WO2020121399A1 - ロボット制御システム及びロボット制御方法 - Google Patents
ロボット制御システム及びロボット制御方法 Download PDFInfo
- Publication number
- WO2020121399A1 WO2020121399A1 PCT/JP2018/045428 JP2018045428W WO2020121399A1 WO 2020121399 A1 WO2020121399 A1 WO 2020121399A1 JP 2018045428 W JP2018045428 W JP 2018045428W WO 2020121399 A1 WO2020121399 A1 WO 2020121399A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- work
- coordinate system
- coordinate
- image processing
- coordinate value
- Prior art date
- Legal status (The legal status 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 status listed.)
- Ceased
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Program-controlled manipulators
- B25J9/16—Program controls
- B25J9/1694—Program controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
- B25J9/1697—Vision controlled systems
Definitions
- the present specification discloses a technique related to a robot control system and a robot control method including a camera that images a work supplied from a supply device from above.
- a camera attached to the tip of the robot arm or a camera fixedly arranged above the robot arm movable range as in Patent Document 1 is used to determine the position coordinates of the workpiece and the work target portion.
- a system is used that detects the position coordinates of and automatically corrects the gripping position of the work or the position of the work target part.
- a CCTV lens which has a high degree of distribution, is often used because of its price, size, weight, and the like, and the image of a workpiece that is picked up differs in appearance and shape between the central portion and the peripheral portion.
- This parallax has a three-dimensional shape and becomes more prominent in a work with a large height, and the detection rate of the target work and the detection accuracy of position coordinates tend to deteriorate toward the periphery of the image where the influence of parallax increases.
- the field of view is wider and a large work can be imaged, so the above-described deterioration of the position coordinate detection accuracy becomes a factor that deteriorates the robot work accuracy.
- the accuracy can be further secured if the heights do not match. difficult.
- a supply device that supplies a work area of a known height dimension to a work area at a constant height position, and a robot that performs a predetermined work on the work supplied to the work area
- a two-dimensional camera that images the work supplied to the work area from a predetermined height position, and a two-dimensional image captured by the camera is processed to set the position of the work as a reference point of the image.
- An image processing unit that recognizes coordinate values of a two-dimensional coordinate system (hereinafter referred to as “vision coordinate system”), and coordinate values of the vision coordinate system that are recognized as the position of the work by image processing of the image processing unit, of the robot.
- a coordinate conversion unit that converts the coordinate values of the world coordinate system, which is a three-dimensional coordinate system, and a target position of the arm of the robot based on the position of the workpiece that is converted into the coordinate values of the world coordinate system by the coordinate conversion unit.
- the work that is the work target of the robot is imaged by the two-dimensional camera, but even if the two-dimensional image captured by the two-dimensional camera is processed, the three-dimensional shape such as the height dimension of the work is unknown. Absent.
- a robot used in a production factory handles a large number of works of the same shape supplied by a supply device, so that the three-dimensional shape such as the height dimension of the work can be handled as known data.
- the size of the work in the image captured by the two-dimensional camera changes depending on the distance (working distance) between the two-dimensional camera and the upper end surface of the work, The size of the work in the image changes accordingly. For example, as the height dimension of the work increases, the distance between the upper end surface of the work and the camera decreases, and the size of the work in the image increases.
- the coordinate value of the two-dimensional vision coordinate system recognized as the position of the work in the image processing of the image processing unit is corrected according to the height dimension of the work, and the corrected vision coordinate system is corrected. Is converted into coordinate values of a three-dimensional world coordinate system that controls the position of the robot arm.
- the image recognition system for obtaining the coordinate values of the vision coordinate system can be inexpensively configured with one two-dimensional camera, and the calculation load of image processing can be reduced.
- the height position (Z coordinate value) of the work area to which the work is supplied can be handled as known data (the Z coordinate value of the work area is known) if the height position is always a constant height position.
- the height position of the upper end surface of the work can also be handled as known data.
- the coordinate values of the two-dimensional vision coordinate system can be converted into the coordinate values of the three-dimensional world coordinate system.
- the coordinate values of the vision coordinate system recognized as the position of the work by the image processing of the image processing unit are corrected according to the height dimension of the work and the height position of the work area, and the corrected vision coordinates
- the coordinate value of the system may be converted into the coordinate value of the world coordinate system.
- FIG. 1 is a front view showing the appearance of the robot control system of the first embodiment.
- FIG. 2 is a diagram illustrating the relationship between the height position of the hand camera, the height position of the work placement surface in the work area, and the height dimension of the work in the first embodiment.
- FIG. 3 is a block diagram showing the electrical configuration of the robot control system of the first embodiment.
- FIG. 4 is a diagram showing a display example of the GUI.
- FIG. 5 is a diagram illustrating an example of the picking impossible condition “overlap”.
- FIG. 6 is a diagram showing an example of the picking incapable condition “adjacent”.
- FIG. 6 is a diagram showing an example of the picking impossible condition “abnormal posture”.
- FIG. 8 is a front view showing the appearance of the robot control system of the second embodiment.
- FIG. 9 is a diagram showing the configuration of the main part of the robot control system of the third embodiment.
- Example 1 will be described with reference to FIGS. 1 to 7. First, the configuration of the robot 11 will be described with reference to FIG.
- the robot 11 is, for example, a 5-axis vertical multi-joint robot, and includes a fixed base 13 installed on the factory floor 12 and a fixed base 13 rotatably provided on the fixed base 13 about a first joint shaft 14 (J1).
- the third arm 19 rotatably provided by the third arm 19, the wrist portion 21 rotatably provided by the fourth joint shaft 20 (J4) at the tip of the third arm 19, and the fifth joint shaft 21 by the wrist portion 21. 22 (J5) and an end effector 23 which is attached so as to be rotatable and replaceable.
- the end effector 23 attached to the wrist portion 21 is configured to rotate by the fourth joint shaft 20 which is the joint shaft of the wrist portion 21.
- the end effector 23 may be, for example, a suction nozzle, a hand, a gripper, a welding machine, or the like.
- the first to fifth joint shafts 14, 16, 18, 20, 22 of the robot 11 are driven by servomotors 25 to 29 (see FIG. 3), respectively.
- each of the servo motors 25 to 29 is provided with an encoder 31 to 35 for detecting a rotation angle, and information about the rotation angle detected by each of the encoders 31 to 35 is transmitted via a servo amplifier 36. It is fed back to the control unit 37.
- the controller 37 feeds back the servo motors 25 to 29 via the servo amplifier 36 so that the rotation angles of the servo motors 25 to 29 detected by the encoders 31 to 35 match the respective target rotation angles.
- the positions of the arms 15, 17, 19 of the robot 11, the wrist part 21, and the end effector 23 are feedback-controlled to the respective target positions.
- the servo amplifier 36 is a multi-axis amplifier that feedback-controls the plurality of servo motors 25 to 29.
- the servo motors 25 to 29 are feedback-controlled by separate servo amplifiers one by one. Is also good.
- the supply device 39 that supplies the work 30 to be worked to the work area 38 at a constant height position.
- the supply device 39 may be configured by a conveyor, or a parts feeder having any structure such as a vibration type parts feeder may be used.
- the height position of the work area 38 is known. It may be a constant height position.
- a fixed camera 51 which is a two-dimensional camera, is vertically installed on a fixed structure 50 (for example, a ceiling of a robot protection fence) installed above the work area 38.
- the work 30 is imaged.
- the robot control unit 42 that controls the operation of the robot 11 configured as described above, as shown in FIG. 3, has a parameter input unit 46, a parameter storage unit 47, an image processing unit 43, a coordinate conversion unit 44, a control unit 37, and It has a configuration including a servo amplifier 36 and the like.
- the parameter input unit 46 converts the parameter value of image processing input by the operator by operating the input device 45 into numerical information suitable for internal processing.
- the input device 45 is a mouse, a keyboard, or the like, and may be a touch panel on the LCD.
- the operator operates the input device 45 in accordance with an instruction of a GUI (graphical user interface) displayed on a display device 48 such as an LCD monitor, which is a peripheral device of the robot control unit 42, and operates the height dimension of the work 30.
- the parameter value is input to the parameter input unit 46.
- On the display device 48 which is a peripheral device of the robot control unit 42, as shown in FIG. 4, an input field for the parameter value of the image processing to be input by the operator is displayed by GUI.
- the parameter value converted into numerical information by the parameter input unit 46 is stored in the parameter storage unit 47 including a storage such as a ROM or a HDD.
- Each parameter value is stored in the parameter storage unit 47 as a value unique to each type of work 30 to be worked. As a result, even when the same type of work 30 is used in another supply device or another robot, image processing can be performed using the same parameter value, and therefore, the same accuracy is always obtained without depending on the environment. Can be kept.
- the image processing unit 43 has a function of performing pattern matching using the contour shape of the workpiece registered in advance as a template and detecting the position coordinates and angle of the workpiece 30 to be gripped.
- the grippable condition means that the following three conditions (1) to (3) are satisfied.
- the grippable condition (1) is that there is no overlap between the works A as shown in FIG.
- the work A shown in FIG. 5 is a washer. This is because when the works A overlap each other, the height of the works A recognized by the image processing fluctuates from a known value, so that the end effector 23 cannot hold the work A.
- the grippable condition (2) is that the works B are not adjacent to each other as shown in FIG.
- the work B shown in FIG. 6 is a screw. This is because when the works B are adjacent to each other, the end effector 23 interferes with the adjacent work B that is not a grip target.
- the grippable condition (3) is that the work B as shown in FIG. 7 is not in an abnormal posture.
- the work B shown in FIG. 7 is a screw. This is because when the work B has an abnormal posture, the height of the work B recognized by image processing fluctuates from a known value, and the end effector 23 cannot hold the work B.
- the image processing unit 43 processes the two-dimensional image captured by the fixed camera 51 and sets the position of the work 30 on the work area 38 to the two-dimensional orthogonal coordinates with the reference point (for example, the center of the image) of the image as the origin. Recognize by the coordinate value of the system (hereinafter referred to as "vision coordinate system") (image processing step).
- the coordinate axes of this vision coordinate system are the Xv axis and the Yv axis that are orthogonal to each other on the image. Since the fixed camera 51 that images the work 30 on the work area 38 images the optical axis vertically downward, the captured image is a horizontal plane image, and the Xv axis and the Yv axis are orthogonal coordinate axes on the horizontal plane.
- the image processing unit 43 recognizes the position of the work 30 by the image processing with the coordinate value in pixel units in the vision coordinate system.
- the coordinate conversion unit 44 converts the coordinate values of the two-dimensional vision coordinate system recognized as the position of the work 30 by the image processing of the image processing unit 43 into the arms 15, 17, 19 of the robot 11, the wrist unit 21, and the end.
- the coordinates are converted into coordinate values in the world coordinate system for controlling the position of the effector 23 (coordinate conversion step).
- This world coordinate system is a three-dimensional orthogonal coordinate system with the reference point as the origin, and the coordinate axes of the world coordinate system are the orthogonal coordinate axes (X axis and Y axis) on the horizontal plane and the vertically upward coordinate axis (Z axis). is there.
- the unit of the coordinate value of this world coordinate system is the unit of length (for example, ⁇ m unit).
- the origin (reference point) of this world coordinate system is, for example, the center of the arm movable region of the robot 11 (the region where the end effector 23 on the tip side of the wrist 21 can move).
- the control unit 37 based on the position of the work 30 converted into the coordinate values of the three-dimensional world coordinate system by the coordinate conversion unit 44, the target positions of the arms 15, 17, 19 of the robot 11, the wrist unit 21, and the end effector 23. Is set by the coordinate values of the world coordinate system, and the positions of the arms 15, 17, 19 and the wrist 21 and the end effector 23 are controlled by the coordinate values of the world coordinate system (control step).
- the work 30 on the work area 38 that is the work target of the robot 11 is imaged by the two-dimensional fixed camera 51.
- the work 30 is processed.
- the three-dimensional shape such as the height dimension of 30 is unknown.
- the robot 11 used in the production factory handles a large number of workpieces 30 having the same shape supplied by the supply device 39, and thus the three-dimensional shape such as the height dimension of the workpiece 30 can be handled as known data. is there.
- the size of the work 30 in the image captured by the fixed camera 51 changes according to the distance (working distance) between the fixed camera 51 and the upper end surface of the work 30, the height dimension of the work 30. Accordingly, the size of the work 30 in the image changes. For example, as the height dimension of the work 30 increases, the distance between the upper end surface of the work 30 and the fixed camera 51 decreases, and the size of the work 30 in the image increases.
- the coordinate conversion unit 44 sets the coordinate value of the two-dimensional vision coordinate system recognized as the position of the work 30 by the image processing of the image processing unit 43 to the work 30.
- the correction is performed according to the height dimension, and the corrected coordinate value of the vision coordinate system is converted into the coordinate value of the three-dimensional world coordinate system that controls the arm position of the robot 11 (coordinate conversion step).
- coordinate conversion step the process of correcting the coordinate value of the vision coordinate system according to the height dimension of the work 30 will be described in detail.
- the image processing unit 43 recognizes the coordinate values (Xv, Yv) of the position of the work 30 on the work area 38 in the vision coordinate system in pixel units, while the coordinate values (X, Y, Z) in the world coordinate system.
- the unit of () is a unit of length (for example, a unit of [ ⁇ m]). Therefore, it is necessary to convert the coordinate value in the pixel unit of the vision coordinate system into the coordinate value of the same length unit (for example, a unit of [ ⁇ m]) as the coordinate value of the world coordinate system.
- the resolution used in the process of converting the coordinate value of the pixel unit of the vision coordinate system into the coordinate value of the unit of the same length as the coordinate value of the world coordinate system depends on the height dimension H of the work 30.
- the corrected resolution Rh is used to convert the coordinate value in the pixel unit of the vision coordinate system into the coordinate value in the unit of the same length as the coordinate value in the world coordinate system.
- the height dimension H of the work 30 needs to be within the range of the depth of field of the lens 52 of the fixed camera 51.
- the resolution is a length per pixel, and is represented by a unit of [ ⁇ m/pixel], for example. Specifically, the resolution can be calculated by the field of view of the fixed camera 51/the number of pixels.
- the field of view (actual length of the area shown in the image) is the working distance, which is the distance between the lens 52 of the fixed camera 51 and the upper end surface of the work 30 to be imaged. Since it changes in proportion to WD, the resolution also changes in proportion to working distance WD.
- the height position of the work placement surface of the work area 38 is used as the reference height position, and the resolution at the reference height position is calculated as the reference resolution Ro.
- the distance between the reference height position and the lens 52 of the fixed camera 51 is calculated as the reference working distance WDstd, and the resolution at the reference working distance WDstd is calculated as the reference resolution Ro.
- the reference working distance WDstd is a fixed value determined in advance within a range in which the fixed camera 51 can image the work 30 on the work area 38.
- the unit resolution Runi is, for example, the amount of change in resolution per 1 mm
- the unit of the predetermined height Tcp is also the unit of [mm], and both units are matched.
- the corrected resolution Rh is obtained by subtracting the integrated value of the unit resolution Runi and the height dimension H of the work 30 from the reference resolution Ro using the following equation (2).
- Rh Ro-Runi ⁇ H (2)
- the coordinate value (Xv , Yv ) in pixel units of the vision coordinate system is the same as the coordinate value of the world coordinate system. Convert to the coordinate value (X, Y) in the unit of length.
- the height position (Z coordinate value) of the work area 38 since the height position (Z coordinate value) of the work area 38 is always a constant height position, it can be treated as known data (the Z coordinate value of the work area 38 is known). Furthermore, by adding the known height dimension H of the work 30 to the height position of the work area 38, the height position of the upper end surface of the work 30 can also be handled as known data. Thereby, the coordinate values of the two-dimensional vision coordinate system can be converted into the coordinate values of the three-dimensional world coordinate system.
- the resolution indicates the size per pixel in the image and is calculated by the following equation (5).
- Resolution field of view/number of pixels (5)
- the visual field is derived by the following equation (6) when the working distance WD is determined.
- Field of view (H/focal length) ⁇ WD (6)
- H is the size of the image sensor of the fixed camera 51.
- the unit resolution ⁇ is a constant determined by the specifications (number of pixels, unit size) of the image sensor of the fixed camera 51, the focal length of the lens 52, and the magnification.
- the resolution is proportional to the working distance WD.
- the coordinate value of the two-dimensional vision coordinate system recognized as the position of the work 30 on the work area 38 by the image processing of the image processing unit 43 is determined according to the height dimension of the work 30. Since the coordinate values of the corrected vision coordinate system are converted into the coordinate values of the three-dimensional world coordinate system that controls the arm position of the robot 11, the image captured by the two-dimensional fixed camera 51 is corrected. The coordinate values of the two-dimensional vision coordinate system recognized as the position of the work 30 can be converted into the coordinate values of the three-dimensional world coordinate system. As a result, the image recognition system for obtaining the coordinate values of the vision coordinate system can be inexpensively configured with the one two-dimensional fixed camera 51, and the demand for cost reduction can be satisfied. Moreover, since it is two-dimensional image processing, the calculation load of the image processing can be reduced as compared with the conventional three-dimensional image processing, and the demand for high-speed image processing can be met at low cost.
- the work 30 on the work area 38 is imaged by the fixed camera 51, it is not necessary to move the position of the fixed camera 51 by the robot 11 during production, and the work 30 can be imaged accordingly.
- the time required can be shortened, the productivity can be improved, and the control of the robot 11 can be simplified.
- the fixed camera 51 mounted vertically downward on the fixed structure 50 (for example, the ceiling of the robot protection fence) installed above the work area 38 captures an image of the work 30 on the work area 38.
- the hand camera 40 attached to the wrist portion 21 of the robot 11 is used as a two-dimensional camera that images the work 30 on the work area 38. ing.
- the hand camera 40 when the hand camera 40 images the work 30 on the work area 38 while the robot 11 is operating (in production) and the position of the work 30 is recognized by the coordinate values of the vision coordinate system,
- the hand camera 40 is oriented vertically downward and the work 30 on the work area 38 is housed within the field of view of the hand camera 40, and the lens 41 of the hand camera 40 and the reference height position (the height of the work placement surface of the work area 38).
- the position of the hand camera 40 is controlled to a constant height by controlling the robot 11 so that the distance between the hand camera 40 and the position) becomes a predetermined reference working distance WDstd.
- the reference height position is not limited to the height position of the work placement surface of the work area 38, and may be another height position.
- the reference height position may be appropriately set within the range of height positions at which the image can be captured. Other matters are the same as in the first embodiment.
- the coordinate values of the two-dimensional vision coordinate system in which the image captured by the two-dimensional hand camera 40 is processed and recognized as the position of the work 30. Can be accurately converted into coordinate values in the three-dimensional world coordinate system.
- FIG. 9 shows a configuration example using the fixed camera 51.
- the fixed camera 51 is installed so that the works 30 on the plurality of work areas 38 are accommodated within the field of view.
- the height position of the hand camera 40 may be controlled so that the works 30 on the plurality of work areas 38 fit within the field of view of the hand camera 40.
- the height positions of the plurality of work areas 38 are different for each work area 38 due to an assembly error or the like. It may differ slightly. In this case, the size of the work 30 in the image captured by the fixed camera 51 from the predetermined height position changes according to the height dimension of the work 30 and the height position of the work area 38.
- the coordinate conversion unit 44 sets the coordinate value of the vision coordinate system recognized as the position of the work 30 by the image processing of the image processing unit 43 to the height dimension of the work 30 and the height of the work area 38. Correction is performed according to the position, and the corrected coordinate value of the vision coordinate system is converted into the coordinate value of the world coordinate system (coordinate conversion step).
- the height position of the work placement surface of any one of the plurality of work areas 38 may be set as the reference height position, or the fixed camera 51 may be used.
- the height position of the work placement surface of the central work area 38 located immediately below may be set as the reference height position.
- the reference height position is not limited to the height position of the work placement surface of the work area 38, and may be another height position.
- the fixed camera 51 images the work 30 on the work area 38.
- the reference height position may be set appropriately within the range of possible height positions.
- the work 30 on each work area 38 is not affected.
- the coordinate value of the two-dimensional vision coordinate system recognized as the position can be accurately converted into the coordinate value of the three-dimensional world coordinate system.
- the present invention is not limited to the first to third embodiments described above, and both the hand camera 40 and the fixed camera 51 are installed, and the hand camera 40 is provided depending on the required resolution and the position of the work area 38 in the arm movable area of the robot 11.
- the fixed camera 51 and the fixed camera 51 may be selectively used. For example, when the size of the work 30 is small and high resolution is required, the hand camera 40 is used, and the hand camera 40 is used for the work area 38 installed outside the visual field of the fixed camera 51. It should be used.
- the hand camera 40 may be moved for each work area 38 to image the work 30.
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Manipulator (AREA)
Abstract
Description
まず、図1に基づいてロボット11の構成を説明する。
把持可能な条件(1)は図5に示すようなワークA同士の重なりが無いことである。図5に示すワークAはワッシャである。ワークAが重なっていると、画像処理で認識するワークAの高さが既知の値から変動するため、エンドエフェクタ23で把持できない姿勢となるためである。
把持可能な条件(2)は図6に示すようなワークB同士の隣接が無いことである。図6に示すワークBはねじである。ワークBが隣接していると、エンドエフェクタ23が隣接する把持対象外のワークBと干渉するためである。
把持可能な条件(3)は図7に示すようなワークBが異常な姿勢になっていないことである。図7に示すワークBはねじである。ワークBが異常な姿勢になると、画像処理で認識するワークBの高さが既知の値から変動するため、エンドエフェクタ23で把持できない姿勢となるためである。
Runi =(Ro -R1 )/Tcp …(1)
Rh =Ro -Runi ×H …(2)
Y=Yv ×Rh …(4)
この2次元のビジョン座標系の座標値を3次元の世界座標系の座標値に変換する。
分解能=視野/画素数 …(5)
視野=(H/焦点距離)×WD …(6)
ここで、Hは固定カメラ51のイメージセンサのサイズである。
分解能={(H/焦点距離)×WD}/画素数
={(H/焦点距離)/画素数}×WD
=α×WD ……(7)
Runi =(Ro -R1 )/Tcp …(8)
Rh =Ro -Runi ×(H+ΔWD) …(9)
X=Xv ×Rh …(10)
Y=Yv ×Rh …(11)
この2次元のビジョン座標系の座標値を3次元の世界座標系の座標値に変換する。
尚、上記各実施例1~3に限定されず、ハンドカメラ40と固定カメラ51の両方を設置して、要求される分解能やロボット11のアーム可動領域内における作業エリア38の位置によってハンドカメラ40と固定カメラ51とを使い分けるようにしても良い。例えば、ワーク30のサイズが小さくて高い分解能が要求される場合には、ハンドカメラ40を使用し、また、固定カメラ51の視野から外れた位置に設置された作業エリア38についてはハンドカメラ40を使用するようにすれば良い。また、固定カメラ51の視野内に複数の作業エリア38が収まる場合には、固定カメラ51の視野内に複数の作業エリア38を収めて撮像すれば、複数の作業エリア38上のワーク30の画像処理を能率良く行うことができる。或は、複数の作業エリア38が存在する場合に、作業エリア38毎にハンドカメラ40を移動させてワーク30を撮像するようにしても良い。
Claims (12)
- 高さ寸法が既知のワークを一定の高さ位置の作業エリアに供給する供給装置と、
前記作業エリアに供給されたワークに対して所定の作業を行うロボットと、
前記作業エリアに供給されたワークを所定の高さ位置から撮像する2次元のカメラと、
前記2次元のカメラで撮像した2次元の画像を処理して前記ワークの位置を当該画像の基準点を原点とする2次元座標系(以下「ビジョン座標系」という)の座標値で認識する画像処理部と、
前記画像処理部の画像処理で前記ワークの位置として認識した前記ビジョン座標系の座標値を前記ロボットの3次元座標系である世界座標系の座標値に変換する座標変換部と、
前記座標変換部で前記世界座標系の座標値に変換した前記ワークの位置に基づいて前記ロボットのアームの目標位置を前記世界座標系の座標値で設定して当該アームの位置を前記世界座標系の座標値で制御する制御部とを備え、
前記座標変換部は、前記2次元のカメラで撮像した画像内の前記ワークのサイズが当該ワークの高さ寸法に応じて変化することを考慮して、前記画像処理部の画像処理で前記ワークの位置として認識した前記ビジョン座標系の座標値を当該ワークの高さ寸法に応じて補正し、補正後のビジョン座標系の座標値を前記世界座標系の座標値に変換する、ロボット制御システム。 - 前記画像処理部は、前記ビジョン座標系で前記ワークの位置の座標値をピクセル単位で認識し、
前記座標変換部は、前記画像処理部の画像処理で前記ワークの位置として認識した前記ビジョン座標系の座標値を当該ワークの高さ寸法に応じて補正する際に、前記ビジョン座標系のピクセル単位の座標値を前記世界座標系の座標値と同じ長さの単位の座標値に変換する処理に用いる分解能(1ピクセル当たりの長さ)を前記ワークの高さ寸法に応じて補正し、補正後の分解能を用いて前記ビジョン座標系のピクセル単位の座標値を前記世界座標系の座標値と同じ長さの単位の座標値に変換する、請求項1に記載のロボット制御システム。 - 前記座標変換部は、前記作業エリアのワーク載置面の高さ位置を基準高さ位置として当該基準高さ位置における分解能を基準分解能Ro として算出すると共に、当該基準高さ位置から所定高さTcpだけ高い位置における分解能R1 を算出して、下記の(1)式を用いて単位高さ寸法当たりの分解能変化量を単位分解能Runi として算出し、下記の(2)式を用いて前記基準分解能Ro から前記単位分解能Runi と前記ワークの高さ寸法Hとの積算値を引き算することで、前記補正後の分解能Rhを求める、請求項2に記載のロボット制御システム。
Runi =(Ro -R1 )/Tcp …(1)
Rh =Ro -Runi ×H …(2) - 高さ寸法が既知のワークを作業エリアに供給する供給装置と、
前記作業エリアに供給されたワークに対して所定の作業を行うロボットと、
前記作業エリアに供給されたワークを所定の高さ位置から撮像する2次元のカメラと、
前記2次元のカメラで撮像した2次元の画像を処理して前記ワークの位置を当該画像の基準点を原点とする2次元座標系(以下「ビジョン座標系」という)の座標値で認識する画像処理部と、
前記画像処理部の画像処理で前記ワークの位置として認識した前記ビジョン座標系の座標値を前記ロボットの3次元座標系である世界座標系の座標値に変換する座標変換部と、
前記座標変換部で前記世界座標系の座標値に変換した前記ワークの位置に基づいて前記ロボットのアームの目標位置を前記世界座標系の座標値で設定して当該アームの位置を前記世界座標系の座標値で制御する制御部とを備え、
前記座標変換部は、前記2次元のカメラで撮像した画像内の前記ワークのサイズが当該ワークの高さ寸法及び前記作業エリアのワーク載置面の高さ位置に応じて変化することを考慮して、前記画像処理部の画像処理で前記ワークの位置として認識した前記ビジョン座標系の座標値を当該ワークの高さ寸法及び前記作業エリアのワーク載置面の高さ位置に応じて補正し、補正後のビジョン座標系の座標値を前記世界座標系の座標値に変換する、ロボット制御システム。 - 前記画像処理部は、前記ビジョン座標系で前記ワークの位置の座標値をピクセル単位で認識し、
前記座標変換部は、前記画像処理部の画像処理で前記ワークの位置として認識した前記ビジョン座標系の座標値を当該ワークの高さ寸法及び前記作業エリアのワーク載置面の高さ位置に応じて補正する際に、前記ビジョン座標系のピクセル単位の座標値を前記世界座標系の座標値と同じ長さの単位の座標値に変換する処理に用いる分解能(1ピクセル当たりの長さ)を前記ワークの高さ寸法及び前記作業エリアのワーク載置面の高さ位置に応じて補正し、補正後の分解能を用いて前記ビジョン座標系のピクセル単位の座標値を前記世界座標系の座標値と同じ長さの単位の座標値に変換する、請求項4に記載のロボット制御システム。 - 前記座標変換部は、前記2次元のカメラで前記作業エリア上のワークを撮像可能な高さ位置の範囲内で設定した基準高さ位置における分解能を基準分解能Ro として算出すると共に、当該基準高さ位置から所定高さTcpだけ高い位置における分解能R1 を算出して、下記の(3)式を用いて単位高さ寸法当たりの分解能変化量を単位分解能Runi として算出し、下記の(4)式を用いて前記基準高さ位置から前記作業エリアのワーク載置面の高さ位置までの高さ寸法ΔWDと前記ワークの高さ寸法Hとの和に前記単位分解能Runi を積算して求めた値を前記基準分解能Ro から引き算することで、前記補正後の分解能Rhを求める、請求項5に記載のロボット制御システム。
Runi =(Ro -R1 )/Tcp …(3)
Rh =Ro -Runi ×(H+ΔWD) …(4) - 前記2次元のカメラは、前記ロボットのアーム先端部に取り付けられ、
前記制御部は、前記作業エリアに供給されたワークを前記2次元のカメラで撮像する際に当該2次元のカメラの高さ位置が前記世界座標系の座標値で前記所定の高さ位置となるように前記ロボットのアームの位置を制御する、請求項1乃至6のいずれかに記載のロボット制御システム。 - 前記2次元のカメラは、前記世界座標系の座標値で前記所定の高さ位置となる場所に固定されている、請求項1乃至6のいずれかに記載のロボット制御システム。
- 前記画像処理部は、少なくとも前記ワークの高さ寸法を含む情報や画像処理パラメータをGUI(グラフィカル・ユーザー・インターフェース)上から登録可能に構成されている、請求項1乃至8のいずれかに記載のロボット制御システム。
- 前記画像処理部は、前記ワークの姿勢及び複数のワーク同士の重なりを認識する機能を有する、請求項1乃至9のいずれかに記載のロボット制御システム。
- 高さ寸法が既知のワークを一定の高さ位置の作業エリアに供給する供給装置と、
前記作業エリアに供給されたワークに対して所定の作業を行うロボットと、
前記作業エリアに供給されたワークを所定の高さ位置から撮像して2次元の画像を取得する2次元のカメラとを備え、
前記2次元のカメラで撮像した2次元の画像を処理して前記ワークの位置を当該画像の基準点を原点とする2次元座標系(以下「ビジョン座標系」という)の座標値で認識する画像処理工程と、
前記画像処理工程の画像処理で前記ワークの位置として認識した前記ビジョン座標系の座標値を前記ロボットの3次元座標系である世界座標系の座標値に変換する座標変換工程と、
前記座標変換工程で前記世界座標系の座標値に変換した前記ワークの位置に基づいて前記ロボットのアームの目標位置を前記世界座標系の座標値で設定して当該アームの位置を前記世界座標系の座標値で制御する制御工程とを含むロボット制御方法であって、
前記座標変換工程において、前記2次元のカメラで撮像した画像内の前記ワークのサイズが当該ワークの高さ寸法に応じて変化することを考慮して、前記画像処理工程の画像処理で前記ワークの位置として認識した前記ビジョン座標系の座標値を当該ワークの高さ寸法に応じて補正し、補正後のビジョン座標系の座標値を前記世界座標系の座標値に変換する、ロボット制御方法。 - 高さ寸法が既知のワークを作業エリアに供給する供給装置と、
前記作業エリアに供給されたワークに対して所定の作業を行うロボットと、
前記作業エリアに供給されたワークを所定の高さ位置から撮像して2次元の画像を取得する2次元のカメラとを備え、
前記2次元のカメラで撮像した2次元の画像を処理して前記ワークの位置を当該画像の基準点を原点とする2次元座標系(以下「ビジョン座標系」という)の座標値で認識する画像処理工程と、
前記画像処理工程の画像処理で前記ワークの位置として認識した前記ビジョン座標系の座標値を前記ロボットの3次元座標系である世界座標系の座標値に変換する座標変換工程と、
前記座標変換工程で前記世界座標系の座標値に変換した前記ワークの位置に基づいて前記ロボットのアームの目標位置を前記世界座標系の座標値で設定して当該アームの位置を前記世界座標系の座標値で制御する制御工程とを含むロボット制御方法であって、
前記座標変換工程において、前記2次元のカメラで撮像した画像内の前記ワークのサイズが当該ワークの高さ寸法及び前記作業エリアの高さ位置に応じて変化することを考慮して、前記画像処理工程の画像処理で前記ワークの位置として認識した前記ビジョン座標系の座標値を当該ワークの高さ寸法及び前記作業エリアの高さ位置に応じて補正し、補正後のビジョン座標系の座標値を前記世界座標系の座標値に変換する、ロボット制御方法。
Priority Applications (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2020558832A JP7057841B2 (ja) | 2018-12-11 | 2018-12-11 | ロボット制御システム及びロボット制御方法 |
| CN201880099483.1A CN113015604B (zh) | 2018-12-11 | 2018-12-11 | 机器人控制系统及机器人控制方法 |
| EP18943223.0A EP3895855B1 (en) | 2018-12-11 | 2018-12-11 | Robot control system and robot control method |
| PCT/JP2018/045428 WO2020121399A1 (ja) | 2018-12-11 | 2018-12-11 | ロボット制御システム及びロボット制御方法 |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/JP2018/045428 WO2020121399A1 (ja) | 2018-12-11 | 2018-12-11 | ロボット制御システム及びロボット制御方法 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2020121399A1 true WO2020121399A1 (ja) | 2020-06-18 |
Family
ID=71075975
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2018/045428 Ceased WO2020121399A1 (ja) | 2018-12-11 | 2018-12-11 | ロボット制御システム及びロボット制御方法 |
Country Status (4)
| Country | Link |
|---|---|
| EP (1) | EP3895855B1 (ja) |
| JP (1) | JP7057841B2 (ja) |
| CN (1) | CN113015604B (ja) |
| WO (1) | WO2020121399A1 (ja) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114119773A (zh) * | 2021-11-30 | 2022-03-01 | 马鞍山学院 | 一种用于工业机器人智能抓取检测的相机自动对焦方法 |
| CN114770461A (zh) * | 2022-04-14 | 2022-07-22 | 深圳技术大学 | 一种基于单目视觉的移动机器人及其自动抓取方法 |
| CN115194773A (zh) * | 2022-08-22 | 2022-10-18 | 苏州佳祺仕信息科技有限公司 | 一种视觉引导组装方法及装置 |
| WO2024209630A1 (ja) | 2023-04-06 | 2024-10-10 | 株式会社Fuji | 画像処理方法およびロボットシステム |
| JP7591938B2 (ja) | 2021-02-10 | 2024-11-29 | 株式会社キーエンス | 制御装置 |
| CN119304866A (zh) * | 2024-10-11 | 2025-01-14 | 大连中远海运海事工程技术有限公司 | 一种高压油泵拆装电动提升翻转机系统 |
| EP4640381A1 (en) | 2022-12-23 | 2025-10-29 | Denso Corporation | Robot control system |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102948945B1 (ko) * | 2023-05-30 | 2026-04-07 | 화천기공 주식회사 | 공작물의 측정 포인트 추출 방법 및 시스템 |
| CN116673965B (zh) * | 2023-07-21 | 2025-12-26 | 梅卡曼德(雄安)机器人科技股份有限公司 | 物体位姿的确定方法、装置、机器人及存储介质 |
| WO2025263899A1 (ko) * | 2024-06-21 | 2025-12-26 | 삼성전자 주식회사 | 로봇-비전 간 캘리브레이션을 위한 전자 장치 및 이를 이용한 캘리브레이션 방법 |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0788791A (ja) * | 1993-09-20 | 1995-04-04 | Mitsubishi Electric Corp | ロボット装置およびその周辺装置 |
| JPH11300670A (ja) * | 1998-04-21 | 1999-11-02 | Fanuc Ltd | 物品ピックアップ装置 |
| JP2000304509A (ja) * | 1999-04-21 | 2000-11-02 | Matsushita Electric Works Ltd | 物体特定方法及び装置 |
| JP2008183690A (ja) * | 2007-01-31 | 2008-08-14 | Nachi Fujikoshi Corp | ロボット制御装置及びロボット制御システム |
| JP2013233639A (ja) * | 2012-05-10 | 2013-11-21 | Hitachi Zosen Fukui Corp | ワークの位置検出方法及びそれを用いたワークの搬送方法 |
| JP2015182144A (ja) | 2014-03-20 | 2015-10-22 | キヤノン株式会社 | ロボットシステムおよびロボットシステムの校正方法 |
Family Cites Families (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090152785A1 (en) * | 2005-09-12 | 2009-06-18 | Kabushiki Kaisha Yaskawa Denki | Alignment apparatus and original point returning method of alignment apparatus, turning table, translational table, machine including alignment apparatus and machine control system |
| JP4309439B2 (ja) * | 2007-03-30 | 2009-08-05 | ファナック株式会社 | 対象物取出装置 |
| JP4565023B2 (ja) * | 2008-07-04 | 2010-10-20 | ファナック株式会社 | 物品取り出し装置 |
| US8452077B2 (en) * | 2010-02-17 | 2013-05-28 | Applied Materials, Inc. | Method for imaging workpiece surfaces at high robot transfer speeds with correction of motion-induced distortion |
| JP2011177845A (ja) * | 2010-03-02 | 2011-09-15 | Seiko Epson Corp | ロボットのキャリブレーション方法及びロボット用キャリブレーション装置 |
| JP5505138B2 (ja) * | 2010-07-05 | 2014-05-28 | 株式会社安川電機 | ロボット装置およびロボット装置による把持方法 |
| DE102012200220A1 (de) * | 2011-06-20 | 2012-12-20 | Semilev Gmbh | Verfahren zum Kalibrieren eines aktiv magnetgelagerten Roboters |
| JP6415026B2 (ja) * | 2013-06-28 | 2018-10-31 | キヤノン株式会社 | 干渉判定装置、干渉判定方法、コンピュータプログラム |
| JP6364856B2 (ja) * | 2014-03-25 | 2018-08-01 | セイコーエプソン株式会社 | ロボット |
| CN104786226A (zh) * | 2015-03-26 | 2015-07-22 | 华南理工大学 | 抓取在线工件的机器人位姿及运动轨迹定位系统与方法 |
| JP6126183B2 (ja) * | 2015-10-05 | 2017-05-10 | ファナック株式会社 | ターゲットマークを撮像するカメラを備えたロボットシステム |
| JP6250901B2 (ja) * | 2015-10-28 | 2017-12-20 | ファナック株式会社 | Cncとロボット制御装置が通信ネットワークを介して接続されたロボットシステム |
| JP2018012184A (ja) * | 2016-07-22 | 2018-01-25 | セイコーエプソン株式会社 | 制御装置、ロボットおよびロボットシステム |
| WO2018098395A1 (en) * | 2016-11-25 | 2018-05-31 | Glowforge Inc. | Improved engraving in a computer numerically controlled machine |
| CN106607907B (zh) * | 2016-12-23 | 2017-09-26 | 西安交通大学 | 一种移动视觉机器人及其测控方法 |
-
2018
- 2018-12-11 WO PCT/JP2018/045428 patent/WO2020121399A1/ja not_active Ceased
- 2018-12-11 JP JP2020558832A patent/JP7057841B2/ja active Active
- 2018-12-11 EP EP18943223.0A patent/EP3895855B1/en active Active
- 2018-12-11 CN CN201880099483.1A patent/CN113015604B/zh active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0788791A (ja) * | 1993-09-20 | 1995-04-04 | Mitsubishi Electric Corp | ロボット装置およびその周辺装置 |
| JPH11300670A (ja) * | 1998-04-21 | 1999-11-02 | Fanuc Ltd | 物品ピックアップ装置 |
| JP2000304509A (ja) * | 1999-04-21 | 2000-11-02 | Matsushita Electric Works Ltd | 物体特定方法及び装置 |
| JP2008183690A (ja) * | 2007-01-31 | 2008-08-14 | Nachi Fujikoshi Corp | ロボット制御装置及びロボット制御システム |
| JP2013233639A (ja) * | 2012-05-10 | 2013-11-21 | Hitachi Zosen Fukui Corp | ワークの位置検出方法及びそれを用いたワークの搬送方法 |
| JP2015182144A (ja) | 2014-03-20 | 2015-10-22 | キヤノン株式会社 | ロボットシステムおよびロボットシステムの校正方法 |
Non-Patent Citations (1)
| Title |
|---|
| See also references of EP3895855A4 |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7591938B2 (ja) | 2021-02-10 | 2024-11-29 | 株式会社キーエンス | 制御装置 |
| CN114119773A (zh) * | 2021-11-30 | 2022-03-01 | 马鞍山学院 | 一种用于工业机器人智能抓取检测的相机自动对焦方法 |
| CN114770461A (zh) * | 2022-04-14 | 2022-07-22 | 深圳技术大学 | 一种基于单目视觉的移动机器人及其自动抓取方法 |
| CN114770461B (zh) * | 2022-04-14 | 2023-12-01 | 深圳技术大学 | 一种基于单目视觉的移动机器人及其自动抓取方法 |
| CN115194773A (zh) * | 2022-08-22 | 2022-10-18 | 苏州佳祺仕信息科技有限公司 | 一种视觉引导组装方法及装置 |
| CN115194773B (zh) * | 2022-08-22 | 2024-01-05 | 苏州佳祺仕科技股份有限公司 | 一种视觉引导组装方法及装置 |
| EP4640381A1 (en) | 2022-12-23 | 2025-10-29 | Denso Corporation | Robot control system |
| WO2024209630A1 (ja) | 2023-04-06 | 2024-10-10 | 株式会社Fuji | 画像処理方法およびロボットシステム |
| EP4691706A1 (en) | 2023-04-06 | 2026-02-11 | Fuji Corporation | Image processing method and robot system |
| EP4691706A4 (en) * | 2023-04-06 | 2026-05-13 | Fuji Corp | IMAGE PROCESS AND ROBOT SYSTEM |
| CN119304866A (zh) * | 2024-10-11 | 2025-01-14 | 大连中远海运海事工程技术有限公司 | 一种高压油泵拆装电动提升翻转机系统 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113015604A (zh) | 2021-06-22 |
| EP3895855A1 (en) | 2021-10-20 |
| EP3895855A4 (en) | 2022-05-11 |
| CN113015604B (zh) | 2024-03-08 |
| EP3895855B1 (en) | 2026-04-15 |
| JPWO2020121399A1 (ja) | 2021-09-02 |
| JP7057841B2 (ja) | 2022-04-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7057841B2 (ja) | ロボット制御システム及びロボット制御方法 | |
| JP7153085B2 (ja) | ロボットキャリブレーションシステム及びロボットキャリブレーション方法 | |
| JP7281910B2 (ja) | ロボット制御システム | |
| JP2022028672A (ja) | ロボットモーション用のビジョンシステムの自動ハンドアイ校正のためのシステム及び方法 | |
| JP6228120B2 (ja) | 多関節型ロボットを備えた作業機および電気部品装着機 | |
| US9050728B2 (en) | Apparatus and method for measuring tool center point position of robot | |
| US20140114459A1 (en) | Robot system and processed product producing method | |
| JP6869159B2 (ja) | ロボットシステム | |
| JP2019113895A (ja) | ワークを撮像する視覚センサを備える撮像装置 | |
| CN108177150A (zh) | 基于视觉的电梯门板定位与抓取装置及方法 | |
| US12134195B2 (en) | Control device for robot, robot system, control method, and program | |
| JP2015136770A (ja) | 視覚センサのデータ作成システム及び検出シミュレーションシステム | |
| JP4289619B2 (ja) | 多関節ロボットのツール位置補正方法 | |
| US12459131B2 (en) | Picking system | |
| WO2022097535A1 (ja) | ティーチング操作を用いた設定方法 | |
| US20240269853A1 (en) | Calibration method, calibration device, and robotic system | |
| JP7481432B2 (ja) | ロボットの教示位置を修正するための装置、教示装置、ロボットシステム、教示位置修正方法、及びコンピュータプログラム | |
| JP2006082170A (ja) | キャリブレーション方法 | |
| JP7242856B2 (ja) | ロボット制御システム及びロボット制御方法 | |
| JP7510514B2 (ja) | オフセット値設定方法およびロボット制御装置 | |
| JP7145332B2 (ja) | ロボット制御システム及びロボット制御方法 | |
| WO2023032400A1 (ja) | 自動搬送装置、及びシステム | |
| JPH06206186A (ja) | 視覚センサ付き水平多関節型ロボットのハンドリング精度校正法 | |
| JP7576620B2 (ja) | カメラの位置ずれ測定方法 | |
| JP2017074637A (ja) | ツールセンターポイント推定方法、ツールセンターポイント推定装置 |
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: 18943223 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 2020558832 Country of ref document: JP Kind code of ref document: A |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| ENP | Entry into the national phase |
Ref document number: 2018943223 Country of ref document: EP Effective date: 20210712 |
|
| WWG | Wipo information: grant in national office |
Ref document number: 2018943223 Country of ref document: EP |