TWI778870B - Dynamic image positioning method and system for robot feeding - Google Patents

Dynamic image positioning method and system for robot feeding Download PDF

Info

Publication number
TWI778870B
TWI778870B TW110143433A TW110143433A TWI778870B TW I778870 B TWI778870 B TW I778870B TW 110143433 A TW110143433 A TW 110143433A TW 110143433 A TW110143433 A TW 110143433A TW I778870 B TWI778870 B TW I778870B
Authority
TW
Taiwan
Prior art keywords
tested
deviation value
standard
image
processed
Prior art date
Application number
TW110143433A
Other languages
Chinese (zh)
Other versions
TW202317337A (en
Inventor
楊崢嶸
劉浩東
高志鵬
Original Assignee
大陸商環旭電子股份有限公司
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 大陸商環旭電子股份有限公司 filed Critical 大陸商環旭電子股份有限公司
Application granted granted Critical
Publication of TWI778870B publication Critical patent/TWI778870B/en
Publication of TW202317337A publication Critical patent/TW202317337A/en

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/16—Programme controls
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J15/00—Gripping heads and other end effectors
    • B25J15/06—Gripping heads and other end effectors with vacuum or magnetic holding means
    • B25J15/0616—Gripping heads and other end effectors with vacuum or magnetic holding means with vacuum
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/16—Programme controls
    • B25J9/1694—Programme 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

Abstract

本發明提供了一種用於機器人放料的動態影像定位方法及系統，包括在取料工位和放料工位之間往復運動的機械臂，及設置在取料工位和放料工位元之間的攝像裝置。動態影像定位方法包括步驟：控制機械臂的取料端從取料工位吸取待測物料，並向放料工位移動；在機械臂的取料端移動至攝像裝置視野範圍內時，控制攝像裝置進行拍照，獲得待處理圖像；識別待處理圖像上待測物料的邊緣線，進而計算待測物料的定位偏差值；機械臂的取料端運動至放料工位的正上方，根據定位偏差值，調整機械臂的姿態進行放料。The invention provides a dynamic image positioning method and system for robot unloading, including a mechanical arm reciprocating between a reclaiming station and a discharging station, and a unit arranged at the reclaiming station and the discharging station between the cameras. The dynamic image positioning method includes the steps of: controlling the reclaiming end of the mechanical arm to absorb the material to be tested from the reclaiming station and moving to the discharging station; when the reclaiming end of the mechanical arm moves into the field of view of the camera device, control the camera The device takes pictures to obtain the image to be processed; recognizes the edge line of the material to be tested on the image to be processed, and then calculates the positioning deviation value of the material to be tested; Positioning deviation value, adjust the posture of the robot arm to discharge.

Description

用於機器人放料的動態影像定位方法及系統Dynamic image positioning method and system for robot feeding

本發明關於定位運輸技術領域，尤其是指一種用於機器人放料的動態影像定位方法及系統。 The present invention relates to the technical field of positioning and transportation, in particular to a dynamic image positioning method and system for robot feeding.

近年來，隨著電子產品需求量的增長，生產電子產品的自動化設備投入越來越普及。 In recent years, with the increase in the demand for electronic products, the investment in automation equipment for the production of electronic products has become more and more popular.

針對機器人上下料，當前技術是待測物料抓取至擺放的過程，通過靜態取像定位方式，即機器人停在相機上方固定位置，機器人停穩再整定一定時間後相機取像，之後根據圖像計算物料與目標位的定位偏差值，機器人再啟動去目標位，最終擺放時加上定位偏差值，從而準確擺放物料。該方式的缺點是取像時待測物需要固定不動，即手臂在取像的時間段內完全停止不動，效率沒有最大化，且取像機會只有一次，如出現圖像模糊等異常狀況時，無法根據圖像計算出定位偏差值，機器人需放棄物料擺放，造成機器人測試效率不高的問題。 For robot loading and unloading, the current technology is the process of grasping and placing the material to be tested. The static image positioning method is used, that is, the robot stops at a fixed position above the camera, the robot stops steadily and then adjusts for a certain period of time. Like calculating the positioning deviation value between the material and the target position, the robot starts to go to the target position again, and the positioning deviation value is added to the final placement, so as to accurately place the material. The disadvantage of this method is that the object to be measured needs to be fixed during the image acquisition, that is, the arm completely stops during the image acquisition time period, the efficiency is not maximized, and the image acquisition opportunity is only once, such as abnormal conditions such as image blurring, The positioning deviation value cannot be calculated according to the image, and the robot needs to abandon the material placement, resulting in the problem of low robot testing efficiency.

一種當前技術是機器人與相機間使用觸發式感測器來完成動作的同步性，即機器人經過相機前的感測器，感測器感應到機器人並觸發拍照。感測器與實際拍照位置的距離需要經過反復測試，以保證感測器觸發的拍照信號能在機器人剛好走到相機上方的固定位置時讓相機拍照。這個方式的缺點是 需要多一個感測器的硬體成本，以及付出較多的時間反復測試實際拍照位置的距離。因此，需要一種機器人不停止運動，也不需要反復測試實際拍照位置，效率更高、成本更低的機器人放料定位方法。 One current technology is the use of trigger sensors between the robot and the camera to complete the synchronization of actions, that is, the robot passes the sensor in front of the camera, and the sensor senses the robot and triggers a photo. The distance between the sensor and the actual photographing position needs to be repeatedly tested to ensure that the photographing signal triggered by the sensor can make the camera take a picture when the robot just walks to the fixed position above the camera. The disadvantage of this method is that The hardware cost of one more sensor is required, and more time is spent to repeatedly test the distance of the actual photographing position. Therefore, there is a need for a robot feeding positioning method with higher efficiency and lower cost that does not stop the movement of the robot and does not need to repeatedly test the actual photographing position.

本發明的目的是提供一種用於機器人放料的動態影像定位方法及系統，解決現有技術中放料定位時，機器人需要停止運動，或需要增加成本並需要反復測試實際拍照位置的問題。 The purpose of the present invention is to provide a dynamic image positioning method and system for robot feeding, which solves the problems in the prior art that when feeding and positioning, the robot needs to stop moving, or needs to increase the cost and repeatedly test the actual photographing position.

本發明提供的技術方案如下： The technical scheme provided by the present invention is as follows:

本發明提供一種用於機器人放料的動態影像定位方法，包括在一取料工位和一放料工位之間往復運動的一機械臂，以及設置在該取料工位和該放料工位之間的一攝像裝置。動態影像定位方法包括步驟：控制該機械臂的一取料端從該取料工位吸取一待測物料，並向該放料工位移動；在該機械臂的取料端移動至該攝像裝置視野範圍內時，控制該攝像裝置進行拍照，獲得一待處理圖像；識別該待處理圖像上該待測物料的一邊緣線，進而計算該待測物料的定位偏差值；控制該機械臂的取料端運動至該放料工位的正上方，並根據該定位偏差值，調整該機械臂的姿態進行放料。 The invention provides a dynamic image positioning method for robot unloading, comprising a mechanical arm that reciprocates between a reclaiming station and a discharging station, and a mechanical arm arranged at the reclaiming station and the unloading station A camera device between the bits. The dynamic image positioning method includes the steps of: controlling a reclaiming end of the robotic arm to pick up a material to be tested from the reclaiming station and moving to the discharging station; moving the reclaiming end of the robotic arm to the camera device When it is within the field of view, control the camera to take pictures to obtain an image to be processed; identify an edge line of the material to be tested on the image to be processed, and then calculate the positioning deviation value of the material to be tested; control the robotic arm The reclaiming end of the robot moves to the top of the discharging station, and according to the positioning deviation value, the posture of the robotic arm is adjusted to discharge the material.

通過將攝像裝置設在取料工位和放料工位之間，使得當機器人控制機械臂的取料端從取料工位吸取待測物料，並移動至攝像裝置視野範圍內 時，能夠直接控制攝像裝置進行拍照，獲得待處理圖像，再識別待處理圖像上待測物料的邊緣線，便能夠計算出待測物料的定位偏差值，機器人根據定位偏差值調整機械臂的姿態，便能夠實現精準的放料。由於攝像裝置在拍照時，是直接由機器人通過軟體通信方式給出觸發信號至攝像裝置，不需要感測器觸發，因此不需要機器人停止運動，也不需要反復測試實際攝像裝置的拍照位置，使得機器人的定位放料效率更高、成本更低。 By arranging the camera device between the reclaiming station and the discharging station, when the robot controls the reclaiming end of the robotic arm to pick up the material to be tested from the reclaiming station, and move it into the field of view of the camera device When the camera is detected, it can directly control the camera to take pictures, obtain the image to be processed, and then identify the edge line of the material to be tested on the image to be processed, then the positioning deviation value of the material to be tested can be calculated, and the robot adjusts the robotic arm according to the positioning deviation value. The posture can achieve accurate feeding. When the camera takes a picture, the robot directly sends a trigger signal to the camera through software communication, without the need for sensor triggering, so the robot does not need to stop moving, and there is no need to repeatedly test the shooting position of the actual camera, so that The positioning and feeding efficiency of the robot is higher and the cost is lower.

進一步地，該機械臂的取料端設置有至少一對吸盤，每對吸盤中一個用於吸取該待測物料，另一個空置。計算該待測物料的定位偏差值，具體包括：識別該待處理圖像上該待測物料的邊緣線，以及對應的空置吸盤的邊緣線；根據該待測物料的邊緣線和該空置吸盤的邊緣線計算該待測物料的定位偏差值。 Further, at least one pair of suction cups is provided at the material taking end of the mechanical arm, one of each pair of suction cups is used for sucking the material to be tested, and the other is vacant. Calculating the positioning deviation value of the material to be tested includes: identifying the edge line of the material to be tested on the image to be processed, and the corresponding edge line of the empty suction cup; according to the edge line of the material to be tested and the empty suction cup The edge line calculates the positioning deviation value of the material to be tested.

具體地，在設置參考位置時，為了保證定位的精準，可以在機械臂的取料端設置至少一對吸盤，每對吸盤中一個用於吸取待測物料，另一個空置。由於兩個吸盤的相對位置固定，使得在處理待處理圖像時，通過識別待處理圖像上待測物料的邊緣線，以及對應的空置吸盤的邊緣線，便能夠計算待測物料的定位偏差值。 Specifically, when setting the reference position, in order to ensure accurate positioning, at least a pair of suction cups can be set at the material taking end of the robotic arm, one of each pair of suction cups is used to suck the material to be tested, and the other is vacant. Since the relative positions of the two suction cups are fixed, when processing the image to be processed, the positioning deviation of the material to be tested can be calculated by identifying the edge line of the material to be tested on the image to be processed and the corresponding edge line of the empty suction cup. value.

進一步地，該吸盤上均設置有特徵點。計算該待測物料的定位偏差值，具體包括：識別該待處理圖像上該空置吸盤的特徵點，以及該待處理圖像上該待測物料的邊緣線； 獲取一標準待測物料的一標準中心點與一標準吸盤的一標準特徵點的一第一偏差值；根據該待測物料的邊緣線，計算該待測物料的中心點；計算該待測物料的中心點與該空置吸盤的特徵點的一第二偏差值；根據該第一偏差值和該第二偏差值計算該待測物料的該定位偏差值。 Further, feature points are provided on the suction cups. Calculate the positioning deviation value of the material to be tested, specifically including: identifying the feature point of the empty suction cup on the image to be processed, and the edge line of the material to be tested on the image to be processed; Obtain a first deviation value between a standard center point of a standard material to be tested and a standard feature point of a standard suction cup; calculate the center point of the material to be tested according to the edge line of the material to be tested; calculate the material to be tested A second deviation value between the center point of the empty suction cup and the characteristic point of the empty suction cup; the positioning deviation value of the material to be tested is calculated according to the first deviation value and the second deviation value.

通過在吸盤上設置特徵點，使得在處理待處理圖像時，能夠識別待處理圖像上空置吸盤的特徵點，以及待處理圖像上待測物料的邊緣線，再根據待測物料的邊緣線，能夠計算待測物料的中心點；同時，通過獲取標準待測物料的標準中心點與標準吸盤的標準特徵點的第一偏差值，以及待測物料的中心點與空置吸盤的特徵點的第二偏差值，能夠計算待測物料的定位偏差值。 By setting the feature points on the suction cup, when processing the image to be processed, the feature points of the empty suction cup on the image to be processed and the edge line of the material to be tested on the image to be processed can be identified, and then according to the edge of the material to be tested The center point of the material to be tested can be calculated; at the same time, by obtaining the first deviation value between the standard center point of the standard material to be tested and the standard feature point of the standard suction cup, and the difference between the center point of the material to be tested and the feature point of the empty suction cup The second deviation value can calculate the positioning deviation value of the material to be tested.

進一步地，該定位偏差值包括一偏移量和一偏移角度。 Further, the positioning deviation value includes an offset amount and an offset angle.

進一步地，在平面坐標系內，該偏移量(X，Y)的計算公式為：

Figure 110143433-A0305-02-0005-1
偏移角度θ的計算公式為：
Figure 110143433-A0305-02-0005-2
 其中，該標準待測物料對應的該標準中心點為(X1,Y1)，對應的該標準吸盤的該標準特徵點為(Xb,Yb)，對應的偏移角度為θ0，X 0=X b -X 1，Y 0=Y b -Y 1，θ0=arctan｜-Y 0/X 0｜；該待測物料的中心點為(X'，Y')，對應的該空置吸盤的特徵點為(
Figure 110143433-A0305-02-0005-7
，
Figure 110143433-A0305-02-0005-8
)，對應的偏移角度為
Figure 110143433-A0305-02-0005-3
，
Figure 110143433-A0305-02-0005-4
，
Figure 110143433-A0305-02-0005-5
，
Figure 110143433-A0305-02-0005-6
。 Further, in the plane coordinate system, the calculation formula of the offset (X, Y) is:
Figure 110143433-A0305-02-0005-1
 The formula for calculating the offset angle θ is:
Figure 110143433-A0305-02-0005-2
 Wherein, the standard center point corresponding to the standard material to be tested is (X 1 , Y 1 ), the corresponding standard feature point of the standard suction cup is (X b , Y b ), and the corresponding offset angle is θ 0 , X 0 = X b - X 1 , Y 0 = Y b - Y 1 , θ 0 = arctan |- Y 0 / X 0 |; the center point of the material to be tested is (X', Y') , corresponding to the The characteristic points of the vacant suction cups are (
Figure 110143433-A0305-02-0005-7
,
Figure 110143433-A0305-02-0005-8
 ), the corresponding offset angle is
Figure 110143433-A0305-02-0005-3
,
Figure 110143433-A0305-02-0005-4
,
Figure 110143433-A0305-02-0005-5
,
Figure 110143433-A0305-02-0005-6
.

進一步地，識別該待處理圖像上該待測物料的邊緣線之前，還包括： Further, before identifying the edge line of the material to be tested on the image to be processed, it also includes:

預先錄入該標準吸盤的該標準特徵點的座標，以及該標準待測物料的該標準中心點的座標，該標準待測物料的標準中心點和該標準吸盤的標準特徵點分別為該機械臂的取料端上預設於該放料工位正上方時的物料中心點和該空置吸盤的標準特徵點。 The coordinates of the standard feature point of the standard suction cup and the coordinates of the standard center point of the standard material to be tested are pre-entered. The standard center point of the standard material to be tested and the standard feature point of the standard suction cup are the The material center point and the standard feature point of the empty suction cup are preset on the reclaiming end when it is directly above the discharging station.

進一步地，機器人放料的動態影像定位方法還包括：在該機械臂的取料端移動至該攝像裝置視野範圍內時，控制該攝像裝置進行拍照，獲得若干個該待處理圖像；分別根據各個該待處理圖像計算該待測物料的若干個該定位偏差值；及根據各個該定位偏差值的平均值，調整該機械臂的姿態。 Further, the dynamic image positioning method for robot unloading also includes: when the reclaiming end of the robotic arm moves within the field of view of the camera, controlling the camera to take pictures to obtain several images to be processed; A plurality of the positioning deviation values of the material to be tested are calculated for each of the to-be-processed images; and the posture of the robotic arm is adjusted according to the average value of each of the positioning deviation values.

另外，本發明還提供一種用於機器人放料的動態影像定位系統，包括：機器人，具有在一取料工位和一放料工位之間往復運動的一機械臂，且該機器人控制該機械臂的取料端從該取料工位吸取一待測物料，並向該放料工位移動；攝像裝置，設置在該取料工位和該放料工位之間，該機器人在該機械臂的取料端移動至該攝像裝置視野範圍內時，控制該攝像裝置進行拍照，獲得一待處理圖像；影像處理端，用於識別該待處理圖像上該待測物料的邊緣線，進而計算該待測物料的一定位偏差值；及 當該機械臂的取料端運動至該放料工位的正上方時，該機器人根據該定位偏差值，調整該機械臂的姿態進行放料。 In addition, the present invention also provides a dynamic image positioning system for robot unloading, comprising: a robot having a mechanical arm that reciprocates between a reclaiming station and a feeding station, and the robot controls the machine The reclaiming end of the arm sucks a material to be tested from the reclaiming station and moves to the discharging station; the camera device is arranged between the reclaiming station and the discharging station, and the robot is in the machine When the reclaiming end of the arm moves into the field of view of the camera device, it controls the camera device to take pictures to obtain an image to be processed; the image processing end is used to identify the edge line of the material to be tested on the image to be processed, and then calculate a positioning deviation value of the material to be tested; and When the reclaiming end of the manipulator moves to just above the discharging station, the robot adjusts the posture of the manipulator according to the positioning deviation value to discharge the manipulator.

通過將攝像裝置設在取料工位和放料工位之間，使得當機器人控制機械臂的取料端從取料工位吸取待測物料，並移動至攝像裝置視野範圍內時，能夠直接控制攝像裝置進行拍照，獲得待處理圖像，再識別待處理圖像上待測物料的邊緣線，便能夠計算出待測物料的定位偏差值，機器人根據定位偏差值調整機械臂的姿態，便能夠實現精準的放料。由於攝像裝置在拍照時，是直接由機器人通過軟體通信方式給出觸發信號至攝像裝置，不需要感測器觸發，因此不需要機器人停止運動，也不需要反復測試實際攝像裝置的拍照位置，使得機器人的定位放料效率更高、成本更低。 By arranging the camera device between the reclaiming station and the discharging station, when the robot controls the reclaiming end of the manipulator to pick up the material to be tested from the reclaiming station and move it into the field of view of the camera device, it can directly Control the camera device to take pictures, obtain the image to be processed, and then identify the edge line of the material to be tested on the image to be processed, and then the positioning deviation value of the material to be tested can be calculated. Accurate feeding can be achieved. When the camera takes a picture, the robot directly sends a trigger signal to the camera through software communication, without the need for sensor triggering, so the robot does not need to stop moving, and there is no need to repeatedly test the shooting position of the actual camera, so that The positioning and feeding efficiency of the robot is higher and the cost is lower.

進一步地，該機械臂的取料端設置有至少一對吸盤，每對吸盤中一個用於吸取該待測物料，另一個空置。該影像處理端識別該待處理圖像上該待測物料的邊緣線，以及對應的空置吸盤的邊緣線，並根據該待測物料的邊緣線和該空置吸盤的邊緣線計算該待測物料的定位偏差值。 Further, at least one pair of suction cups is provided at the material taking end of the mechanical arm, one of each pair of suction cups is used for sucking the material to be tested, and the other is vacant. The image processing end identifies the edge line of the material to be tested and the corresponding edge line of the empty suction cup on the image to be processed, and calculates the edge line of the material to be tested according to the edge line of the material to be tested and the edge line of the empty suction cup. Positioning offset value.

具體地，在設置參考位置時，為了保證定位的精準，可以在機械臂的取料端設置至少一對吸盤，每對吸盤中一個用於吸取待測物料，另一個空置，由於兩個吸盤的相對位置固定，使得在處理待處理圖像時，通過識別待處理圖像上待測物料的邊緣線，以及對應的空置吸盤的邊緣線，便能夠計算待測物料的定位偏差值。 Specifically, when setting the reference position, in order to ensure the accuracy of positioning, at least one pair of suction cups can be set at the material taking end of the robotic arm, one of each pair of suction cups is used to absorb the material to be tested, and the other is vacant. The relative position is fixed, so that when processing the image to be processed, by identifying the edge line of the material to be tested on the image to be processed and the corresponding edge line of the empty suction cup, the positioning deviation value of the material to be tested can be calculated.

進一步地，該吸盤上均設置有特徵點。該影像處理端識別該待處理圖像上該空置吸盤的特徵點，以及該待處理圖像上該待測物料的邊緣線，並根據該待測物料的邊緣線，計算該待測物料的中心點。該影像處理端獲取標準 待測物料的標準中心點與標準吸盤的標準特徵點的第一偏差值，以及該待測物料的中心點與該空置吸盤的特徵點的第二偏差值，並根據該第一偏差值和該第二偏差值計算該待測物料的該定位偏差值。 Further, feature points are provided on the suction cups. The image processing end identifies the feature point of the empty suction cup on the image to be processed and the edge line of the material to be tested on the image to be processed, and calculates the center of the material to be tested according to the edge line of the material to be tested point. The image processing terminal obtains the standard The first deviation value between the standard center point of the material to be tested and the standard feature point of the standard suction cup, and the second deviation value between the center point of the material to be tested and the feature point of the empty suction cup, and based on the first deviation value and the The second deviation value calculates the positioning deviation value of the material to be tested.

通過在吸盤上設置特徵點，使得在處理待處理圖像時，能夠識別待處理圖像上空置吸盤的特徵點，以及待處理圖像上待測物料的邊緣線，再根據待測物料的邊緣線，能夠計算待測物料的中心點；同時，通過獲取標準待測物料的標準中心點與標準吸盤的標準特徵點的第一偏差值，以及待測物料的中心點與空置吸盤的特徵點的第二偏差值，能夠計算待測物料的定位偏差值。 By setting the feature points on the suction cup, when processing the image to be processed, the feature points of the empty suction cup on the image to be processed and the edge line of the material to be tested on the image to be processed can be identified, and then according to the edge of the material to be tested The center point of the material to be tested can be calculated; at the same time, by obtaining the first deviation value between the standard center point of the standard material to be tested and the standard feature point of the standard suction cup, and the difference between the center point of the material to be tested and the feature point of the empty suction cup The second deviation value can calculate the positioning deviation value of the material to be tested.

根據本發明提供的一種用於機器人放料的動態影像定位方法及系統，通過將攝像裝置設在取料工位和放料工位之間，使得當機器人控制機械臂的取料端從取料工位吸取待測物料，並移動至攝像裝置視野範圍內時，能夠直接控制攝像裝置進行拍照，獲得待處理圖像，再識別待處理圖像上待測物料的邊緣線，便能夠計算出待測物料的定位偏差值，機器人根據定位偏差值調整機械臂的姿態，便能夠實現精準的放料。由於攝像裝置在拍照時，是直接由機器人通過軟體通信方式給出觸發信號至攝像裝置，不需要感測器觸發，因此不需要機器人停止運動，也不需要反復測試實際攝像裝置的拍照位置，使得機器人的定位放料效率更高、成本更低。 According to a dynamic image positioning method and system for robot unloading provided by the present invention, by setting the camera device between the reclaiming station and the unloading station, when the robot controls the reclaiming end of the manipulator arm from the reclaiming When the station picks up the material to be tested and moves it into the field of view of the camera device, it can directly control the camera device to take pictures, obtain the image to be processed, and then identify the edge line of the material to be tested on the image to be processed, and then calculate the The positioning deviation value of the material is measured, and the robot adjusts the posture of the mechanical arm according to the positioning deviation value, so as to realize accurate feeding. When the camera takes a picture, the robot directly sends a trigger signal to the camera through software communication, without the need for sensor triggering, so the robot does not need to stop moving, and there is no need to repeatedly test the shooting position of the actual camera, so that The positioning and feeding efficiency of the robot is higher and the cost is lower.

S1-S4:步驟 S1-S4: Steps

S31-S37:步驟 S31-S37: Steps

1:吸盤 1: suction cup

2:待測物料 2: Materials to be tested

3:特徵點 3: Feature points

4:機器人 4: Robots

5:攝像裝置 5: Camera device

6:影像處理端 6: Image processing terminal

下面將以明確易懂的方式，結合圖式說明優選實施方式，對本方案的上述特性、技術特徵、優點及其實現方式予以進一步說明。 The preferred embodiments will be described below in a clear and easy-to-understand manner with reference to the drawings, and the above-mentioned characteristics, technical features, advantages and implementation manners of the present solution will be further described.

圖1是本發明實施例的整體流程示意圖； 圖2是本發明實施例的機械臂取料端結構示意圖；圖3是本發明實施例的機械臂取料端仰視結構示意圖；圖4是本發明實施例的一個流程示意圖；圖5是本發明實施例的另一個流程示意圖；及圖6是本發明實施例的系統結構示意圖。 Fig. 1 is the overall flow schematic diagram of the embodiment of the present invention; Fig. 2 is a schematic structural diagram of a reclaiming end of a manipulator according to an embodiment of the present invention; Fig. 3 is a schematic diagram of a bottom view of the reclaiming end of a manipulator according to an embodiment of the present invention; Fig. 4 is a schematic flow diagram of an embodiment of the present invention; Another schematic flowchart of the embodiment; and FIG. 6 is a schematic diagram of the system structure of the embodiment of the present invention.

為了更清楚地說明本發明實施例或現有技術中的技術方案，下面將對照圖式說明本發明的具體實施方式。顯而易見地，下面描述中的圖式僅是本發明的一些實施例，對於本領域普通技術人員來講，在不付出創造性勞動的前提下，還可以根據這些圖式獲得其他的圖式，並獲得其他的實施方式。 In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, specific embodiments of the present invention will be described below with reference to the drawings. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained from these drawings without creative work, and obtain other implementations.

為使圖面簡潔，各圖中只示意性地表示出了與本發明相關的部分，它們並不代表其作為產品的實際結構。另外，以使圖面簡潔便於理解，在有些圖中具有相同結構或功能的部件，僅示意性地繪示了其中的一個，或僅標出了其中的一個。在本文中，“一個”不僅表示“僅此一個”，也可以表示“多於一個”的情形。 In order to keep the drawings concise, the drawings only schematically show the parts related to the present invention, and they do not represent its actual structure as a product. In addition, in order to make the drawings concise and easy to understand, in some drawings, only one of the components having the same structure or function is schematically shown, or only one of them is marked. As used herein, "one" not only means "only one", but also "more than one".

實施例1 Example 1

本發明的一個實施例，如圖1所示，本發明提供一種用於機器人放料的動態影像定位方法，包括在一取料工位和一放料工位之間往復運動的一機械臂，以及設置在取料工位和放料工位元之間的一攝像裝置。機械臂為多關節機械手臂，且由機器人控制，用於實現物料的抓取、運輸和放置。較佳地，攝像裝置可設置在靠近放料工位的位置。 One embodiment of the present invention, as shown in FIG. 1, the present invention provides a dynamic image positioning method for robot unloading, including a robotic arm that reciprocates between a reclaiming station and a feeding station, and a camera device arranged between the reclaiming station and the discharging station. The robotic arm is a multi-joint robotic arm and is controlled by a robot for grasping, transporting and placing materials. Preferably, the camera device can be arranged near the discharge station.

該方案包括步驟： The program includes steps:

S1：控制機械臂的取料端從取料工位吸取待測物料，並向放料工位移動。 S1: Control the reclaiming end of the robotic arm to pick up the material to be tested from the reclaiming station and move to the discharging station.

具體地，機械臂的取料端在轉移物料時，可以採用吸盤吸附的方式，不會使物料位置偏差較大，在其他實施例中，還可以抓取等方式。另外，本方案在轉移物料時，機械臂中間不會停止，也不會減速，以保證工作效率。 Specifically, when the material transfer end of the robotic arm transfers the material, the suction cup can be used to absorb the material, which will not cause a large deviation of the material position. In other embodiments, it can also be grasped. In addition, when transferring materials in this solution, the robot arm will not stop or slow down in the middle to ensure work efficiency.

S2：在機械臂的取料端移動至攝像裝置視野範圍內時，控制攝像裝置進行拍照，獲得待處理圖像。 S2: When the reclaiming end of the robotic arm moves into the field of view of the camera device, the camera device is controlled to take pictures to obtain an image to be processed.

具體地，當機械臂的取料端移動至攝像裝置視野範圍內時，由機器人通過軟體通信方式給出觸發信號至攝像裝置，使攝像裝置開始拍照。攝像裝置可直接獲取到機械臂取料端的俯視圖。有別於現有技術中常用的感測器觸發的方式，該方式能夠使攝像裝置提前準備拍照，從而不需要機械臂停止或減速。攝像裝置可以為工業相機等，為保證攝像裝置在機械臂的連續移動中獲取到清晰的待處理圖像，攝像裝置可為高幀速全域快門相機。 Specifically, when the reclaiming end of the robotic arm moves into the field of view of the camera device, the robot sends a trigger signal to the camera device through software communication, so that the camera device starts to take pictures. The camera device can directly obtain the top view of the reclaiming end of the robotic arm. Different from the sensor-triggered method commonly used in the prior art, this method enables the camera device to prepare for taking pictures in advance, so that the robot arm does not need to stop or decelerate. The camera device may be an industrial camera, etc. In order to ensure that the camera device obtains clear images to be processed during the continuous movement of the robotic arm, the camera device may be a high frame rate global shutter camera.

S3：識別待處理圖像上待測物料的邊緣線，進而計算待測物料的定位偏差值。 S3: Identify the edge line of the material to be tested on the image to be processed, and then calculate the positioning deviation value of the material to be tested.

在獲取待處理圖像後，通過圖像分析，能夠識別出處理圖像上待測物料的邊緣線，從而計算出待測物料的定位偏差值。 After acquiring the image to be processed, through image analysis, the edge line of the material to be tested on the processed image can be identified, thereby calculating the positioning deviation value of the material to be tested.

S4：控制機械臂的取料端運動至放料工位的正上方，並根據定位偏差值，調整機械臂的姿態。 S4: Control the reclaiming end of the robotic arm to move directly above the unloading station, and adjust the posture of the robotic arm according to the positioning deviation value.

具體地，在計算出待測物料的定位偏差值後，便能夠調整機械臂的姿態，使得待測物料的位置回到標準位置，從而實現規範放料，便於待測物料之後的運輸、測試等。 Specifically, after calculating the positioning deviation value of the material to be tested, the posture of the robotic arm can be adjusted so that the position of the material to be tested returns to the standard position, so as to realize standardized feeding and facilitate the transportation and testing of the material to be tested afterward. .

通過將攝像裝置設在取料工位和放料工位之間，使得當機器人控制機械臂的取料端從取料工位吸取待測物料，並移動至攝像裝置視野範圍內時，能夠直接控制攝像裝置進行拍照，獲得待處理圖像，再識別待處理圖像上待測物料的邊緣線，便能夠計算出待測物料的定位偏差值，機器人根據定位偏差值調整機械臂的姿態，便能夠實現精準的放料。由於攝像裝置在拍照時，是直接由機器人通過軟體通信方式給出觸發信號至攝像裝置，不需要感測器觸發，因此不需要機器人停止運動，也不需要反復測試實際攝像裝置的拍照位置，使得機器人的定位放料效率更高、成本更低。 By arranging the camera device between the reclaiming station and the discharging station, when the robot controls the reclaiming end of the manipulator to pick up the material to be tested from the reclaiming station and move it into the field of view of the camera device, it can directly Control the camera device to take pictures, obtain the image to be processed, and then identify the edge line of the material to be tested on the image to be processed, and then the positioning deviation value of the material to be tested can be calculated. Accurate feeding can be achieved. When the camera takes a picture, the robot directly sends a trigger signal to the camera through software communication, without the need for sensor triggering, so the robot does not need to stop moving, and there is no need to repeatedly test the shooting position of the actual camera, so that The positioning and feeding efficiency of the robot is higher and the cost is lower.

實施例2 Example 2

本發明的一個實施例，如圖2和圖3所示，在實施例1的基礎上，機械臂的取料端設置有至少一對吸盤1，每對吸盤1中一個用於吸取待測物料2，另一個空置。 In an embodiment of the present invention, as shown in Figures 2 and 3, on the basis of Embodiment 1, at least one pair of suction cups 1 is provided at the material taking end of the robotic arm, one of each pair of suction cups 1 is used to suck the material to be tested 2, the other is vacant.

具體地，在本方案中，可以採用吸盤吸附的方式轉移物料，另外，為了便於偏差定位，可以將吸盤1設置為至少一對，每對吸盤1中的一個用於吸取待測物料2，另一個空置，兩個吸盤相對位置固定，從而可以以空置吸盤為參考，對待測物料的偏差程度進行計算。 Specifically, in this solution, the material can be transferred by means of suction cups. In addition, in order to facilitate deviation positioning, at least one pair of suction cups 1 can be set, one of each pair of suction cups 1 is used to absorb the material to be tested 2, and the other is used to absorb the material to be tested. One is vacant, and the relative positions of the two suction cups are fixed, so that the deviation of the material to be measured can be calculated with the vacant suction cup as a reference.

如圖4所示，計算待測物料的定位偏差值，具體包括： As shown in Figure 4, calculate the positioning deviation value of the material to be tested, including:

S31：識別待處理圖像上待測物料的邊緣線，以及對應的空置吸盤的邊緣線。 S31: Identify the edge line of the material to be tested on the image to be processed, and the edge line of the corresponding empty suction cup.

S32：根據待測物料的邊緣線和空置吸盤的邊緣線計算待測物料的定位偏差值。 S32: Calculate the positioning deviation value of the material to be tested according to the edge line of the material to be tested and the edge line of the empty suction cup.

具體地，在設置參考位置時，為了保證定位的精準，可以在機械臂的取料端設置至少一對吸盤1，每對吸盤1中一個用於吸取待測物料，另一個空置，由於兩個吸盤1的相對位置固定，使得在處理待處理圖像時，通過識別待處理圖像上待測物料2的邊緣線，以及對應的空置吸盤的邊緣線，便能夠計算待測物料的定位偏差值。 Specifically, when setting the reference position, in order to ensure the accuracy of positioning, at least one pair of suction cups 1 can be set at the material taking end of the robotic arm, one of each pair of suction cups 1 is used to suck the material to be tested, and the other is vacant. The relative position of the suction cup 1 is fixed, so that when processing the image to be processed, by identifying the edge line of the material to be tested 2 on the image to be processed and the corresponding edge line of the empty suction cup, the positioning deviation value of the material to be tested can be calculated. .

較佳地，吸盤1上均設置有特徵點3。 Preferably, the suction cups 1 are all provided with feature points 3 .

如圖5所示，計算待測物料的定位偏差值，具體包括： As shown in Figure 5, calculate the positioning deviation value of the material to be tested, including:

S33：識別待處理圖像上空置吸盤的特徵點，以及待處理圖像上待測物料的邊緣線。 S33: Identify the feature points of the empty suction cups on the image to be processed, and the edge line of the material to be tested on the image to be processed.

S34：獲取標準待測物料的標準中心點與標準吸盤的標準特徵點的第一偏差值。 S34: Obtain a first deviation value between the standard center point of the standard material to be tested and the standard feature point of the standard suction cup.

S35：根據待測物料的邊緣線，計算待測物料的中心點。 S35: Calculate the center point of the material to be tested according to the edge line of the material to be tested.

S36：計算待測物料的中心點與空置吸盤的特徵點的第二偏差值。 S36: Calculate the second deviation value between the center point of the material to be tested and the feature point of the empty suction cup.

S37：根據第一偏差值和第二偏差值計算待測物料的定位偏差值。 S37: Calculate the positioning deviation value of the material to be tested according to the first deviation value and the second deviation value.

通過在吸盤1上設置特徵點3，使得在處理待處理圖像時，能夠識別待處理圖像上空置吸盤的特徵點，以及待處理圖像上待測物料2的邊緣線，再根據待測物料2的邊緣線，能夠計算待測物料2的中心點；同時，通過獲取標準待測物料的標準中心點與標準吸盤的標準特徵點的第一偏差值，以及待測物料2的中心點與空置吸盤的特徵點的第二偏差值，能夠計算待測物料的定位偏差值。 By setting the feature points 3 on the suction cup 1, when processing the image to be processed, the feature points of the empty suction cup on the image to be processed and the edge line of the material to be tested 2 on the image to be processed can be identified. The edge line of material 2 can calculate the center point of material 2 to be tested; at the same time, by obtaining the first deviation value between the standard center point of the standard material to be tested and the standard feature point of the standard suction cup, and the center point of the material to be tested 2 and the standard feature point The second deviation value of the feature point of the empty suction cup can calculate the positioning deviation value of the material to be tested.

較佳地，定位偏差值包括偏移量和偏移角度。 Preferably, the positioning deviation value includes an offset amount and an offset angle.

進一步較佳地，在平面坐標系內，偏移量(X，Y)的計算公式為：

Figure 110143433-A0305-02-0013-9
偏移角度的計算公式為：
Figure 110143433-A0305-02-0013-10
 其中，標準待測物料對應的標準中心點為(X1,Y1)，對應的標準吸盤的標準特徵點為(Xb,Yb)，對應的偏移角度為θ0，X 0=X b -X 1，Y 0=Y b -Y 1，θ0=arctan｜-Y 0/X 0｜；待測物料的中心點為(X'，Y')，對應的空置吸盤的特徵點為(
Figure 110143433-A0305-02-0013-12
，
Figure 110143433-A0305-02-0013-13
)，對應的偏移角度為
Figure 110143433-A0305-02-0013-11
，
Figure 110143433-A0305-02-0013-14
，
Figure 110143433-A0305-02-0013-15
，
Figure 110143433-A0305-02-0013-16
。 Further preferably, in the plane coordinate system, the calculation formula of the offset (X, Y) is:
Figure 110143433-A0305-02-0013-9
 The formula for calculating the offset angle is:
Figure 110143433-A0305-02-0013-10
 Among them, the standard center point corresponding to the standard material to be tested is (X 1 , Y 1 ), the standard feature point of the corresponding standard suction cup is (X b , Y b ), and the corresponding offset angle is θ 0 , X 0 = X b - X 1 , Y 0 = Y b - Y 1 , θ 0 = arctan |- Y 0 / X 0 |; the center point of the material to be tested is (X', Y') , and the corresponding feature point of the empty suction cup is (
Figure 110143433-A0305-02-0013-12
,
Figure 110143433-A0305-02-0013-13
 ), the corresponding offset angle is
Figure 110143433-A0305-02-0013-11
,
Figure 110143433-A0305-02-0013-14
,
Figure 110143433-A0305-02-0013-15
,
Figure 110143433-A0305-02-0013-16
.

較佳地，識別待處理圖像上機械臂的預設位置，以及待測物料的邊緣線之前，還包括：預先錄入標準吸盤的標準特徵點的座標，以及標準待測物料的標準中心點的座標，其中，標準待測物料的標準中心點和標準吸盤的標準特徵點分別為機械臂的取料端上預設於放料工位正上方時的物料中心點和空置吸盤的標準特徵點。 Preferably, before recognizing the preset position of the robotic arm on the image to be processed and the edge line of the material to be tested, it also includes: pre-entering the coordinates of the standard feature point of the standard suction cup, and the coordinates of the standard center point of the standard material to be tested. Coordinates, where the standard center point of the standard material to be tested and the standard feature point of the standard suction cup are the material center point and the standard feature point of the empty suction cup when the reclaiming end of the robotic arm is preset directly above the discharge station.

較佳地，本發明提供的用於機器人放料的動態影像定位方法還包括： Preferably, the dynamic image positioning method for robot feeding provided by the present invention further includes:

S5：在機械臂的取料端移動至攝像裝置視野範圍內時，控制攝像裝置進行拍照，獲得若干個待處理圖像。 S5: When the reclaiming end of the robotic arm moves into the field of view of the camera device, control the camera device to take pictures to obtain several images to be processed.

S6：分別根據各個待處理圖像計算待測物料的若干個定位偏差值。 S6: Calculate several positioning deviation values of the material to be tested according to each image to be processed.

S7：根據各個定位偏差值的平均值，調整機械臂的姿態。 S7: Adjust the posture of the robotic arm according to the average value of each positioning deviation value.

為了保證定位的精準度，可以在機械臂的取料端移動至攝像裝置視野範圍內時，控制攝像裝置進行多次拍照，以獲得若干個待處理圖像，再分別根據各個待處理圖像計算待測物料的若干個定位偏差值，能夠獲取若干個定位偏差值的平均值，以該平均值對機械臂的姿態進行調整，能夠使調整的精準度更高。 In order to ensure the accuracy of positioning, when the reclaiming end of the robotic arm moves into the field of view of the camera device, the camera device can be controlled to take pictures multiple times to obtain several images to be processed, and then calculated according to each image to be processed. For several positioning deviation values of the material to be tested, the average value of several positioning deviation values can be obtained, and the posture of the robot arm can be adjusted with the average value, which can make the adjustment more accurate.

實施例3 Example 3

本發明的一個實施例，如圖6所示，本發明還提供一種用於機器人放料的動態影像定位系統，包括機器人4、攝像裝置5和影像處理端6。 In an embodiment of the present invention, as shown in FIG. 6 , the present invention further provides a dynamic image positioning system for robot feeding, including a robot 4 , a camera device 5 and an image processing end 6 .

機器人4具有在一取料工位和一放料工位之間往復運動的一機械臂，且機器人4控制機械臂的取料端從取料工位吸取待測物料，並向放料工位移動。 The robot 4 has a mechanical arm that reciprocates between a reclaiming station and a discharging station, and the robot 4 controls the reclaiming end of the mechanical arm to absorb the material to be tested from the reclaiming station, and send it to the discharging station. move.

具體地，機械臂的取料端在轉移物料時，可以採用吸盤吸附的方式，不會使物料位置偏差較大，在其他實施例中，還可以抓取等方式。另外，本方案在轉移物料時，機械臂中間不會停止，也不會減速，以保證工作效率。 Specifically, when the material transfer end of the robotic arm transfers the material, the suction cup can be used to absorb the material, which will not cause a large deviation of the material position. In other embodiments, it can also be grasped. In addition, when transferring materials in this solution, the robot arm will not stop or slow down in the middle to ensure work efficiency.

攝像裝置5設置在取料工位和放料工位之間，機器人4在機械臂的取料端移動至攝像裝置5視野範圍內時，控制攝像裝置5進行拍照，獲得待處理圖像。 The camera device 5 is arranged between the reclaiming station and the discharging station. When the robot 4 moves the reclaiming end of the mechanical arm into the field of view of the camera device 5, it controls the camera device 5 to take pictures to obtain the image to be processed.

具體地，當機械臂的取料端移動至攝像裝置5視野範圍內時，由機器人4通過軟體通信方式給出觸發信號至攝像裝置5，使攝像裝置5開始拍照。 攝像裝置5可直接獲取到機械臂取料端的俯視圖。有別於現有技術中常用的感測器觸發的方式，該方式能夠使攝像裝置5提前準備拍照，從而不需要機械臂停止或減速。攝像裝置5可以為工業相機等，為保證攝像裝置5在機械臂的連續移動中獲取到清晰的待處理圖像，攝像裝置5可為高幀速全域快門相機。 Specifically, when the reclaiming end of the robotic arm moves within the field of view of the camera device 5, the robot 4 sends a trigger signal to the camera device 5 through software communication, so that the camera device 5 starts taking pictures. The camera device 5 can directly obtain the top view of the take-up end of the manipulator. Different from the sensor triggering method commonly used in the prior art, this method enables the camera device 5 to prepare for taking pictures in advance, so that the mechanical arm does not need to stop or decelerate. The camera device 5 may be an industrial camera or the like. In order to ensure that the camera device 5 can obtain clear images to be processed during the continuous movement of the robotic arm, the camera device 5 may be a high frame rate global shutter camera.

影像處理端6用於識別待處理圖像上待測物料的邊緣線，進而計算待測物料的定位偏差值。 The image processing terminal 6 is used to identify the edge line of the material to be tested on the image to be processed, and then calculate the positioning deviation value of the material to be tested.

在獲取待處理圖像後，通過圖像分析，能夠識別出處理圖像上待測物料的邊緣線，從而計算出待測物料的定位偏差值。 After acquiring the image to be processed, through image analysis, the edge line of the material to be tested on the processed image can be identified, thereby calculating the positioning deviation value of the material to be tested.

當機械臂的取料端運動至放料工位的正上方時，機器人4根據定位偏差值，調整機械臂的姿態進行放料。 When the reclaiming end of the robotic arm moves directly above the unloading station, the robot 4 adjusts the posture of the robotic arm to unload according to the positioning deviation value.

具體地，在計算出待測物料的定位偏差值後，便能夠調整機械臂的姿態，使得待測物料的位置回到標準位置，從而實現規範放料，便於待測物料之後的運輸、測試等。 Specifically, after calculating the positioning deviation value of the material to be tested, the posture of the robotic arm can be adjusted so that the position of the material to be tested returns to the standard position, so as to realize standardized feeding and facilitate the transportation and testing of the material to be tested afterward. .

通過將攝像裝置5設在取料工位和放料工位之間，使得當機器人4控制機械臂的取料端從取料工位吸取待測物料，並移動至攝像裝置5視野範圍內時，能夠直接控制攝像裝置5進行拍照，獲得待處理圖像，再識別待處理圖像上待測物料的邊緣線，便能夠計算出待測物料的定位偏差值，機器人根據定位偏差值調整機械臂的姿態，便能夠實現精準的放料。由於攝像裝置在拍照時，是直接由機器人通過軟體通信方式給出觸發信號至攝像裝置，不需要感測器觸發，因此不需要機器人停止運動，也不需要反復測試實際攝像裝置的拍照位置，使得機器人的定位放料效率更高、成本更低。 By arranging the camera device 5 between the reclaiming station and the discharging station, when the robot 4 controls the reclaiming end of the robotic arm to pick up the material to be tested from the reclaiming station and move it into the field of view of the camera device 5 , can directly control the camera device 5 to take pictures, obtain the image to be processed, and then identify the edge line of the material to be tested on the image to be processed, then the positioning deviation value of the material to be tested can be calculated, and the robot adjusts the mechanical arm according to the positioning deviation value. The posture can achieve accurate feeding. When the camera takes a picture, the robot directly sends a trigger signal to the camera through software communication, without the need for sensor triggering, so the robot does not need to stop moving, and there is no need to repeatedly test the shooting position of the actual camera, so that The positioning and feeding efficiency of the robot is higher and the cost is lower.

實施例4 Example 4

本發明的一個實施例，如圖2和3所示，在實施例3的基礎上，機械臂的取料端設置有至少一對吸盤1，每對吸盤1中一個用於吸取待測物料2，另一個空置。 In an embodiment of the present invention, as shown in Figures 2 and 3, on the basis of Embodiment 3, at least one pair of suction cups 1 is provided at the reclaiming end of the robotic arm, one of each pair of suction cups 1 is used to suck the material to be tested 2 , another vacant.

具體地，在本方案中，可以採用吸盤吸附的方式轉移物料，另外，為了便於偏差定位，可以將吸盤1設置為至少一對，每對吸盤1中一個用於吸取待測物料2，另一個空置，兩個吸盤相對位置固定，從而可以以空置吸盤為參考，對待測物料的偏差程度進行計算。 Specifically, in this solution, the material can be transferred by means of suction cups. In addition, in order to facilitate deviation positioning, at least one pair of suction cups 1 can be set, and one pair of suction cups 1 is used to absorb the material to be tested 2, and the other is used to absorb the material to be tested. When vacant, the relative positions of the two suction cups are fixed, so that the deviation of the material to be measured can be calculated by taking the vacant suction cup as a reference.

影像處理端6識別待處理圖像上待測物料2的邊緣線，以及對應的空置吸盤的邊緣線，並根據待測物料2的邊緣線和空置吸盤的邊緣線計算待測物料2的定位偏差值。 The image processing end 6 identifies the edge line of the material to be tested 2 on the image to be processed and the corresponding edge line of the empty suction cup, and calculates the positioning deviation of the material to be tested 2 according to the edge line of the material to be tested 2 and the edge line of the empty suction cup value.

具體地，在設置參考位置時，為了保證定位的精準，可以在機械臂的取料端設置至少一對吸盤1，每對吸盤1中的一個用於吸取待測物料，另一個空置，由於兩個吸盤1的相對位置固定，使得在處理待處理圖像時，通過識別待處理圖像上待測物料2的邊緣線，以及對應的空置吸盤的邊緣線，便能夠計算待測物料的定位偏差值。 Specifically, when setting the reference position, in order to ensure the accuracy of positioning, at least one pair of suction cups 1 can be set at the feeding end of the robotic arm, one of each pair of suction cups 1 is used to absorb the material to be tested, and the other is vacant. The relative positions of the suction cups 1 are fixed, so that when processing the image to be processed, the positioning deviation of the material to be tested can be calculated by identifying the edge line of the material to be tested 2 on the image to be processed and the corresponding edge line of the empty suction cup. value.

較佳地，吸盤1上均設置有特徵點3。 Preferably, the suction cups 1 are all provided with feature points 3 .

影像處理端6識別待處理圖像上空置吸盤的特徵點，以及待處理圖像上待測物料2的邊緣線，並根據待測物料2的邊緣線，計算待測物料2的中心點。 The image processing end 6 identifies the feature points of the empty suction cups on the image to be processed and the edge line of the material to be tested 2 on the image to be processed, and calculates the center point of the material to be tested 2 according to the edge line of the material to be tested 2 .

影像處理端6獲取標準待測物料的標準中心點與標準吸盤的標準特徵點的第一偏差值，以及待測物料2的中心點與空置吸盤的特徵點的第二偏差值，計算待測物料的定位偏差值。 The image processing end 6 obtains the first deviation value between the standard center point of the standard material to be tested and the standard feature point of the standard suction cup, and the second deviation value between the center point of the material to be tested 2 and the feature point of the empty suction cup, and calculates the material to be tested The positioning deviation value of .

通過在吸盤1上設置特徵點3，使得在處理待處理圖像時，能夠識別待處理圖像上空置吸盤的特徵點，以及待處理圖像上待測物料2的邊緣線，再根據待測物料2的邊緣線，能夠計算待測物料2的中心點；同時，通過獲取標準待測物料的標準中心點與標準吸盤的標準特徵點的第一偏差值，以及待測物料2的中心點與空置吸盤的特徵點的第二偏差值，能夠計算待測物料的定位偏差值。 By setting the feature points 3 on the suction cup 1, when processing the image to be processed, the feature points of the empty suction cup on the image to be processed and the edge line of the material to be tested 2 on the image to be processed can be identified. The edge line of material 2 can calculate the center point of material 2 to be tested; at the same time, by obtaining the first deviation value between the standard center point of the standard material to be tested and the standard feature point of the standard suction cup, and the center point of the material to be tested 2 and the standard feature point The second deviation value of the feature point of the empty suction cup can calculate the positioning deviation value of the material to be tested.

應當說明的是，上述實施例均可根據需要自由組合。以上所述僅是本發明的優選實施方式，應當指出，對於本技術領域的普通技術人員來說，在不脫離本發明原理的前提下，還可以做出若干改進和潤飾，這些改進和潤飾也應視為本發明的保護範圍。 It should be noted that the above embodiments can be freely combined as required. The above are only the preferred embodiments of the present invention. It should be pointed out that for those skilled in the art, without departing from the principles of the present invention, several improvements and modifications can be made. It should be regarded as the protection scope of the present invention.

S1-S4:步驟 S1-S4: Steps

Claims (8)

一種用於機器人放料的動態影像定位方法，包括在一取料工位和一放料工位之間往復運動的一機械臂，以及設置在該取料工位和該放料工位元之間的一攝像裝置，該動態影像定位方法包括步驟：控制該機械臂的一取料端從該取料工位吸取一待測物料，並向該放料工位移動；在該機械臂的取料端移動至該攝像裝置視野範圍內時，控制該攝像裝置進行拍照，獲得一待處理圖像；識別該待處理圖像上該待測物料的一邊緣線，進而計算該待測物料的一定位偏差值；及控制該機械臂的取料端運動至該放料工位的正上方，並根據該定位偏差值，調整該機械臂的姿態進行放料，其中，該機械臂的取料端設置有至少一對吸盤，每對該吸盤中的一個用於吸取該待測物料，另一個空置；其中，計算該待測物料的定位偏差值包括：識別該待處理圖像上該待測物料的邊緣線，以及對應的空置吸盤的邊緣線；及根據該待測物料的邊緣線和該空置吸盤的邊緣線計算該待測物料的定位偏差值。 A dynamic image positioning method for robot feeding, comprising a mechanical arm reciprocating between a reclaiming station and a feeding station, and a mechanical arm arranged between the feeding station and the feeding station A camera device between the two, the dynamic image positioning method includes the steps of: controlling a reclaiming end of the robotic arm to pick up a material to be measured from the reclaiming station, and moving to the discharging station; When the material end moves into the field of view of the camera device, control the camera device to take pictures to obtain an image to be processed; identify an edge line of the material to be tested on the image to be processed, and then calculate an edge of the material to be tested. Positioning deviation value; and control the reclaiming end of the mechanical arm to move directly above the discharging station, and adjust the posture of the mechanical arm to discharge according to the positioning deviation value, wherein the reclaiming end of the mechanical arm At least one pair of suction cups is provided, and one of the suction cups is used to absorb the material to be tested, and the other is vacant; wherein, calculating the positioning deviation value of the material to be tested includes: identifying the material to be tested on the image to be processed and the corresponding edge line of the empty suction cup; and calculate the positioning deviation value of the material to be tested according to the edge line of the material to be tested and the edge line of the empty suction cup. 如請求項1所述的用於機器人放料的動態影像定位方法，其中，該吸盤上均設置有特徵點，計算該待測物料的定位偏差值包括：識別該待處理圖像上該空置吸盤的特徵點，以及該待處理圖像上該待測物料的邊緣線； 獲取一標準待測物料的一標準中心點與一標準吸盤的一標準特徵點的一第一偏差值；根據該待測物料的邊緣線，計算該待測物料的中心點；計算該待測物料的中心點與該空置吸盤的特徵點的一第二偏差值；及根據該第一偏差值和該第二偏差值計算該待測物料的該定位偏差值。 The dynamic image positioning method for robot feeding according to claim 1, wherein feature points are set on the suction cups, and calculating the positioning deviation value of the material to be tested includes: identifying the empty suction cups on the image to be processed The feature points of , and the edge line of the material to be tested on the image to be processed; Obtain a first deviation value between a standard center point of a standard material to be tested and a standard feature point of a standard suction cup; calculate the center point of the material to be tested according to the edge line of the material to be tested; calculate the material to be tested A second deviation value between the center point of the empty suction cup and the characteristic point of the empty suction cup; and the positioning deviation value of the material to be tested is calculated according to the first deviation value and the second deviation value. 如請求項2所述的用於機器人放料的動態影像定位方法，其中，該定位偏差值包括一偏移量和一偏移角度。 The dynamic image positioning method for robot feeding according to claim 2, wherein the positioning deviation value includes an offset and an offset angle. 如請求項3所述的用於機器人放料的動態影像定位方法，其中，在平面坐標系內，該偏移量(X，Y)的計算公式為：
Figure 110143433-A0305-02-0019-17
 偏移角度θ的計算公式為：
Figure 110143433-A0305-02-0019-18
 其中，該標準待測物料對應的該標準中心點為(X1,Y1)，對應的該標準吸盤的該標準特徵點為(Xb,Yb)，對應的偏移角度為θ0，X 0=X b -X 1，Y 0=Y b -Y 1，θ0=arctan｜-Y 0/X 0｜；該待測物料的中心點為(X'，Y')，對應的該空置吸盤的特徵點為(
Figure 110143433-A0305-02-0019-20
，
Figure 110143433-A0305-02-0019-21
)，對應的偏移角度為
Figure 110143433-A0305-02-0019-19
，
Figure 110143433-A0305-02-0019-22
，
Figure 110143433-A0305-02-0019-23
，
Figure 110143433-A0305-02-0019-24
。 The dynamic image positioning method for robot feeding according to claim 3, wherein, in the plane coordinate system, the calculation formula of the offset (X, Y) is:
Figure 110143433-A0305-02-0019-17
 The formula for calculating the offset angle θ is:
Figure 110143433-A0305-02-0019-18
 Wherein, the standard center point corresponding to the standard material to be tested is (X 1 , Y 1 ), the corresponding standard feature point of the standard suction cup is (X b , Y b ), and the corresponding offset angle is θ 0 , X 0 = X b - X 1 , Y 0 = Y b - Y 1 , θ 0 = arctan |- Y 0 / X 0 |; the center point of the material to be tested is (X', Y') , corresponding to the The characteristic points of the vacant suction cups are (
Figure 110143433-A0305-02-0019-20
,
Figure 110143433-A0305-02-0019-21
) , the corresponding offset angle is
Figure 110143433-A0305-02-0019-19
,
Figure 110143433-A0305-02-0019-22
,
Figure 110143433-A0305-02-0019-23
,
Figure 110143433-A0305-02-0019-24
. 如請求項2所述的用於機器人放料的動態影像定位方法，其中，識別該待處理圖像上該待測物料的邊緣線之前，還包括：預先錄入該標準吸盤的該標準特徵點的座標，以及該標準待測物料的該標準中心點的座標，該標準待測物料的標準中心點和該標準吸盤的標準特徵點分別為該機械臂的取料端上預設於該放料工位正上方時的物料中心點和該空置吸盤的標準特徵點。 The dynamic image positioning method for robot feeding according to claim 2, wherein before identifying the edge line of the material to be tested on the image to be processed, the method further comprises: pre-entering the standard feature point of the standard suction cup. The coordinates, and the coordinates of the standard center point of the standard material to be measured, the standard center point of the standard material to be measured and the standard feature point of the standard suction cup are respectively preset on the unloading tool on the pick-up end of the robotic arm. The center point of the material when it is directly above and the standard feature point of the empty suction cup. 如請求項1-5的任一項所述的用於機器人放料的動態影像定位方法，還包括在該機械臂的取料端移動至該攝像裝置視野範圍內時，控制該攝像裝置進行拍照，獲得若干個該待處理圖像；分別根據各個該待處理圖像計算該待測物料的若干個該定位偏差值；及根據各個該定位偏差值的平均值，調整該機械臂的姿態。 The dynamic image positioning method for robot discharging according to any one of claims 1 to 5, further comprising controlling the camera to take pictures when the reclaiming end of the robotic arm moves within the field of view of the camera , obtain a number of the images to be processed; calculate a number of the positioning deviation values of the material to be tested according to each of the to-be-processed images; and adjust the posture of the robotic arm according to the average value of the positioning deviation values. 一種用於機器人放料的動態影像定位系統，包括：機器人，具有在一取料工位和一放料工位之間往復運動的一機械臂，且該機器人控制該機械臂的取料端從該取料工位吸取一待測物料，並向該放料工位移動；攝像裝置，設置在該取料工位和該放料工位之間，該機器人在該機械臂的取料端移動至該攝像裝置視野範圍內時，控制該攝像裝置進行拍照，獲得一待處理圖像； 影像處理端，用於識別該待處理圖像上該待測物料的邊緣線，進而計算該待測物料的一定位偏差值；及當該機械臂的取料端運動至該放料工位的正上方時，該機器人根據該定位偏差值，調整該機械臂的姿態進行放料，其中，該機械臂的取料端設置有至少一對吸盤，每對該吸盤中的一個用於吸取該待測物料，另一個空置；該影像處理端識別該待處理圖像上該待測物料的邊緣線，以及對應的空置吸盤的邊緣線，並根據該待測物料的邊緣線和該空置吸盤的邊緣線計算該待測物料的定位偏差值。 A dynamic image positioning system for robot unloading, comprising: a robot, which has a mechanical arm that reciprocates between a reclaiming station and a discharging station, and the robot controls a reclaiming end of the mechanical arm from The reclaiming station picks up a material to be tested and moves to the unloading station; the camera device is arranged between the reclaiming station and the unloading station, and the robot moves at the reclaiming end of the mechanical arm When the camera is within the field of view of the camera, control the camera to take pictures to obtain a to-be-processed image; The image processing end is used to identify the edge line of the material to be tested on the image to be processed, and then calculate a positioning deviation value of the material to be tested; and when the pick-up end of the robotic arm moves to the discharge station When it is directly above, the robot adjusts the posture of the mechanical arm to discharge materials according to the positioning deviation value, wherein at least a pair of suction cups are provided at the reclaiming end of the mechanical arm, and each of the suction cups is used to suck the to-be-to-be The image processing end identifies the edge line of the material to be tested on the image to be processed, and the corresponding edge line of the empty suction cup, and according to the edge line of the material to be tested and the edge of the empty suction cup Line to calculate the positioning deviation value of the material to be tested. 如請求項7所述的用於機器人放料的動態影像定位系統，其中，該吸盤上均設置有特徵點；該影像處理端識別該待處理圖像上該空置吸盤的特徵點，以及該待處理圖像上該待測物料的邊緣線，並根據該待測物料的邊緣線，計算該待測物料的中心點；該影像處理端獲取標準待測物料的標準中心點與一標準吸盤的一標準特徵點的一第一偏差值，以及該待測物料的中心點與該空置吸盤的特徵點的一第二偏差值，並根據該第一偏差值和該第二偏差值計算該待測物料的該定位偏差值。The dynamic image positioning system for robot feeding according to claim 7, wherein feature points are set on the suction cups; the image processing end identifies the feature points of the empty suction cups on the image to be processed, and the feature points of the suction cups to be processed Process the edge line of the material to be tested on the image, and calculate the center point of the material to be tested according to the edge line of the material to be tested; the image processing end obtains the standard center point of the standard material to be tested and a standard suction cup. A first deviation value of the standard feature point, and a second deviation value between the center point of the material to be tested and the feature point of the empty suction cup, and the material to be tested is calculated according to the first deviation value and the second deviation value The positioning deviation value of .
TW110143433A 2021-10-20 2021-11-22 Dynamic image positioning method and system for robot feeding TWI778870B (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111223243.8A CN113814984B (en) 2021-10-20 2021-10-20 Dynamic image positioning method and system for robot emptying
CN202111223243.8 2021-10-20

Publications (2)

Publication Number Publication Date
TWI778870B true TWI778870B (en) 2022-09-21
TW202317337A TW202317337A (en) 2023-05-01

Family

ID=78920740

Family Applications (1)

Application Number Title Priority Date Filing Date
TW110143433A TWI778870B (en) 2021-10-20 2021-11-22 Dynamic image positioning method and system for robot feeding

Country Status (2)

Country Link
CN (1) CN113814984B (en)
TW (1) TWI778870B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114749981B (en) * 2022-05-27 2023-03-24 中迪机器人(盐城)有限公司 Feeding and discharging control system and method based on multi-axis robot

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102207369A (en) * 2010-03-29 2011-10-05 富士施乐株式会社 Article recognition apparatus and article processing apparatus using the same
US10434655B2 (en) * 2014-09-03 2019-10-08 Canon Kabushiki Kaisha Robot apparatus and method for controlling robot apparatus
CN111490283A (en) * 2019-12-10 2020-08-04 江苏丰盈科技有限公司 Lamination process, lamination equipment and manipulator applied to lamination equipment

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107150032B (en) * 2016-03-04 2020-06-23 上海电气集团股份有限公司 Workpiece identification and sorting device and method based on multi-image acquisition equipment
CN108839024A (en) * 2018-06-29 2018-11-20 易思维（杭州）科技有限公司 A kind of visual guide method suitable for the automatic loading process of arrangements for automotive doors
CN210121750U (en) * 2019-06-28 2020-03-03 Oppo（重庆）智能科技有限公司 Assembling device
CN110561435B (en) * 2019-09-17 2021-04-27 北京康视杰视觉技术有限公司 Method, device and system for guiding manipulator and upper computer
CN111152222A (en) * 2020-01-07 2020-05-15 理光图像技术（上海）有限公司 Target object moving system
CN112894823B (en) * 2021-02-08 2022-06-21 珞石（山东）智能科技有限公司 Robot high-precision assembling method based on visual servo

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102207369A (en) * 2010-03-29 2011-10-05 富士施乐株式会社 Article recognition apparatus and article processing apparatus using the same
US10434655B2 (en) * 2014-09-03 2019-10-08 Canon Kabushiki Kaisha Robot apparatus and method for controlling robot apparatus
CN111490283A (en) * 2019-12-10 2020-08-04 江苏丰盈科技有限公司 Lamination process, lamination equipment and manipulator applied to lamination equipment

Also Published As

Publication number Publication date
CN113814984A (en) 2021-12-21
TW202317337A (en) 2023-05-01
CN113814984B (en) 2023-04-18

Similar Documents

Publication Publication Date Title
CN110125926B (en) Automatic workpiece picking and placing method and system
CN111452040B (en) System and method for associating machine vision coordinate space in a pilot assembly environment
CN109940662B (en) Image pickup device provided with vision sensor for picking up workpiece
CN111250406A (en) PCB detection production line automatic placement method and system based on visual positioning
EP3173194B1 (en) Manipulator system, image capturing system, transfer method of object, and carrier medium
JP4257570B2 (en) Transfer robot teaching device and transfer robot teaching method
TWI404609B (en) Parameters adjustment method of robotic arm system and adjustment apparatus
JP5370774B2 (en) Tray transfer apparatus and method
TWI532117B (en) Grain bonding device and its joint head device, and collet position adjustment method
JP5488806B2 (en) Tray transfer apparatus and method
JP5893695B1 (en) Article transport system
JP2019198950A (en) Robot system for taking out work-piece loaded in bulk state and robot system control method
CN109238135B (en) Method for accurately positioning incoming material to test box based on vision
CN110332884B (en) Alignment guiding method for upper and lower CCD cameras
TWI778870B (en) Dynamic image positioning method and system for robot feeding
CN109952178B (en) Working robot and working position correction method
CN109489558A (en) Range Measurement System and distance measurement method
CN114952898A (en) Robot system, device manufacturing apparatus, device manufacturing method, teaching position adjusting method, and computer-readable recording medium
CN112001967A (en) Method and device for guiding manipulator to carry object by camera
CN115008477B (en) Manipulator movement compensation method, manipulator movement compensation device and computer-readable storage medium
CN115159149A (en) Material taking and unloading method and device based on visual positioning
CN210100014U (en) Automatic pose recognition device for miniaturized materials
JP6991783B2 (en) Article transport method, article transport device, optical element manufacturing method, optical element manufacturing device, program, recording medium
TW202035255A (en) Object transporting method and system capable of transporting an object according to image recognition
CN108145711A (en) Product space moving method and system

Legal Events

Date Code Title Description
GD4A Issue of patent certificate for granted invention patent