  • the black grid portion is not filled in Fig. 4b, it being understood that the distribution of the black and white grids of Fig. 4b is the same as that of Fig. 4a.
  • S102 Detecting a predetermined area of the calibration plate during the movement, and calculating a shape variable of the boundary line caused by the front end of the robot for each movement.
  • the front end of the control robot In the predetermined area, the front end of the control robot is gradually moved. In order to make the finally obtained corrected calibration point as close as possible to the corner point of the calibration plate, the front end of the robot gradually moves with its minimum moving step, and gradually moves from one reference calibration point to another reference calibration point until the predetermined area is traversed. Full range. It can be understood that since the moving distance of the robot front end is its minimum moving step, the robot front end moves in a matrix from one reference calibration point to another reference calibration point in a predetermined area.
  • the front end of the robot moves from one reference calibration point to another reference point in a matrix in a predetermined area, specifically, at least four reference points determined in steps S1011 to S1014, with the robot front end
  • the minimum moving step setting matrix controls the front end of the robot to move from one point to another in the matrix.
  • the four reference points determined on the checkerboard are A, B, C, and D, respectively.
  • a 3 ⁇ 3 matrix (123, 456, 789) can be set according to the minimum moving step of the front end of the robot, and the front end of the control robot is gradually moved in numerical order in the matrix until all the steps are traversed. Step position.
  • the reflected image of the calibration plate is acquired once. Since the front end of the robot moves in the predetermined area, it is not known which movement causes the front end of the robot to be positioned closest to the corner of the calibration plate on the calibration plate. Then, each time the front end of the robot moves, the reflected image of the calibration plate is acquired once. Through each acquired image of the calibration plate, the deformation of the boundary line in the reflection image of the calibration plate caused by the front end of the robot is obtained each time the front end of the robot is moved.
  • the reflected image of the calibration plate obtained each time is analyzed, and the boundary line in the reflection image of the calibration plate caused by the flexible front film being pressed by the front end of the robot after each movement of the front end of the robot can be calculated.
  • Shape variable
  • the position of the corrected calibration point is finally determined by the calculated shape of the boundary line, and the corrected calibration point needs to be as close as possible to the corner of the calibration plate;
  • the shape variable of the boundary line calculated in this step may be more than a boundary line shape.
  • the shape variable of the boundary line is the same as the shape variable of the boundary line in steps S1011 to S1014, and both refer to the distance from the vertex of the protrusion in the reflected image to the original position of the boundary line.
  • the shape variable of the boundary line caused by the front end of the robot is the distance from the boundary line of the front end of the robot on the calibration plate after each movement of the robot.
  • the reflection image of the calibration plate is continuously acquired.
  • step S103 includes the following steps:
  • S1031 Extract a shape variable having the smallest value from the calculated shape variable of the boundary line corresponding to the front end of each mobile robot.
  • the detection result in this step is the shape variable of the boundary line in the reflection image of the calibration plate caused by the extrusion of the flexible film by the front end of the robot calculated in step S102, that is, the distance of the front end of the robot on the calibration plate after each movement of the robot The distance of the line.
  • the shape variable with the smallest value is extracted, that is, the distance from the vertex of the convex to the boundary line in the reflection image of the calibration plate is extracted from the calculated plurality of distances.
  • the minimum value in .
  • the minimum values of the distances from the vertices of the protrusions in the reflection image of the calibration plate to the adjacent two boundary lines are respectively extracted.
  • step S1031 According to the minimum value of the distance between the raised vertex and the adjacent two boundary lines in the reflected image of the calibration plate extracted in step S1031, it can be determined that in the process of moving the front end of the robot in the area determined by the reference calibration point, The position of the front end of the robot on the calibration plate closest to the corner of the calibration plate, which is the corrected punctuation point.
  • step S1031 and step S1032 the position of the corrected calibration point H is finally calculated near the corner point of the calibration plate.
  • the black grid portion is not filled in Fig. 4c, it being understood that the distribution of the black and white grids of Fig. 4c is the same as Fig. 4a.
  • the distance between the front end of the robot and the adjacent two boundary lines when the corner of the front end of the robot is closest to the calibration plate can be obtained. Since the coordinates of the corner point of the calibration plate in the visual coordinate system are known, the front end of the robot can be directly passed. The distance between the adjacent two boundary lines is used to obtain a conversion relationship between the robot coordinate system and the visual coordinate system.
  • FIG. 7 is a functional block diagram of an embodiment of a calibration system for a robot of the present invention.
  • the calibration system 200 of the robot includes a calibration plate 201 provided with a flexible film, and a visual device 202, a processor 203 and a memory 204 connected by a bus;
  • the memory 204 is used to store a preset movement rule of the robot and an execution instruction of the processor 203.
  • the calibration plate 201 is disposed within the line of sight of the vision device 202, and the vision device 204 is used to detect the calibration 201.
  • the processor 203 is configured to perform the following actions:
  • the calibration plate 201 is a checkerboard; the corner point is the intersection of the vertical line and the horizontal line on the checkerboard, wherein the vertical line and the horizontal line are the boundary lines of the grid on the checkerboard.
  • a checkerboard in which the black and white grids intersect can be selected as the calibration plate 201.
  • the predetermined area is determined by at least four reference points, wherein determining the at least four reference points comprises: determining, by using the initial position of the robot as an origin, determining at least one reference point in each of four directions of the boundary line to determine At least four reference points constituting a predetermined area.
  • determining at least four reference points is specifically: taking the initial position of the front end of the robot as an origin, controlling the front end of the robot to move in four directions extending along the boundary line respectively; acquiring a reflection image of the calibration plate for each movement; calculating according to the reflected image The shape variable of the boundary line caused by the front end of the robot is obtained for each movement; the shape variable with the smallest value is extracted from the shape variable, and the position of the robot front end corresponding to the smallest value variable is the reference point.
  • the processor 203 performs control on the calibration plate provided with the flexible film to move the front end of the robot according to a preset rule in a predetermined area, so that the robot front end gradually moves from the minimum moving distance by the controller 205 in the predetermined area.
  • One reference point is moved to another reference point until the predetermined area is traversed.
  • the processor 203 performs a detection on a predetermined area of the calibration plate during the movement, and calculates a shape variable of the boundary line caused by the front end of the robot for each movement, which specifically includes the following contents:
  • the reflected image of the calibration plate 201 is acquired by the visual device 202; the reflected image is analyzed, and the shape of the boundary line caused by the front end of the robot is calculated for each movement. variable.
  • the processor 203 determines, by the processor 203, the location of the calibration point according to the shape variable, specifically including the following content:
  • the content of the action performed by the processor 203 corresponds to the calibration method of the robot shown in FIG. 1 to FIG. 7 .
  • the content of the action performed by the processor 203 corresponds to the calibration method of the robot shown in FIG. 1 to FIG. 7 .
  • the detailed description of the method for calibrating the robot and details are not described herein again.
  • the present invention also proposes a calibration plate embodiment, as shown in FIG. 8, which is a schematic structural view of an embodiment of the calibration plate of the present invention.
  • the calibration plate 800 of the present embodiment includes a calibration plate block 81 on which a flexible film 82 is disposed.
  • the flexible film 82 deforms when it is squeezed.
  • the calibration plate block 81 is provided with a calibration object for calibration, such as a colored calibration ring, a calibration point, and the like.
  • the calibration plate 81 is a checkerboard
  • FIG. 9a is a top view of the calibration plate 800 in the present embodiment
  • FIG. 9b is a cross-sectional view along LL in FIG. 9a.
  • This embodiment uses a black and white grid.
  • the shaded portion in Figure 9a is a black grid
  • the left side of the black grid represents a white grid. It can be understood that there are several numbers of black and white grids on the checkerboard. Only a part of the black and white grids are shown in Fig. 9a, and the entire calibration board is not represented.
  • the checkerboard of the black and white grids is only in a specific real-time manner in the checkerboard of the present application.
  • the calibration board can have a checkerboard of vertical and horizontal lines, and the corner point is The intersection of the vertical line and the horizontal line on the checkerboard, wherein the vertical line and the horizontal line are the boundary lines of each grid on the checkerboard.
  • the checkerboard may also be a checkerboard of all black squares or both are white. The checkerboard, or any other checkerboard of any color.
  • a plurality of marker points 83 for positioning the front end contacts of the robot are disposed near the corners of the checkerboard.
  • the corner point of the checkerboard is the intersection of the black grid and the white grid.
  • a marker point 83 is provided near the intersection point, and the corner point can be easily found by the reflection image of the calibration plate 800 when the object is calibrated by the calibration plate 800.
  • the flexible film 82 disposed on the calibration plate 81 is a flexible film whose surface reflects infrared.
  • the calibration point 83 disposed on the calibration plate 81 may not be visible in the reflected image, and the infrared plate is used to illuminate the calibration plate by infrared light. Further, the calibration point 83 provided on the calibration plate 81 is observed in the reflected image of the calibration plate.

Abstract

A robot calibration method, system, and calibration board. The calibration method comprises: controlling, in a predetermined region of a calibration board (12) provided with a flexible film (10), a front robot end (11) to move according to a predetermined rule, the predetermined region containing corner points; measuring, during the moving process, the predetermined region of the calibration board, and calculating edge line deformation caused by the front robot end for each movement; and determining, according to the deformation, positions of calibration points to complete robot calibration. The method is employed to obtain relatively accurate positions of the calibration points, thus improving accuracy of a transform relationship between a robot coordinate system and a vision coordinate system.

Description

一种机器人的标定方法、系统及标定板 Calibration method, system and calibration board for robot
【技术领域】[Technical Field]
本发明涉及机器人坐标设定技术领域,尤其涉及一种机器人的标定方法、系统及标定板。The invention relates to the technical field of robot coordinate setting, in particular to a calibration method, a system and a calibration plate of a robot.
【背景技术】 【Background technique】
目前,在全世界的制造业中,工业机器人已经在生产中起到越来越重要的作用。为了使工业机器人能够胜任更复杂的工作,机器人不但要有更好的控制系统,还需要更多的感知环境变化。其中,机器人视觉以其信息量大、信息完整度高成为最重要的机器人感知装置。以用机器人进行电路板电子元件的精密焊接为例,焊接过程中,机器人可利用视觉系统中的摄像机对工件或工作面进行定位,计算工作场景相对于机器人的相对位置,以辅助机器人完成作业。At present, industrial robots have played an increasingly important role in production in manufacturing industries around the world. In order to make industrial robots more capable of more complex work, robots not only need better control systems, but also need to be more aware of environmental changes. Among them, robot vision has become the most important robot sensing device with its large amount of information and high information integrity. For example, in the welding process, the robot can perform precise welding of the electronic components of the circuit board. During the welding process, the robot can position the workpiece or the working surface by using the camera in the vision system, and calculate the relative position of the working scene relative to the robot to assist the robot to complete the work.
机器人利用视觉系统计算视觉坐标系与机器人坐标系之间的转换关系成为了机器人发展的重要研究课题,得到较精确的坐标系之间的转换关系是解决机器人完成高精度作业的前提。然而,现有的机器人通常是由人工将机器人直接移动至视觉系统的标定点以使机器人利用视觉系统计算视觉坐标系与机器人坐标系之间的转换关系,但人工的对照方法不能保证两者所对照的标定点为同一点,这种做法通常存在较大的人为误差,从而导致得到的转换关系的误差较大。The use of the vision system to calculate the conversion relationship between the visual coordinate system and the robot coordinate system has become an important research topic for the development of robots. Obtaining the conversion relationship between the more accurate coordinate systems is the premise for solving the high-precision operation of the robot. However, existing robots usually manually move the robot directly to the calibration point of the vision system to enable the robot to calculate the conversion relationship between the visual coordinate system and the robot coordinate system using the visual system, but the artificial comparison method cannot guarantee the two. The calibration point of the comparison is the same point. In this way, there is usually a large human error, which leads to a large error in the obtained conversion relationship.
【发明内容】 [Summary of the Invention]
本发明的目的在于提供一种机器人的标定方法、系统及标定板,能够提高机器人坐标系与视觉坐标之间的转换关系的精确度。The object of the present invention is to provide a calibration method, a system and a calibration plate for a robot, which can improve the accuracy of the conversion relationship between the robot coordinate system and the visual coordinates.
为实现上述目的,本发明提供一种机器人的标定方法,包括标定板,所述标定板包括棋盘格,所述棋盘格上的垂线和水平线的交点为所述棋盘格上的角点,所述垂线和所述水平线为格子的边界线,其特征在于,该标定方法包括:In order to achieve the above object, the present invention provides a calibration method for a robot, including a calibration plate, the calibration plate includes a checkerboard, and an intersection of a vertical line and a horizontal line on the checkerboard is a corner point on the checkerboard. The vertical line and the horizontal line are boundary lines of the grid, and the calibration method includes:
在设置有柔性膜的标定板的一预定区域内控制机器人前端按预设规则移动,所述预定区域包含所述角点;Controlling the front end of the robot to move according to a preset rule in a predetermined area of the calibration plate provided with the flexible film, the predetermined area including the corner point;
在移动过程中对所述标定板的所述预定区域进行检测,计算得到每次移动时,由所述机器人前端引起的边界线的形变量;Detecting the predetermined area of the calibration plate during the movement, and calculating a shape variable of the boundary line caused by the front end of the robot for each movement;
根据所述形变量确定标定点的位置,完成对机器人的标定。The position of the calibration point is determined according to the shape variable, and the calibration of the robot is completed.
其中,所述预定区域由至少四个参考点确定,其中,确定至少四个参考点包括:Wherein the predetermined area is determined by at least four reference points, wherein determining the at least four reference points comprises:
以所述机器人前端的初始位置点为原点,在所述边界线的四个方向上分别确定至少一个参考点,以确定构成所述预定区域的至少四个参考点。Taking an initial position point of the front end of the robot as an origin, at least one reference point is respectively determined in four directions of the boundary line to determine at least four reference points constituting the predetermined area.
其中,所述以所述机器人前端的初始位置点为原点,在所述边界线的四个方向上分别确定至少一个参考点,以确定构成所述预定区域的至少四个参考点,包括:Wherein, the initial position point of the front end of the robot is taken as an origin, and at least one reference point is respectively determined in four directions of the boundary line to determine at least four reference points constituting the predetermined area, including:
以所述机器人前端的初始位置点为原点,控制所述机器人前端分别沿所述边界线延伸的四个方向移动;Taking the initial position point of the front end of the robot as an origin, controlling the front ends of the robot to move in four directions extending along the boundary line respectively;
获取每次移动时所述标定板的反射图像;Obtaining a reflection image of the calibration plate each time it moves;
根据所述反射图像,计算得到每次移动时,由所述机器人前端引起的边界线的形变量;Calculating, according to the reflected image, a shape variable of a boundary line caused by the front end of the robot at each movement;
从所述形变量中提取数值最小的形变量,所述数值最小的形变量对应的机器人前端所在的位置即为参考点。The shape variable with the smallest value is extracted from the shape variable, and the position of the robot front end corresponding to the smallest shape variable is the reference point.
其中,所述在设置有柔性膜的标定板上一预定区域内控制机器人前端按预设规则移动,包括:Wherein, the controlling the robot front end moves according to a preset rule in a predetermined area on the calibration plate provided with the flexible film, including:
在所述预定区域内,控制所述机器人前端按其最小移动距离移动,直至遍布所述区域。Within the predetermined area, the front end of the robot is controlled to move at its minimum moving distance until it is spread over the area.
其中,所述根据所述形变量确定标定点的位置,包括:Wherein, determining the location of the calibration point according to the shape variable comprises:
从计算得到的每次移动机器人前端对应的边界线的形变量中,提取数值最小的形变量;Extracting the shape variable with the smallest value from the calculated shape variable of the boundary line corresponding to the front end of each mobile robot;
根据所述数值最小的形变量,确定所述标定点的位置。The position of the calibration point is determined based on the shape variable having the smallest value.
其中,所述根据所述数值最小的形变量,确定所述标定点的位置,包括:Wherein, determining the location of the calibration point according to the shape variable with the smallest value, including:
以所述数值最小的形变量对应的位置点作为所述标定点的位置。The position point corresponding to the shape variable having the smallest value is used as the position of the calibration point.
另一方面,本发明提出了一种机器人的标定系统,该标定系统包括:设置有柔性膜的标定板,以及通过总线连接的视觉装置、处理器和存储器;In another aspect, the present invention provides a calibration system for a robot, the calibration system comprising: a calibration plate provided with a flexible film, and a visual device, a processor and a memory connected by a bus;
所述存储器,用于存储机器人的预设移动规则以及所述处理器的执行指令;The memory is configured to store a preset movement rule of the robot and an execution instruction of the processor;
所述视觉装置,用于对所述标定板进行检测;The visual device is configured to detect the calibration plate;
所述处理器用于执行下述动作:The processor is configured to perform the following actions:
在设置有柔性膜的标定板的一预定区域内控制机器人前端按预设规则移动,所述预定区域包含所述角点;Controlling the front end of the robot to move according to a preset rule in a predetermined area of the calibration plate provided with the flexible film, the predetermined area including the corner point;
在移动过程中对所述标定板的所述预定区域进行检测,计算得到每次移动时,由所述机器人前端引起的边界线的形变量;Detecting the predetermined area of the calibration plate during the movement, and calculating a shape variable of the boundary line caused by the front end of the robot for each movement;
根据所述形变量确定标定点的位置,完成对机器人的标定。The position of the calibration point is determined according to the shape variable, and the calibration of the robot is completed.
其中,所述预定区域由至少四个参考点确定,其中,确定至少四个参考点包括:Wherein the predetermined area is determined by at least four reference points, wherein determining the at least four reference points comprises:
以所述机器人前端的初始位置点为原点,在所述边界线的四个方向上分别确定至少一个参考点,以确定构成所述预定区域的至少四个参考点。Taking an initial position point of the front end of the robot as an origin, at least one reference point is respectively determined in four directions of the boundary line to determine at least four reference points constituting the predetermined area.
其中,所述以所述机器人前端的初始位置点为原点,在所述边界线的四个方向上分别确定至少一个参考点,以确定构成所述预定区域的至少四个参考点,包括:Wherein, the initial position point of the front end of the robot is taken as an origin, and at least one reference point is respectively determined in four directions of the boundary line to determine at least four reference points constituting the predetermined area, including:
以所述机器人前端的初始位置点为原点,控制所述机器人前端分别沿所述边界线延伸的四个方向移动;Taking the initial position point of the front end of the robot as an origin, controlling the front ends of the robot to move in four directions extending along the boundary line respectively;
获取每次移动时所述标定板的反射图像;Obtaining a reflection image of the calibration plate each time it moves;
根据所述反射图像,计算得到每次移动时,由所述机器人前端引起的边界线的形变量;Calculating, according to the reflected image, a shape variable of a boundary line caused by the front end of the robot at each movement;
从所述形变量中提取数值最小的形变量,所述数值最小的形变量对应的机器人前端所在的位置即为参考点。The shape variable with the smallest value is extracted from the shape variable, and the position of the robot front end corresponding to the smallest shape variable is the reference point.
其中,所述处理器执行的在设置有柔性膜的标定板上一预定区域内控制机器人前端按预设规则移动,包括:The controlling the robot front end to move according to a preset rule in a predetermined area on the calibration plate provided with the flexible film, including:
在所述预定区域内,控制所述机器人前端按其最小移动距离移动,直至遍布所述区域。Within the predetermined area, the front end of the robot is controlled to move at its minimum moving distance until it is spread over the area.
其中,所述处理器执行的所述根据所述形变量确定标定点的位置,包括:The determining, by the processor, the location of the calibration point according to the shape variable, including:
从计算得到的每次移动机器人前端对应的边界线的形变量中,提取数值最小的形变量;Extracting the shape variable with the smallest value from the calculated shape variable of the boundary line corresponding to the front end of each mobile robot;
根据所述数值最小的形变量,确定所述标定点的位置。The position of the calibration point is determined based on the shape variable having the smallest value.
其中,所述处理器执行的所述根据所述数值最小的形变量,确定所述标定点的位置,包括:The determining, by the processor, the location of the calibration point according to the shape variable with the smallest value, including:
以所述数值最小的形变量对应的位置点作为所述标定点的位置。The position point corresponding to the shape variable having the smallest value is used as the position of the calibration point.
另一方面,本发明提出了一种标定板,该标定板包括:In another aspect, the invention provides a calibration plate, the calibration plate comprising:
标定板板块,所述标定板板块上设置有柔性膜。A calibration plate is provided, and a flexible film is disposed on the calibration plate.
其中,所述标定板板块为棋盘格。Wherein, the calibration plate block is a checkerboard.
其中,所述棋盘格的角点附近设置有多个用于对机器人前端触点进行定位的标识点。Wherein, a plurality of identification points for positioning the front end contacts of the robot are arranged near the corners of the checkerboard.
其中,所述柔性膜为表面反射红外的柔性膜。Wherein, the flexible film is a flexible film whose surface reflects infrared.
有益效果:区别于现有技术的情况,本发明通过在设置有柔性膜的标定板的一预定区域内控制机器人前端按预设规则移动,所述预定区域包含所述角点;在移动过程中对所述标定板的所述预定区域进行检测,计算得到每次移动时,由所述机器人前端引起的边界线的形变量;根据所述形变量确定标定点的位置,完成对机器人的标定。通过上述方法,能够计算得到相对精确的标定点的位置,进而提高机器人坐标系与视觉坐标之间的转换关系的精确度。Advantageous Effects: Different from the prior art, the present invention controls the front end of the robot to move according to a preset rule in a predetermined area of the calibration plate provided with the flexible film, the predetermined area including the corner point; during the moving process The predetermined area of the calibration plate is detected, and a shape variable of a boundary line caused by the front end of the robot is calculated for each movement; the position of the calibration point is determined according to the deformation variable, and the calibration of the robot is completed. Through the above method, the position of the relatively accurate calibration point can be calculated, thereby improving the accuracy of the conversion relationship between the robot coordinate system and the visual coordinate.
【附图说明】 [Description of the Drawings]
图1是本发明机器人的标定方法第一实施例的流程示意图;1 is a schematic flow chart of a first embodiment of a calibration method of a robot according to the present invention;
图2是图1所示的标定方法第一实施例中预定区域的确定方法一实施例的流程示意图; 2 is a schematic flow chart of an embodiment of a method for determining a predetermined area in the first embodiment of the calibration method shown in FIG. 1;
图3a-3b是图1所示的标定方法第一实施例中标定板上柔性膜形变的示意图;3a-3b are schematic views showing deformation of a flexible film on a calibration plate in the first embodiment of the calibration method shown in FIG. 1;
图4a-4c是本发明机器人的标定方法第一实施例的结构示意图;4a-4c are schematic structural views of a first embodiment of a calibration method of a robot according to the present invention;
图5是图1所示的标定方法第一实施例中步骤S102的机器人前端移动的轨迹示意图;FIG. 5 is a schematic diagram of a trajectory of the movement of the front end of the robot in step S102 in the first embodiment of the calibration method shown in FIG. 1; FIG.
图6是图1所示的方法第一实施例中的步骤S103的流程示意图;FIG. 6 is a schematic flowchart of step S103 in the first embodiment of the method shown in FIG. 1;
图7是本发明机器人的标定系统第一实施例的功能模块图;Figure 7 is a functional block diagram of a first embodiment of a calibration system for a robot of the present invention;
图8是本发明标定板一实施例的结构示意图;Figure 8 is a schematic structural view of an embodiment of a calibration plate of the present invention;
图9a-9b是本发明标定板另一实施例的结构示意图。9a-9b are schematic views showing the structure of another embodiment of the calibration plate of the present invention.
【具体实施方式】【detailed description】
为使本领域的技术人员更好地理解本发明的技术方案,下面结合附图和具体实施方式对本发明所提供的一种机器人的标定方法、系统及标定板做进一步详细描述。显然,所描述的实施方式仅仅是本发明一种机器人的标定方法、系统及标定板的一部分实施方式,而不是全部的实施方式。基于本发明中的实施方式,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施方式,均属于本发明保护的范围。In order to enable a person skilled in the art to better understand the technical solutions of the present invention, a calibration method, a system and a calibration plate of a robot provided by the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiment is only a part of the calibration method, system and calibration plate of the robot of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.
现有技术中,统一机器人坐标系和视觉坐标系是通过人为操作将机器人前端移动至视觉系统下标定板的角点处,由于视觉系统下标定板的角点的坐标是已知的,则直接将标定板的角点的坐标赋值给机器人前端,以完成机器人的标定。但实际操作中,人为操作将机器人前端移动至视觉系统下标定板的角点处往往存在很大误差,通过肉眼很难判断是否机器人前端真正落在标定板的角点上,导致标定机器人前端的误差较大。而本发明则通过对标定板进行检测,确定机器人前端在最靠近标定板的角点时的位置,进而提升标定机器人的精确度。In the prior art, the unified robot coordinate system and the visual coordinate system are manually moved to move the front end of the robot to the corner point of the calibration plate under the vision system. Since the coordinates of the corner points of the calibration plate under the vision system are known, Assign the coordinates of the corner points of the calibration plate to the front end of the robot to complete the calibration of the robot. However, in practice, the manipulator moves the front end of the robot to the corner of the calibration plate under the vision system. There is often a large error. It is difficult to judge whether the front end of the robot actually falls on the corner of the calibration plate by the naked eye, resulting in the calibration of the front end of the robot. The error is large. In the present invention, the calibration plate is detected to determine the position of the front end of the robot closest to the corner of the calibration plate, thereby improving the accuracy of the calibration robot.
参阅图1,图1是本发明机器人的标定方法第一实施例的流程示意图,该方法包括如下步骤:Referring to FIG. 1 , FIG. 1 is a schematic flowchart of a first embodiment of a calibration method for a robot according to the present invention. The method includes the following steps:
S101、在设置有柔性膜的标定板的一预定区域内控制机器人前端按预设规则移动。S101. Control the front end of the robot to move according to a preset rule in a predetermined area of the calibration plate provided with the flexible film.
本实施例中的标定为设置有柔性膜的标定板,且标定板为棋盘格,棋盘格上的格子的边界线分为垂线和水平线,棋盘格的角点即为垂线和水平线的交点。以黑格和白格交错设置的棋盘格为例,标定板上的角点即为棋盘格上黑格和白格的交点,黑格和白格的交线则为边界线。由于标定板上设置有柔性膜,当机器人前端接触标定板时,会对标定板表面的柔性膜产生相应的压力,导致柔性膜发生形变。形变的柔性膜会对机器人前端正下方的标定板的反射图像起到放大作用。若机器人前端与标定板的接触的位置靠近边界线,通过柔性膜的形变和放大作用,可以从获取的标定板的反射图像中获取边界线的形变。The calibration in this embodiment is a calibration plate provided with a flexible film, and the calibration plate is a checkerboard. The boundary line of the lattice on the checkerboard is divided into a vertical line and a horizontal line, and the corner point of the checkerboard is the intersection of the vertical line and the horizontal line. . Taking the checkerboard of the black and white grids as an example, the corner points on the calibration board are the intersections of the black and white grids on the checkerboard, and the intersection of the black and white grids is the boundary line. Since the flexible film is disposed on the calibration plate, when the front end of the robot contacts the calibration plate, a corresponding pressure is generated on the flexible film on the surface of the calibration plate, resulting in deformation of the flexible film. The deformed flexible film magnifies the reflected image of the calibration plate directly below the front end of the robot. If the position of the front end of the robot in contact with the calibration plate is close to the boundary line, the deformation of the boundary line can be obtained from the reflected image of the acquired calibration plate by the deformation and amplification of the flexible film.
可以理解的是,黑格和白格交错的棋盘格仅是本申请中棋盘格的以具体实时方式,在其他实施例中,标定板可以具有垂线和水平线的棋盘格即可,角点即为棋盘格上垂线和水平线的交点,其中,垂线和水平线为棋盘格上每个格子的边界线,在其他实施例中,棋盘格也可以是均为黑格的棋盘格或均为白色的棋盘格,或其他任意颜色的棋盘格。It can be understood that the checkerboard of the black and white grids is only in a specific real-time manner in the checkerboard of the present application. In other embodiments, the calibration board can have a checkerboard of vertical and horizontal lines, and the corner point is The intersection of the vertical line and the horizontal line on the checkerboard, wherein the vertical line and the horizontal line are the boundary lines of each grid on the checkerboard. In other embodiments, the checkerboard may also be a checkerboard of all black squares or both are white. The checkerboard, or any other checkerboard of any color.
在预定区域内,控制机器人前端按其最小移动距离移动,直至遍历该预定区域,以在预定区域中确定出标定点。In the predetermined area, the front end of the control robot is moved by its minimum moving distance until the predetermined area is traversed to determine the calibration point in the predetermined area.
本实施例中,该预定区域由至少四个参考点确定。因此,本实施例中需要确定该至少四个参考点。In this embodiment, the predetermined area is determined by at least four reference points. Therefore, in the embodiment, the at least four reference points need to be determined.
进一步的,如图2所示,步骤S101中确定预定区域包括如下步骤:Further, as shown in FIG. 2, determining the predetermined area in step S101 includes the following steps:
S1011、以机器人前端初始位置点为原点,控制机器人前端分别沿边界线延伸的四个方向移动。S1011: The robot front end is moved in four directions extending along the boundary line with the initial position of the robot front end as the origin.
将机器人前端移动到靠近标定板的角点的某一位置处,以该位置为机器人前端的初始位置点,以机器人前端在标定板上的初始位置点作为原点,将标定板上的边界线看为以该原点向四个不同方向延伸的射线。Move the front end of the robot to a position near the corner of the calibration plate. This position is the initial position of the front end of the robot. The initial position of the front end of the robot on the calibration plate is taken as the origin, and the boundary line on the calibration plate is seen. A ray that extends in four different directions at the origin.
依次控制机器人前端沿着其中一条边界线延伸的方向移动。由于获取的参考标定点是用来最终确定标定点的,而确定的标定点需要尽可能的与标定板上的角点靠近,则控制机器人前端沿着该边界线延伸的方向移动时,机器人前端是沿着该边界线延伸的方向,在边界线的两侧逐步移动的。为了提高获取的参考标定点的精度,此时机器人前端以其最小移动步径在在边界线的两侧逐步移动。The front end of the robot is sequentially controlled to move in a direction in which one of the boundary lines extends. Since the obtained reference calibration point is used to finalize the calibration point, and the determined calibration point needs to be as close as possible to the corner point on the calibration plate, the front end of the robot is controlled when the front end of the control robot moves in the direction in which the boundary line extends. It is a direction extending along the boundary line and gradually moves on both sides of the boundary line. In order to improve the accuracy of the acquired reference calibration point, the front end of the robot is gradually moved on both sides of the boundary line with its minimum moving step.
S1012、获取每次移动时标定板的反射图像。S1012: Obtain a reflection image of the calibration plate at each movement.
如图3a和图3b所示,s1和s2分别为棋盘格上的黑格和白格,机器人前端11接触标定板时对柔性膜10会产生压力,导致柔性膜10发生形变。如图3a所示,若机器人前端10在标定板12上的位置靠近黑格s1和白格s2之间的边界线,则可以获得的标定板12的反射图像中看到边界线发生形变,具体的,能够在标定板12的反射图像中看到边界线朝向机器人前端11在标定板12上的位置的一侧凸起,该凸起的顶点则对应了机器人前端11在标定板12上的位置。如图3b所示,若机器人前端11与标定板12的接触位置正好落在边界线上方,则从获得的标定板12的反射图像中看不到边界线的形变;则通过获取标定板12的反射图像能够得到机器人前端11与标定板12的接触位置。As shown in FIGS. 3a and 3b, s1 and s2 are black and white grids on the checkerboard, respectively, and the front end 11 of the robot contacts the calibration plate to generate pressure on the flexible film 10, causing the flexible film 10 to deform. As shown in FIG. 3a, if the position of the robot front end 10 on the calibration plate 12 is close to the boundary line between the black grid s1 and the white grid s2, the boundary image of the obtained calibration plate 12 is deformed, specifically In the reflected image of the calibration plate 12, it can be seen that the boundary line is convex toward the side of the position of the robot front end 11 on the calibration plate 12, and the apex of the protrusion corresponds to the position of the robot front end 11 on the calibration plate 12. . As shown in FIG. 3b, if the contact position of the robot front end 11 and the calibration plate 12 falls exactly above the boundary line, the deformation of the boundary line is not seen from the obtained reflection image of the calibration plate 12; The reflected image can obtain the contact position of the robot front end 11 with the calibration plate 12.
本实施例中,由于在移动机器人前端的过程中,并不知道哪一次移动会使机器人前端最靠近边界线;则在沿着该边界线延伸的方向上,每移动一次机器人前端,相应获取一次标定板的反射图像。通过每次获取到的标定板的反射图像,以获得每次移动机器人前端后,机器人前端造成的标定板反射图像中边界线的形变情况。In this embodiment, since in the process of moving the front end of the robot, it is not known which movement causes the front end of the robot to be closest to the boundary line; then, in the direction extending along the boundary line, the front end of the robot is moved once for each time. The reflected image of the calibration plate. Through each acquired image of the calibration plate, the deformation of the boundary line in the reflection image of the calibration plate caused by the front end of the robot is obtained each time the front end of the robot is moved.
S1013、根据获取到的反射图像,计算得到每次移动时,由机器人前端引起的边界线的形变量。S1013. Calculate, according to the acquired reflection image, a shape variable of a boundary line caused by the front end of the robot when moving.
对每次获取的标定板的反射图像进行分析,可以计算得到每次移动机器人前端后,由机器人前端挤压柔性膜导致标定板的反射图像中边界线的形变量。By analyzing the reflection image of each acquired calibration plate, it can be calculated that the deformation of the boundary line in the reflection image of the calibration plate is caused by the front end of the robot pressing the flexible film each time the front end of the robot is moved.
由于边界线的形变为边界线朝向机器人前端在标定板上的位置的一侧凸起,则边界线的形变量即为该凸起的程度。进一步,由于该凸起的顶点则对应了机器人前端在标定板上的位置,则边界线的形变量为该凸起的顶点到边界线原来位置的距离。该距离即为机器人前端在标定板上的位置到边界线的距离。则计算得到每次移动机器人前端后,由机器人前端挤压柔性膜导致标定板的反射图像中边界线的形变量即为,计算得到每次移动机器人前端后,机器人前端在标定板上距离边界线的距离。Since the shape of the boundary line becomes a boundary line which is convex toward one side of the position of the robot front end on the index plate, the shape variable of the boundary line is the degree of the protrusion. Further, since the vertex of the protrusion corresponds to the position of the front end of the robot on the calibration plate, the shape variable of the boundary line is the distance from the vertex of the protrusion to the original position of the boundary line. This distance is the distance from the position of the front end of the robot on the calibration plate to the boundary line. Then, after each movement of the front end of the robot, the deformation of the boundary line of the calibration image of the calibration plate is caused by the front end of the robot pressing the flexible film, and the distance between the front end of the robot and the boundary line of the robot on the calibration plate is calculated. the distance.
S1014、从形变量中提取数值最小的形变量,数值最小的形变量对应的机器人前端所在的位置即为参考点。S1014, extracting the smallest shape variable from the shape variable, and the position of the robot front end corresponding to the smallest value variable is the reference point.
从每次移动机器人前端获取的标定板的反射图像中计算得到的形变量中,提取数值最小的形变量。该数值最小的形变量对应的机器人前端在标定板上的位置最靠近该边界线,则将相应的机器人前端在标定板上的位置作为参考点。The shape variable with the smallest value is extracted from the shape variable calculated in the reflection image of the calibration plate acquired by each mobile robot front end. The position of the robot front end corresponding to the smallest value is closest to the boundary line on the calibration plate, and the position of the corresponding robot front end on the calibration plate is used as a reference point.
由于形变量为标定板的反射图像中凸起的顶点到边界线的距离,则数值最小的形变量即为标定板的反射图像中凸起的顶点到边界线的距离中的最小值。根据上述分析可知,数值最小的形变量对应机器人前端在标定板上的离边界线最近的位置,将该位置作为在该方向上确定的一个参考点。Since the shape variable is the distance from the vertex of the convex to the boundary line in the reflected image of the calibration plate, the smallest variable is the minimum of the distance from the vertex of the convex to the boundary line in the reflected image of the calibration plate. According to the above analysis, the shape variable with the smallest value corresponds to the position of the robot front end closest to the boundary line on the calibration plate, and the position is taken as a reference point determined in the direction.
在边界线延伸的其余三个方向上重复步骤S1011至步骤S1014,以完成在边界线延伸的四个方向上,在边界线附近确定至少四个参考点,根据确定的至少四个参考点既能够确定出本实施例中的预定区域。Steps S1011 to S1014 are repeated in the remaining three directions in which the boundary line extends to complete at least four reference points in the four directions in which the boundary line extends, and at least four reference points can be determined according to the determined at least four reference points. The predetermined area in this embodiment is determined.
由于通过步骤S1011至步骤S1014确定的至少四个参考点均在角点附近,且靠近边界线,则通过个四个参考点能够在角点附近将通过机器人前端确定的标定点的范围进一步缩小。Since at least four reference points determined by step S1011 to step S1014 are both near the corner point and close to the boundary line, the range of the calibration point determined by the robot front end can be further narrowed by the four reference points near the corner point.
具体的,通过将步骤S1011至步骤S1014确定的至少四个参考点中,每个参考点均与其两边最近的参考点连接,以确定出预定区域,可以理解的是,标定板的角点在该区域内。Specifically, by selecting at least four reference points determined by step S1011 to step S1014, each reference point is connected with the closest reference point on both sides thereof to determine a predetermined area, it can be understood that the corner point of the calibration board is within the area.
对参考点的确定进行举例:如图4a所示,标定板为黑格和白格相间设置的棋盘格,其角点A为黑格和白格的交点,其四条边界线a、b、c和d分别以角点A向的四个方向延伸。首先,通过步骤S1011,将机器人前端移动到靠近角点A附近的位置,以该位置作为机器人前端的初始位置点,将该初始位置点作为原点,控制机器人前端从原点出发,沿着边界线a延伸的方向,在边界线a附近移动,通过步骤S1012至步骤S1014以确定参考点B;再依次沿边界线b、c和d延伸的方向,重复步骤S1011至步骤S1014,分别确定参考点C、D和E,再将参考点B、C、D、E依次连接,以确定图4b中虚线所围成的预定区域,标定板的角点A在该区域内。为了方便将标示出参考标定点和由参考标定点确定的区域,图4b中对黑格部分未做填充,可以理解的是,图4b的黑格和白格的分布与图4a相同。The determination of the reference point is exemplified: as shown in FIG. 4a, the calibration plate is a checkerboard set between the black and white grids, and the corner point A is the intersection of the black grid and the white grid, and the four boundary lines a, b, c and d extends in four directions of the corner A direction, respectively. First, in step S1011, the front end of the robot is moved to a position near the corner point A, and the position is used as an initial position point of the robot front end, and the initial position point is used as an origin, and the front end of the control robot is started from the origin, along the boundary line a. The direction of the extension moves in the vicinity of the boundary line a, and the reference point B is determined through steps S1012 to S1014; and the steps S1011 to S1014 are repeated in the direction in which the boundary lines b, c, and d extend, respectively, to determine the reference points C, D, respectively. And E, and then reference points B, C, D, E are sequentially connected to determine a predetermined area enclosed by the broken line in Fig. 4b, and the corner point A of the calibration plate is in the area. In order to facilitate the marking of the reference calibration point and the area determined by the reference calibration point, the black grid portion is not filled in Fig. 4b, it being understood that the distribution of the black and white grids of Fig. 4b is the same as that of Fig. 4a.
S102、在移动过程中对标定板的预定区域进行检测,计算得到每次移动时,由机器人前端引起的边界线的形变量。S102: Detecting a predetermined area of the calibration plate during the movement, and calculating a shape variable of the boundary line caused by the front end of the robot for each movement.
在预定区域内,控制机器人前端逐步运动。为了使最终得到的经校正的标定点尽可能靠近标定板的角点,则机器人前端以其最小移动步径逐步移动,逐渐从一个参考标定点移动至另一个参考标定点,直至遍历预定区域的全部范围。可以理解的是,由于机器人前端每次的移动距离都是其最小移动步径,则机器人前端在预定区域内是以矩阵形式从一个参考标定点移动至另一个参考标定点的。In the predetermined area, the front end of the control robot is gradually moved. In order to make the finally obtained corrected calibration point as close as possible to the corner point of the calibration plate, the front end of the robot gradually moves with its minimum moving step, and gradually moves from one reference calibration point to another reference calibration point until the predetermined area is traversed. Full range. It can be understood that since the moving distance of the robot front end is its minimum moving step, the robot front end moves in a matrix from one reference calibration point to another reference calibration point in a predetermined area.
在本实施例中,机器人前端在预定区域内是以矩阵形式从一个参考标定点移动至另一个参考标定点具体为,在步骤S1011至步骤S1014中确定的至少四个参考点内,以机器人前端的最小移动步径设置矩阵,控制机器人前端从矩阵中的一个点移动到另一个点,如图5所示,在棋盘格上确定的四个参考点分别为A、B、C和D,在由A、B、C和D构成的预定区域内,按机器人前端的最小移动步径可以设置一个3×3的矩阵(123,456,789),则控制机器人前端按矩阵中数字顺序逐步移动,直至遍历所有的步径位置。In this embodiment, the front end of the robot moves from one reference calibration point to another reference point in a matrix in a predetermined area, specifically, at least four reference points determined in steps S1011 to S1014, with the robot front end The minimum moving step setting matrix controls the front end of the robot to move from one point to another in the matrix. As shown in Figure 5, the four reference points determined on the checkerboard are A, B, C, and D, respectively. In a predetermined area composed of A, B, C, and D, a 3×3 matrix (123, 456, 789) can be set according to the minimum moving step of the front end of the robot, and the front end of the control robot is gradually moved in numerical order in the matrix until all the steps are traversed. Step position.
进一步的,在预定区域内机器人前端每移动一次,均获取一次标定板的反射图像。由于在预定区域内机器人前端移动时,并不知道哪一次移动会使机器人前端在标定板上的位置最靠近标定板的角点。则机器人前端每移动一次,相应获取一次标定板的反射图像。通过每次获取到的标定板的反射图像,以获得每次移动机器人前端后,机器人前端造成的标定板反射图像中边界线的形变情况。Further, each time the robot front end moves once in the predetermined area, the reflected image of the calibration plate is acquired once. Since the front end of the robot moves in the predetermined area, it is not known which movement causes the front end of the robot to be positioned closest to the corner of the calibration plate on the calibration plate. Then, each time the front end of the robot moves, the reflected image of the calibration plate is acquired once. Through each acquired image of the calibration plate, the deformation of the boundary line in the reflection image of the calibration plate caused by the front end of the robot is obtained each time the front end of the robot is moved.
进一步,根据获取到的反射图像,对每次获取的标定板的反射图像进行分析,则能够计算得到每次移动机器人前端后,由机器人前端挤压柔性膜导致的标定板的反射图像中边界线的形变量。Further, according to the acquired reflected image, the reflected image of the calibration plate obtained each time is analyzed, and the boundary line in the reflection image of the calibration plate caused by the flexible front film being pressed by the front end of the robot after each movement of the front end of the robot can be calculated. Shape variable.
值得注意的是,由于此时需要通过计算得到的边界线的形变量来最终确定经校正的标定点的位置,而经校正的标定点需要尽可能的靠近标定板的角点;当机器人前端靠近标定板的角点时,在标定板的反射图像中,可能同时出现相邻两条边界线均出现形变的情况,因此本步骤中计算的边界线的形变量可以不仅仅是一条边界线的形变量,而是相邻两条边界线的形变量。It is worth noting that the position of the corrected calibration point is finally determined by the calculated shape of the boundary line, and the corrected calibration point needs to be as close as possible to the corner of the calibration plate; When the corner points of the plate are calibrated, in the reflection image of the calibration plate, the deformation of the adjacent two boundary lines may occur at the same time. Therefore, the shape variable of the boundary line calculated in this step may be more than a boundary line shape. A variable, but a shape variable of two adjacent boundary lines.
此处,边界线的形变量与步骤S1011至步骤S1014中的边界线的形变量相同,均指反射图像中凸起的顶点到边界线原来位置的距离。相应的,本步骤中计算得到每次移动,由机器人前端引起的边界线的形变量即为,计算每次移动机器人后,机器人前端在标定板上距离边界线的距离。Here, the shape variable of the boundary line is the same as the shape variable of the boundary line in steps S1011 to S1014, and both refer to the distance from the vertex of the protrusion in the reflected image to the original position of the boundary line. Correspondingly, each time the movement is calculated in this step, the shape variable of the boundary line caused by the front end of the robot is the distance from the boundary line of the front end of the robot on the calibration plate after each movement of the robot.
S103、根据形变量确定标定点的位置,完成对机器人的标定。S103. Determine a position of the calibration point according to the shape variable, and complete calibration of the robot.
在步骤S102移动机器人前端的过程中,持续对标定板的反射图像进行获取。In the process of moving the front end of the robot in step S102, the reflection image of the calibration plate is continuously acquired.
进一步的,如图6所示,步骤S103包括如下步骤:Further, as shown in FIG. 6, step S103 includes the following steps:
S1031、从计算得到的每次移动机器人前端对应的边界线的形变量中,提取数值最小的形变量。S1031: Extract a shape variable having the smallest value from the calculated shape variable of the boundary line corresponding to the front end of each mobile robot.
本步骤中的检测结果即为步骤S102中计算得到的由机器人前端挤压柔性膜导致的标定板的反射图像中边界线的形变量,即每次移动机器人后,机器人前端在标定板上距离边界线的距离。The detection result in this step is the shape variable of the boundary line in the reflection image of the calibration plate caused by the extrusion of the flexible film by the front end of the robot calculated in step S102, that is, the distance of the front end of the robot on the calibration plate after each movement of the robot The distance of the line.
从每次移动机器人前端计算得到的多个形变量中,提取出数值最小的形变量,即为从计算得到的多个距离中提取出标定板的反射图像中凸起的顶点到边界线的距离中的最小值。进一步的,从计算得到的多个距离中,分别提取出标定板的反射图像中凸起的顶点到相邻两条边界线的距离的最小值。From each of the plurality of shape variables calculated by the front end of the mobile robot, the shape variable with the smallest value is extracted, that is, the distance from the vertex of the convex to the boundary line in the reflection image of the calibration plate is extracted from the calculated plurality of distances. The minimum value in . Further, from the calculated plurality of distances, the minimum values of the distances from the vertices of the protrusions in the reflection image of the calibration plate to the adjacent two boundary lines are respectively extracted.
S1032、根据数值最小的形变量,确定标定点的位置。S1032: Determine the position of the calibration point according to the smallest shape variable.
根据步骤S1031分别提取出的标定板的反射图像中凸起的顶点到相邻两条边界线的距离的最小值,即可确定在由参考标定点确定的区域内,移动机器人前端的过程中,机器人前端在标定板上最接近标定板的角点的位置,该位置即为经校正的标点点。According to the minimum value of the distance between the raised vertex and the adjacent two boundary lines in the reflected image of the calibration plate extracted in step S1031, it can be determined that in the process of moving the front end of the robot in the area determined by the reference calibration point, The position of the front end of the robot on the calibration plate closest to the corner of the calibration plate, which is the corrected punctuation point.
如图4c所示,根据步骤S1031和步骤S1032,在标定板的角点附近最终计算得到经校正的标定点H的位置。图4c中对黑格部分未做填充,可以理解的是,图4c的黑格和白格的分布与图4a相同。As shown in FIG. 4c, according to step S1031 and step S1032, the position of the corrected calibration point H is finally calculated near the corner point of the calibration plate. The black grid portion is not filled in Fig. 4c, it being understood that the distribution of the black and white grids of Fig. 4c is the same as Fig. 4a.
通过本实施例能够获取机器人前端最靠近标定板的角点时,机器人前端距离相邻两条边界线的距离;由于标定板的角点在视觉坐标系中的坐标可知,则能够直接通过机器人前端距离相邻两条边界线的距离获取机器人坐标系和视觉坐标系之间的转换关系。According to the embodiment, the distance between the front end of the robot and the adjacent two boundary lines when the corner of the front end of the robot is closest to the calibration plate can be obtained. Since the coordinates of the corner point of the calibration plate in the visual coordinate system are known, the front end of the robot can be directly passed. The distance between the adjacent two boundary lines is used to obtain a conversion relationship between the robot coordinate system and the visual coordinate system.
参阅图7,图7是本发明机器人的标定系统一实施例的功能模块图。该机器人的标定系统200包括设置有柔性膜的标定板201,以及通过总线连接的视觉装置202、处理器203和存储器204;Referring to Figure 7, Figure 7 is a functional block diagram of an embodiment of a calibration system for a robot of the present invention. The calibration system 200 of the robot includes a calibration plate 201 provided with a flexible film, and a visual device 202, a processor 203 and a memory 204 connected by a bus;
存储器204用于存储机器人的预设移动规则以及处理器203的执行指令。标定板201设置在视觉装置202的视线范围内,视觉装置204用于对标定,201进行检测。处理器203用于执行下述动作:The memory 204 is used to store a preset movement rule of the robot and an execution instruction of the processor 203. The calibration plate 201 is disposed within the line of sight of the vision device 202, and the vision device 204 is used to detect the calibration 201. The processor 203 is configured to perform the following actions:
在设置有柔性膜的标定板201的一预定区域内控制机器人前端按预设规则移动,该预定区域包含角点;在移动过程中对标定板的预定区域进行检测,计算得到每次移动时,由机器人前端引起的边界线的形变量;根据计算得到的形变量确定标定点的位置,完成对机器人的标定。Controlling the front end of the robot to move according to a preset rule in a predetermined area of the calibration plate 201 provided with the flexible film, the predetermined area including a corner point; detecting a predetermined area of the calibration plate during the movement, and calculating each movement, The shape variable of the boundary line caused by the front end of the robot; the position of the calibration point is determined according to the calculated shape variable, and the calibration of the robot is completed.
本实施例中,标定板201为棋盘格;角点为棋盘格上垂线和水平线的交点,其中,垂线和水平线的为棋盘格上格子的边界线。在具体实施方式中,可以选择黑格和白格相交的棋盘格作为标定板201。In this embodiment, the calibration plate 201 is a checkerboard; the corner point is the intersection of the vertical line and the horizontal line on the checkerboard, wherein the vertical line and the horizontal line are the boundary lines of the grid on the checkerboard. In a specific embodiment, a checkerboard in which the black and white grids intersect can be selected as the calibration plate 201.
本实施例中,预定区域由至少四个参考点确定,其中,确定至少四个参考点包括:以机器人初始位置点为原点,在边界线的四个方向上分别确定至少一个参考点,以确定构成预定区域的至少四个参考点。In this embodiment, the predetermined area is determined by at least four reference points, wherein determining the at least four reference points comprises: determining, by using the initial position of the robot as an origin, determining at least one reference point in each of four directions of the boundary line to determine At least four reference points constituting a predetermined area.
进一步的,确定至少四个参考点具体为:以机器人前端初始位置点为原点,控制机器人前端分别沿边界线延伸的四个方向移动;获取每次移动时标定板的反射图像;根据反射图像,计算得到每次移动时,由机器人前端引起的边界线的形变量;从形变量中提取数值最小的形变量,数值最小的形变量对应的机器人前端所在的位置即为参考点。Further, determining at least four reference points is specifically: taking the initial position of the front end of the robot as an origin, controlling the front end of the robot to move in four directions extending along the boundary line respectively; acquiring a reflection image of the calibration plate for each movement; calculating according to the reflected image The shape variable of the boundary line caused by the front end of the robot is obtained for each movement; the shape variable with the smallest value is extracted from the shape variable, and the position of the robot front end corresponding to the smallest value variable is the reference point.
进一步的,处理器203执行的在设置有柔性膜的标定板上一预定区域内控制机器人前端按预设规则移动,为在预定区域内,通过控制器205将机器人前端按其最小移动距离逐渐从一个参考点移动至另一个参考点,直至遍历预定区域。Further, the processor 203 performs control on the calibration plate provided with the flexible film to move the front end of the robot according to a preset rule in a predetermined area, so that the robot front end gradually moves from the minimum moving distance by the controller 205 in the predetermined area. One reference point is moved to another reference point until the predetermined area is traversed.
进一步的,处理器203执行的在移动过程中对标定板的预定区域进行检测,计算得到每次移动时,由机器人前端引起的边界线的形变量,具体包括如下内容:Further, the processor 203 performs a detection on a predetermined area of the calibration plate during the movement, and calculates a shape variable of the boundary line caused by the front end of the robot for each movement, which specifically includes the following contents:
在预定区域内每次通过控制器205移动机器人前端,均通过视觉装置202获取一次标定板201的反射图像;对反射图像进行分析,计算得到每次移动时,由机器人前端引起的边界线的形变量。Each time the robot front end is moved by the controller 205 in the predetermined area, the reflected image of the calibration plate 201 is acquired by the visual device 202; the reflected image is analyzed, and the shape of the boundary line caused by the front end of the robot is calculated for each movement. variable.
进一步的,处理器203执行的根据形变量确定标定点的位置,具体包括如下内容:Further, the determining, by the processor 203, the location of the calibration point according to the shape variable, specifically including the following content:
从计算得到的每次移动机器人前端对应的边界线的形变量中,提取数值最小的形变量;根据数值最小的形变量,确定标定点的位置Extracting the shape variable with the smallest value from the calculated shape variable of the boundary line corresponding to the front end of each mobile robot; determining the position of the calibration point according to the shape variable with the smallest value
可以理解的是,本实施例中,处理器203执行的动作内容与图1至图7所示的机器人的标定方法相对应,具体参照上述对机器人标定方法的详细说明,此处不再赘述。It can be understood that, in this embodiment, the content of the action performed by the processor 203 corresponds to the calibration method of the robot shown in FIG. 1 to FIG. 7 . For details, refer to the detailed description of the method for calibrating the robot, and details are not described herein again.
另一方面,本发明还提出了一标定板实施例,如图8所示,图8为本发明标定板一实施例的结构示意图。On the other hand, the present invention also proposes a calibration plate embodiment, as shown in FIG. 8, which is a schematic structural view of an embodiment of the calibration plate of the present invention.
如图8所示,本实施例的标定板800包括标定板板块81,该标定板板块81上设置有柔性膜82。该柔性膜82收到挤压时会发生形变。As shown in FIG. 8, the calibration plate 800 of the present embodiment includes a calibration plate block 81 on which a flexible film 82 is disposed. The flexible film 82 deforms when it is squeezed.
进一步的,该标定板板块81上设置有用于标定的标定物,例如涂有彩色的标定圆环、标定点等。Further, the calibration plate block 81 is provided with a calibration object for calibration, such as a colored calibration ring, a calibration point, and the like.
进一步的,图9a所示,标定板板块81为棋盘格,图9a为本实施例中,标定板800的俯视图,图9b为图9a中沿L-L的剖视图,本实施例以黑格和白格相间的棋盘格为例,图9a中填充阴影的部分即为黑格,黑格左侧表示白格。可以理解的是,棋盘格上的黑格和白格的数量均有若干个,图9a中仅表示了一部分黑格和白格,不表示整个标定板。Further, as shown in FIG. 9a, the calibration plate 81 is a checkerboard, FIG. 9a is a top view of the calibration plate 800 in the present embodiment, and FIG. 9b is a cross-sectional view along LL in FIG. 9a. This embodiment uses a black and white grid. For example, in the case of a checkerboard, the shaded portion in Figure 9a is a black grid, and the left side of the black grid represents a white grid. It can be understood that there are several numbers of black and white grids on the checkerboard. Only a part of the black and white grids are shown in Fig. 9a, and the entire calibration board is not represented.
可以理解的是,黑格和白格交错的棋盘格仅是本申请中棋盘格的以具体实时方式,在其他实施例中,标定板可以具有垂线和水平线的棋盘格即可,角点即为棋盘格上垂线和水平线的交点,其中,垂线和水平线为棋盘格上每个格子的边界线,在其他实施例中,棋盘格也可以是均为黑格的棋盘格或均为白色的棋盘格,或其他任意颜色的棋盘格。It can be understood that the checkerboard of the black and white grids is only in a specific real-time manner in the checkerboard of the present application. In other embodiments, the calibration board can have a checkerboard of vertical and horizontal lines, and the corner point is The intersection of the vertical line and the horizontal line on the checkerboard, wherein the vertical line and the horizontal line are the boundary lines of each grid on the checkerboard. In other embodiments, the checkerboard may also be a checkerboard of all black squares or both are white. The checkerboard, or any other checkerboard of any color.
进一步的,棋盘格的角点附近设置有多个用于对机器人前端触点进行定位的标识点83。棋盘格的角点即为黑格和白格的交点,在该交点附近设置标识点83,能够在利用该标定板800标定物体时,能容易的通过标定板800的反射图像找到该角点。Further, a plurality of marker points 83 for positioning the front end contacts of the robot are disposed near the corners of the checkerboard. The corner point of the checkerboard is the intersection of the black grid and the white grid. A marker point 83 is provided near the intersection point, and the corner point can be easily found by the reflection image of the calibration plate 800 when the object is calibrated by the calibration plate 800.
进一步的,标定板板块81上设置的柔性膜82为表面反射红外的柔性膜。由于通过可见光照射,获取标定板800的反射图像时,在反射图像中可能看不到设置在标定板板块81上的标定点83,则通过表面反射红外的柔性膜,利用红外光照射标定板,进而使得在标定板的反射图像中观察到设置在标定板板块81上的标定点83。Further, the flexible film 82 disposed on the calibration plate 81 is a flexible film whose surface reflects infrared. When the reflected image of the calibration plate 800 is obtained by visible light irradiation, the calibration point 83 disposed on the calibration plate 81 may not be visible in the reflected image, and the infrared plate is used to illuminate the calibration plate by infrared light. Further, the calibration point 83 provided on the calibration plate 81 is observed in the reflected image of the calibration plate.
以上仅为本发明的实施方式,并非因此限制本发明的专利范围,凡是利用本发明说明书及附图内容所作的等效结构或等效流程变换,或直接或间接运用在其他相关的技术领域,均同理包括在本发明的专利保护范围。 The above is only the embodiment of the present invention, and is not intended to limit the scope of the invention, and the equivalent structure or equivalent process transformation made by the specification and the drawings of the present invention may be directly or indirectly applied to other related technical fields. The same is included in the scope of patent protection of the present invention.

Claims (16)

  1. 一种机器人的标定方法,包括标定板,所述标定板包括棋盘格,所述棋盘格上的垂线和水平线的交点为所述棋盘格上的角点,所述垂线和所述水平线为格子的边界线,其特征在于,包括: A calibration method for a robot includes a calibration plate, the calibration plate includes a checkerboard, and an intersection of a vertical line and a horizontal line on the checkerboard is a corner point on the checkerboard, and the vertical line and the horizontal line are The boundary line of the grid is characterized by comprising:
    在设置有柔性膜的标定板的一预定区域内控制机器人前端按预设规则移动,所述预定区域包含所述角点;Controlling the front end of the robot to move according to a preset rule in a predetermined area of the calibration plate provided with the flexible film, the predetermined area including the corner point;
    在移动过程中对所述标定板的所述预定区域进行检测,计算得到每次移动时,由所述机器人前端引起的边界线的形变量;Detecting the predetermined area of the calibration plate during the movement, and calculating a shape variable of the boundary line caused by the front end of the robot for each movement;
    根据所述形变量确定标定点的位置,完成对机器人的标定。The position of the calibration point is determined according to the shape variable, and the calibration of the robot is completed.
  2. 根据权利要求1所述的标定方法,其特征在于,所述预定区域由至少四个参考点确定,其中,确定至少四个参考点包括:The calibration method according to claim 1, wherein the predetermined area is determined by at least four reference points, wherein determining the at least four reference points comprises:
    以所述机器人前端的初始位置点为原点,在所述边界线的四个方向上分别确定至少一个参考点,以确定构成所述预定区域的至少四个参考点。Taking an initial position point of the front end of the robot as an origin, at least one reference point is respectively determined in four directions of the boundary line to determine at least four reference points constituting the predetermined area.
  3. 根据权利要求2所述的标定方法,其特征在于,所述以所述机器人前端的初始位置点为原点,在所述边界线的四个方向上分别确定至少一个参考点,以确定构成所述预定区域的至少四个参考点,包括: The calibration method according to claim 2, wherein the initial position point of the front end of the robot is taken as an origin, and at least one reference point is respectively determined in four directions of the boundary line to determine that the At least four reference points for the predetermined area, including:
    以所述机器人前端的初始位置点为原点,控制所述机器人前端分别沿所述边界线延伸的四个方向移动;Taking the initial position point of the front end of the robot as an origin, controlling the front ends of the robot to move in four directions extending along the boundary line respectively;
    获取每次移动时所述标定板的反射图像;Obtaining a reflection image of the calibration plate each time it moves;
    根据所述反射图像,计算得到每次移动时,由所述机器人前端引起的边界线的形变量;Calculating, according to the reflected image, a shape variable of a boundary line caused by the front end of the robot at each movement;
    从所述形变量中提取数值最小的形变量,所述数值最小的形变量对应的机器人前端所在的位置即为参考点。The shape variable with the smallest value is extracted from the shape variable, and the position of the robot front end corresponding to the smallest shape variable is the reference point.
  4. 根据权利要求1所述的标定方法,其特征在于,所述在设置有柔性膜的标定板上一预定区域内控制机器人前端按预设规则移动,包括:The calibration method according to claim 1, wherein the controlling the robot front end to move according to a preset rule in a predetermined area on the calibration plate provided with the flexible film comprises:
    在所述预定区域内,控制所述机器人前端按其最小移动距离移动,直至遍布所述区域。Within the predetermined area, the front end of the robot is controlled to move at its minimum moving distance until it is spread over the area.
  5. 根据权利要求1所述的标定方法,其特征在于,所述根据所述形变量确定标定点的位置,包括:The calibration method according to claim 1, wherein the determining the position of the calibration point according to the shape variable comprises:
    从计算得到的每次移动机器人前端对应的边界线的形变量中,提取数值最小的形变量;Extracting the shape variable with the smallest value from the calculated shape variable of the boundary line corresponding to the front end of each mobile robot;
    根据所述数值最小的形变量,确定所述标定点的位置。The position of the calibration point is determined based on the shape variable having the smallest value.
  6. 根据权利要求5所述的标定方法,其特征在于,所述根据所述数值最小的形变量,确定所述标定点的位置,包括:The calibration method according to claim 5, wherein the determining the position of the calibration point according to the shape variable having the smallest value comprises:
    以所述数值最小的形变量对应的位置点作为所述标定点的位置。The position point corresponding to the shape variable having the smallest value is used as the position of the calibration point.
  7. 一种机器人的标定系统,其特征在于,包括:设置有柔性膜的标定板,以及通过总线连接的视觉装置、处理器和存储器;A calibration system for a robot, comprising: a calibration plate provided with a flexible film, and a visual device, a processor and a memory connected by a bus;
    所述存储器,用于存储机器人的预设移动规则以及所述处理器的执行指令;The memory is configured to store a preset movement rule of the robot and an execution instruction of the processor;
    所述视觉装置,用于对所述标定板进行检测;The visual device is configured to detect the calibration plate;
    所述处理器用于执行下述动作:The processor is configured to perform the following actions:
    在设置有柔性膜的标定板的一预定区域内控制机器人前端按预设规则移动,所述预定区域包含所述角点;Controlling the front end of the robot to move according to a preset rule in a predetermined area of the calibration plate provided with the flexible film, the predetermined area including the corner point;
    在移动过程中对所述标定板的所述预定区域进行检测,计算得到每次移动时,由所述机器人前端引起的边界线的形变量;Detecting the predetermined area of the calibration plate during the movement, and calculating a shape variable of the boundary line caused by the front end of the robot for each movement;
    根据所述形变量确定标定点的位置,完成对机器人的标定。The position of the calibration point is determined according to the shape variable, and the calibration of the robot is completed.
  8. 根据权利要求7所述的标定系统,其特征在于,所述预定区域由至少四个参考点确定,其中,确定至少四个参考点包括:The calibration system according to claim 7, wherein said predetermined area is determined by at least four reference points, wherein determining at least four reference points comprises:
    以所述机器人前端的初始位置点为原点,在所述边界线的四个方向上分别确定至少一个参考点,以确定构成所述预定区域的至少四个参考点。Taking an initial position point of the front end of the robot as an origin, at least one reference point is respectively determined in four directions of the boundary line to determine at least four reference points constituting the predetermined area.
  9. 根据权利要求8所述的标定系统,其特征在于,所述以所述机器人前端的初始位置点为原点,在所述边界线的四个方向上分别确定至少一个参考点,以确定构成所述预定区域的至少四个参考点,包括:The calibration system according to claim 8, wherein said initial position point of said robot front end is taken as an origin, and at least one reference point is respectively determined in four directions of said boundary line to determine said composition At least four reference points for the predetermined area, including:
    以所述机器人前端的初始位置点为原点,控制所述机器人前端分别沿所述边界线延伸的四个方向移动;Taking the initial position point of the front end of the robot as an origin, controlling the front ends of the robot to move in four directions extending along the boundary line respectively;
    获取每次移动时所述标定板的反射图像;Obtaining a reflection image of the calibration plate each time it moves;
    根据所述反射图像,计算得到每次移动时,由所述机器人前端引起的边界线的形变量;Calculating, according to the reflected image, a shape variable of a boundary line caused by the front end of the robot at each movement;
    从所述形变量中提取数值最小的形变量,所述数值最小的形变量对应的机器人前端所在的位置即为参考点。The shape variable with the smallest value is extracted from the shape variable, and the position of the robot front end corresponding to the smallest shape variable is the reference point.
  10. 根据权利要求7所述的标定系统,其特征在于,所述处理器执行的在设置有柔性膜的标定板上一预定区域内控制机器人前端按预设规则移动,包括:The calibration system according to claim 7, wherein the controlling the movement of the robot front end by a predetermined rule in a predetermined area on the calibration plate provided with the flexible film, comprising:
    在所述预定区域内,控制所述机器人前端按其最小移动距离移动,直至遍布所述区域。Within the predetermined area, the front end of the robot is controlled to move at its minimum moving distance until it is spread over the area.
  11. 根据权利要求7所述的标定系统,其特征在于,所述处理器执行的所述根据所述形变量确定标定点的位置,包括:The calibration system according to claim 7, wherein the determining, by the processor, the position of the calibration point according to the deformation variable comprises:
    从计算得到的每次移动机器人前端对应的边界线的形变量中,提取数值最小的形变量;Extracting the shape variable with the smallest value from the calculated shape variable of the boundary line corresponding to the front end of each mobile robot;
    根据所述数值最小的形变量,确定所述标定点的位置。The position of the calibration point is determined based on the shape variable having the smallest value.
  12. 根据权利要求11所述的标定方法,其特征在于,所述处理器执行的所述根据所述数值最小的形变量,确定所述标定点的位置,包括:The calibration method according to claim 11, wherein the determining, by the processor, the location of the calibration point according to the shape variable having the smallest value comprises:
    以所述数值最小的形变量对应的位置点作为所述标定点的位置。The position point corresponding to the shape variable having the smallest value is used as the position of the calibration point.
  13. 一种标定板,其特征在于,包括:标定板板块,所述标定板板块上设置有柔性膜。A calibration plate, comprising: a calibration plate block, wherein the calibration plate plate is provided with a flexible film.
  14. 根据权利要求13所述的标定板,其特征在于,所述标定板板块为棋盘格。The calibration plate of claim 13 wherein said calibration plate block is a checkerboard.
  15. 根据权利要求14所述的标定板,其特征在于,所述棋盘格的角点附近设置有多个用于对机器人前端触点进行定位的标识点。The calibration plate according to claim 14, wherein a plurality of marking points for positioning the front end contact of the robot are disposed near a corner of the checkerboard.
  16. 根据权利要求15所述的标定板,其特征在于,所述柔性膜为表面反射红外的柔性膜。 The calibration plate of claim 15 wherein said flexible membrane is a flexible membrane having a surface that reflects infrared.
PCT/CN2017/085331 2017-05-22 2017-05-22 Robot calibration method, system, and calibration board WO2018213980A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201780034036.3A CN109311151B (en) 2017-05-22 2017-05-22 Calibration method and system of robot and calibration plate
PCT/CN2017/085331 WO2018213980A1 (en) 2017-05-22 2017-05-22 Robot calibration method, system, and calibration board

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2017/085331 WO2018213980A1 (en) 2017-05-22 2017-05-22 Robot calibration method, system, and calibration board

Publications (1)

Publication Number Publication Date
WO2018213980A1 true WO2018213980A1 (en) 2018-11-29

Family

ID=64395080

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/085331 WO2018213980A1 (en) 2017-05-22 2017-05-22 Robot calibration method, system, and calibration board

Country Status (2)

Country Link
CN (1) CN109311151B (en)
WO (1) WO2018213980A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI747079B (en) * 2019-11-19 2021-11-21 財團法人資訊工業策進會 Measurement system and method for positioning precision of a robot arm

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2013009510A2 (en) * 2011-07-08 2013-01-17 Restoration Robotics, Inc. Calibration and transformation of a camera system's coordinate system
JP2014079864A (en) * 2012-10-18 2014-05-08 Amada Co Ltd Welding robot, and method for arranging arrangement object on surface plate in welding robot
CN105234943A (en) * 2015-09-09 2016-01-13 大族激光科技产业集团股份有限公司 Industrial robot demonstration device and method based on visual recognition
CN205403725U (en) * 2016-02-22 2016-07-27 易喜林 Ultra -thin high accuracy 3D system scaling board framework
CN105904107A (en) * 2016-04-21 2016-08-31 大族激光科技产业集团股份有限公司 Mobile robot laser marking system and laser marking method
CN106272444A (en) * 2016-08-31 2017-01-04 山东中清智能科技有限公司 A kind of realize trick relation and method that dual robot relation is demarcated simultaneously

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1057246C (en) * 1998-07-01 2000-10-11 中国科学院合肥智能机械研究所 Multifunctional skin-like sensor
JP2005103720A (en) * 2003-09-30 2005-04-21 Okuma Corp Measuring device and measuring method
JP2007263795A (en) * 2006-03-29 2007-10-11 Olympus Corp Calibration sample, pattern inspection device and its method
US9652077B2 (en) * 2010-12-09 2017-05-16 T-Mobile Usa, Inc. Touch screen testing platform having components for providing conductivity to a tip
CN103075973A (en) * 2012-12-31 2013-05-01 吉林大学 Non-contact online inspection method for automobile body gap size
CN104089741B (en) * 2014-06-10 2017-01-25 安徽埃力智能科技有限公司 Pressure distribution sensor calibration measuring apparatus
CN104616292B (en) * 2015-01-19 2017-07-11 南开大学 Monocular vision measuring method based on global homography matrix
JP2016187844A (en) * 2015-03-30 2016-11-04 セイコーエプソン株式会社 Robot, robot control device and robot system
CN106644231B (en) * 2016-12-08 2019-03-08 西安近代化学研究所 Measure the effect target structure and test method of removable target shock wave pressure peak value

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2013009510A2 (en) * 2011-07-08 2013-01-17 Restoration Robotics, Inc. Calibration and transformation of a camera system's coordinate system
JP2014079864A (en) * 2012-10-18 2014-05-08 Amada Co Ltd Welding robot, and method for arranging arrangement object on surface plate in welding robot
CN105234943A (en) * 2015-09-09 2016-01-13 大族激光科技产业集团股份有限公司 Industrial robot demonstration device and method based on visual recognition
CN205403725U (en) * 2016-02-22 2016-07-27 易喜林 Ultra -thin high accuracy 3D system scaling board framework
CN105904107A (en) * 2016-04-21 2016-08-31 大族激光科技产业集团股份有限公司 Mobile robot laser marking system and laser marking method
CN106272444A (en) * 2016-08-31 2017-01-04 山东中清智能科技有限公司 A kind of realize trick relation and method that dual robot relation is demarcated simultaneously

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI747079B (en) * 2019-11-19 2021-11-21 財團法人資訊工業策進會 Measurement system and method for positioning precision of a robot arm
US11433551B2 (en) 2019-11-19 2022-09-06 Institute For Information Industry Measurement system and method for positioning accuracy of a robotic arm

Also Published As

Publication number Publication date
CN109311151A (en) 2019-02-05
CN109311151B (en) 2021-07-09

Similar Documents

Publication Publication Date Title
WO2017128865A1 (en) Multiple lens-based smart mechanical arm and positioning and assembly method
WO2014142596A1 (en) Device for sensing operation of air cushion and method therefor
Sato et al. Finger-shaped gelforce: sensor for measuring surface traction fields for robotic hand
WO2009145485A2 (en) Contact sensing device with improved edge position recognition characteristics
WO2018214147A1 (en) Robot calibration method and system, robot and storage medium
WO2014109498A1 (en) Head mounted display providing eye gaze calibration and control method thereof
WO2016127838A1 (en) Computer numerical control machine tool and commissioning method therefor
WO2015099251A1 (en) Method and apparatus for analyzing shape of wafer
WO2016192438A1 (en) Motion sensing interaction system activation method, and motion sensing interaction method and system
WO2016145581A1 (en) Method for generating precise pattern according to hand-drawn graph
WO2015199502A1 (en) Apparatus and method for providing augmented reality interaction service
WO2018213980A1 (en) Robot calibration method, system, and calibration board
WO2017135707A9 (en) Touch-pressure sensitivity correction method and computer-readable recording medium
WO2019245320A1 (en) Mobile robot device for correcting position by fusing image sensor and plurality of geomagnetic sensors, and control method
WO2014086270A1 (en) System and method for selecting measuring basis correction dynamic state intelligently
WO2018072172A1 (en) Method and apparatus for identifying shapes within images, device and computer storage medium
WO2019124728A1 (en) Apparatus and method for identifying object
WO2021002530A1 (en) Portable terminal for generating indoor structure information based on wall surface pointing, and operating method therefor
CN111645067A (en) High-intelligence robot environment sensing method and system
WO2018203590A1 (en) Contact position and depth measurement algorithm for three-dimensional touch recognition
Palla et al. Embedded implementation of an eye-in-hand visual servoing control for a wheelchair mounted robotic arm
Doi et al. Novel proximity sensor for realizing tactile sense in suction cups
JP2005186193A (en) Calibration method and three-dimensional position measuring method for robot
CN115990890B (en) Calibration method and device for manipulator, computer equipment and storage medium
JP7149220B2 (en) Three-dimensional measuring device and three-dimensional measuring method

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17910869

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17910869

Country of ref document: EP

Kind code of ref document: A1