CN103325106A - Moving workpiece sorting method based on LabVIEW - Google Patents

Abstract

Provided is a moving workpiece sorting method based on LabVIEW. The moving workpiece sorting method based on the LabVIEW comprises the following steps of (1) an image processing algorithm for video streams, wherein the image processing algorithm for the video stream is used for detecting the positions and the postures of moving workpieces from collected video, (2) a calibration algorithm for a camera, wherein the calibration algorithm for the camera is used for converting pixel coordinates of the moving workpieces in images of the camera into physical coordinates of the workpieces in a world coordinate system, (3) a correction algorithm for radial distortion of the camera, wherein the correction algorithm for the radial distortion of the camera is used for eliminating radial distortion of images introduced by a wide-angle lens, (4) a Kalman prediction algorithm, wherein the Kalman prediction algorithm is used for carrying out prediction on the positions of the moving workpieces to obtain the workpiece positions without the time lag, (5) a workpiece type recognition algorithm, wherein when the workpieces are conveyed through a conveyor belt, the camera collects the images of the workpieces, recognition is carried out on the types of the workpieces, and classification is facilitated, and (6) a motion control method for a mechanical arm, wherein the motion control method for the mechanical arm comprises a track planning method and a track control method, and the mechanical arm can select an optimal path to rapidly sort the workpieces.

Description

Moving Workpieces method for sorting based on LabVIEW

Technical field

This patent relates to the method for sorting technical field based on machine vision, relates in particular to a kind of visible detection method and product sorting method.

Background technology

Mechanical arm is as a new technology that occurs in the automation field, and its great function also just progressively is familiar with by people: the first, mechanical arm can replace part manually to finish some repeated manual labors; The second, mechanical arm can fulfil assignment fast according to the predefined flow high efficiency of people; Three, mechanical arm has improved workman's working condition greatly, raises labour productivity significantly, has accelerated the paces of industrial production automation.

Along with the fast development of economy, competition among enterprises is more and more fierce, and for raising the efficiency, reducing production costs, travelling belt is widely used.Travelling belt is widely used in industrial production system, and the labour has not only been saved in the application of travelling belt, has improved production efficiency, and has reduced production cost, has brought into play huge effect in commercial production.No matter be that carrying, assembling, workpiece quality detect and all need first target to be grasped, therefore, the classification crawl function of target on the travelling belt there is very high demand.

Traditional industrial robot generally adopts the mode of teaching or off-line programing that processing tasks is carried out path planning and movement programming, the action that just repeats simply in the process to programme in advance and set, therefore traditional industrial robot control technology can't sort Moving Workpieces.

Summary of the invention

A purpose of this patent provides the Moving Workpieces detection method that a kind of accuracy of detection is high, can adapt to the illumination condition variation.

Another purpose of this patent provide a kind of automaticity high, can realize than multiple types workpiece classification, workpiece method for sorting that reliability is higher.

The Moving Workpieces method for sorting of this patent may further comprise the steps:

1) image processing algorithm of video flowing detects position and the attitude of workpiece the motion in the middle of the video that gathers with this algorithm;

2) calibration algorithm of video camera is converted into the pixel coordinate of Moving Workpieces in camera review with this calibration algorithm the physical coordinates of workpiece in the world coordinate system.

3) the Lens Distortion Correction algorithm of video camera is in order to eliminate the radial distortion of the image of introducing because of wide-angle lens.

4) Kalman Prediction algorithm is predicted in order to the position to Moving Workpieces, obtains the location of workpiece without time lag.

5) the type identification algorithm of workpiece, when workpiece from the travelling belt through out-of-date, the camera acquisition workpiece image is identified the workpiece type, is convenient to classification.

6) motion control method of mechanical arm comprises method for planning track, and method for controlling trajectory makes mechanical arm can select optimal path, sorts rapidly workpiece.

Wherein, the algorithm of image processing comprises the extraction of moving target, the attitude detection of Moving Workpieces.This patent adopts the background subtraction point-score to obtain the image coordinate of Moving Workpieces.The background subtraction point-score is a kind of method that adopts present frame in the image sequence and reference background model relatively to detect moving object, and its performance depends on employed background modeling technology.Because background model is constantly being upgraded, so it can adapt to the variation of light, and general threshold method must change its threshold value when light environment changes.Definition image (x, y) is present frame, and acc (x, y) is background model, and frimage (x, y) is the prospect frame, and α is the context update rate, and its scope is 0-1, and acc (x, y) is initialized as 0.

$\mathrm{acc}(x,y)=\mathrm{\α}*\mathrm{image}(x,y)+(1-\mathrm{\α})*\mathrm{acc}(x,y)$

$\mathrm{frimage}(x,y)=\mathrm{image}(x,y)-\mathrm{acc}(x,y)$

According to the foreground image that separates, detect the location of workpiece at last.The attitude detection of Moving Workpieces is processed by gray scale first, seeks at the selected detection side Grad that makes progress to surpass the point of threshold value again, and these points are carried out fitting a straight line, calculates angle.

Wherein, the calibration algorithm of video camera is mainly for the demarcation of monocular two-dimensional visual system.Video camera is installed perpendicular to working face.World coordinate system is positioned on the working face, and the Z axis vertical plane is downward, and only there are translation relation in camera coordinate system and world coordinate system without spin, so rotation matrix R=I (unit matrix) and translation matrix P=[0 0 d are arranged] ^T, d is camera optical axis central point O _cDistance to working face.

$\left[\begin{array}{c}{x}_c\\ y_{\mathrm{<figure-callout\; id="1"\; label="c\; z\; c"\; filenames="127906DEST\_PATH\_IMAGE002.png"\; state="\{\{state\}\}">c</figure-callout>}}& \\ z_c{}_{}\\ 1\end{array}\right]=\left[\begin{array}{cc}\mathrm{<figure-callout\; id="0"\; label="R\; P"\; filenames="2013101293679100003DEST\_PATH\_IMAGE001.png"\; state="\{\{state\}\}">R</figure-callout>}& P\\ 0& 1\end{array}\right]\left[\begin{array}{c}{x}_w\\ y_{\mathrm{<figure-callout\; id="1"\; label="w\; z\; w"\; filenames="127906DEST\_PATH\_IMAGE002.png"\; state="\{\{state\}\}">w</figure-callout>}}& \\ z_w{}_{}\\ 1\end{array}\right]=\left[\begin{array}{c}{x}_w\\ {\mathrm{<figure-callout\; id="1"\; label="y\; w\; d"\; filenames="127906DEST\_PATH\_IMAGE002.png"\; state="\{\{state\}\}">y</figure-callout>}}_w& \\ d\\ 1\end{array}\right]$

In the formula: (x _c, y _c, z _c) be the coordinate of scene point under camera coordinate system, (x _w, y _w, z _w) be the coordinate of scene point under world coordinate system.Can obtain the coordinate of scene point under camera coordinate system by following formula, be easy to get x _c=x _w, y _c=y _w, the coordinate z of Moving Workpieces on working face _w=0.

$\left[\begin{array}{c}\mathrm{<figure-callout\; id="1"\; label="u\; v"\; filenames="127906DEST\_PATH\_IMAGE002.png"\; state="\{\{state\}\}">u</figure-callout>}& \\ v\\ 1\end{array}\right]=\left[\begin{array}{ccc}{k}_x& 0& u_0\\ 0& {\mathrm{<figure-callout\; id="0"\; label="k\; y\; v"\; filenames="2013101293679100003DEST\_PATH\_IMAGE001.png"\; state="\{\{state\}\}">k</figure-callout>}}_y& v_{}{}_0\\ 0& 0& 1\end{array}\right]\left[\begin{array}{c}{x}_c/z_c\\ y_c/{\mathrm{<figure-callout\; id="1"\; label="z\; c"\; filenames="127906DEST\_PATH\_IMAGE002.png"\; state="\{\{state\}\}">z</figure-callout>}}_c\\ 1\end{array}\right]$

$\left\{\begin{array}{c}{k}_{\mathrm{xd}}=\frac{u_2-u_1}{x_{w2}-x_{w1}}\\ k_{\mathrm{yd}}=\frac{v_2-v_1}{y_{w2}-{\mathrm{<figure-callout\; id="1"\; label="y\; w"\; filenames="127906DEST\_PATH\_IMAGE002.png"\; state="\{\{state\}\}">y</figure-callout>}}_w}\end{array}\right.$

Wherein (u, v) is the image coordinate of reference point; (u ₁, v ₁) be a P ₁Image coordinate, (x _W1, y _W1) be a some P ₁The two-dimensional world coordinate; (u ₂, v ₂) be a P ₂Image coordinate, (x _W2, y _W2) be a some P ₂The two-dimensional world coordinate; (u ₀, v ₀) be the image coordinate at camera optical axis center; k _Xd=k _xD, k _Yd=k _yD is the camera parameters that calibrates.

$\left\{\begin{array}{c}{x}_{\mathrm{wi}}=x_{\mathrm{<figure-callout\; id="1"\; label="w"\; filenames="127906DEST\_PATH\_IMAGE002.png"\; state="\{\{state\}\}">w</figure-callout>}1}+(u_i-u_1)/k_{\mathrm{xd}}\\ y_{\mathrm{wi}}={\mathrm{<figure-callout\; id="1"\; label="y\; w"\; filenames="127906DEST\_PATH\_IMAGE002.png"\; state="\{\{state\}\}">y</figure-callout>}}_w+(v_i-v_1)/k_{\mathrm{yd}}\end{array}\right.$

In the formula: (u _i, v _i) be any point P _iImage coordinate, (x _Wi, y _Wi) be a some P _iThe two-dimensional world coordinate.

Wherein, because wide-angle camera has distortion, and wherein obvious with radial distortion, so we carry out Lens Distortion Correction to camera.Simulated the radial distortion matrix of video camera in this patent with the method for linear regression (LR).The distortion equation of given first radial distortion:

$\left\{\begin{array}{c}{u}^{\&prime;}=a_{00}+a_{10}u+a_{01}v+a_{11}\mathrm{uv}+a_{20}{u}^2+a_{02}{v}^2\\ v^{\&prime;}=b_{00}+b_{10}u+b_{10}v+b_{11}\mathrm{uv}+b_{20}{u}^2+b_{02}{v}^2\end{array}\right.$

$\left[\begin{array}{c}{u}^{\&prime;}\\ v^{\&prime;}\end{array}\right]=\left[\begin{array}{cccccc}{a}_{00}& a_{10}& a_{01}& a_{11}& a_{20}& a_{02}\\ b_{00}& b_{10}& b_{01}& b_{11}& b_{20}& b_{02}\end{array}\right]\left[\begin{array}{c}1\\ u\\ v\\ \mathrm{uv}\\ u^2\\ v^2\end{array}\right]$

In the formula: (u, v) is the image coordinate of reference point, and (u', v') is the image coordinate behind the reference point distortion correction, a _St, b _StBe correction coefficient, s, t=0,1,2.

Wherein, the speed of Moving Workpieces is unknown, and position prediction adopts the Kalman Prediction algorithm.Gather respectively two two field pictures, interval 1s, the changes delta x of the location of workpiece is estimated velocity amplitude.Set up system model, then the Moving Workpieces two-dimensional world coordinate that calculates with above-described scaling method is as the position detection value, simultaneously with the speed that estimates as velocity measurement, form observation vector, calculate Kalman filter to the optimum prediction value of workpiece motion s state.

Wherein, the type identification of workpiece will gather the sample of various workpiece, and each sample is carried out feature detection, and the training shapes model, sets up the workpiece sample database.Then clarification of objective in the area-of-interest (ROI) of realtime graphic is detected, and mate with model in the database, calculate matching value, choose the highest result of matching value as the output of sorter.

Wherein, the motion control method of mechanical arm comprises trajectory planning, the TRAJECTORY CONTROL of mechanical arm, the crawl of electronic jaw control.The mechanical arm controller carries out trajectory planning according to the Work position information of host computer prediction to mechanical arm, and the control mechanical arm is adjusted the jaw attitude simultaneously by the expectation orbiting motion, the Moving Workpieces on the crawl travelling belt.Last as requested dissimilar workpiece the classification puts, and then carries out the sorting of next round workpiece.

Description of drawings

Fig. 1 is method of difference context update schematic diagram;

Fig. 2 is workpiece sorter schematic diagram;

Fig. 3 is the theory diagram of Kalman Prediction system;

Fig. 4 is predicted position and observation position Relations Among figure;

Fig. 5 is predicted position and observation position Error Graph.

Fig. 6 is mechanical arm servocontrol trajectory planning schematic diagram.

Fig. 7 is mechanical arm servocontrol process flow diagram.

Embodiment

Be further described below in conjunction with the technical scheme of drawings and Examples to this patent.

Embodiment:

Adopt the background subtraction point-score to extract moving target and at first will carry out modeling to background.Background model is constantly updated, just can be adapted to the variation of ambient light.Fig. 1 is the context update schematic diagram of system, and background frames upgrades according to the loop iteration in the schematic diagram.

$\mathrm{acc}(x,y)=\mathrm{\&alpha;}*\mathrm{image}(x,y)+(1-\mathrm{\&alpha;})*\mathrm{acc}(x,y)$

$\mathrm{frimage}(x,y)=\mathrm{image}(x,y)-\mathrm{acc}(x,y)$

Wherein image (x, y) is present frame, and acc (x, y) is background model, and frimage (x, y) is the prospect frame, and α is the context update rate, chooses α=0.15, and acc (x, y) is initialized as 0.According to the foreground image that separates, detect the location of workpiece at last.

The attitude detection of workpiece is carried out colour picture first the gray scale processing, and the ultimate range that measuring workpieces vertical direction and horizontal direction are shared judges that the attitude of workpiece is tending towards vertically or level.If be tending towards then rim detection from left to right of vertical attitude; If be tending towards then rim detection from top to bottom of horizontal attitude.Rim detection need to detect the point that on selected direction Grad surpasses threshold value, again these points is carried out fitting a straight line, calculates angle.

Workpiece identification on the streamline requires to provide at short notice classification results, the shape of workpiece, and Texture eigenvalue is relatively simple, therefore, directly carries out Model Matching, the schematic diagram of sorter such as Fig. 2 in top view.

At first, the sample of the various workpiece of input carries out feature detection to each sample in the pattern of LabVIEW classify program, and the training shapes model, sets up the workpiece sample database.Then clarification of objective in the area-of-interest (ROI) of realtime graphic is detected, and mate with model in the database, calculate matching value, choose the highest result of matching value as the output of sorter.

Distortion correction implementation process: in order to calculate 12 parameters in the Method for Camera Radial Distortion matrix, need at least the image coordinate of 6 point calibrations front and back.Gather a scaling board picture, threshold value is set, reference point can be detected, we select 12 points of required correcting area, record respectively its image coordinate (u _i, v _i) and (u _i', v _i'), i=1～12 see Table, and the equation shown in the formula composed as follows solves parameter a, b.

$\left[\begin{array}{c}{u}^{\&prime;}\\ v^{\&prime;}\end{array}\right]=\left[\begin{array}{cccccc}{a}_{00}& a_{10}& a_{01}& a_{11}& a_{20}& a_{02}\\ b_{00}& b_{10}& b_{01}& b_{11}& b_{20}& b_{02}\end{array}\right]\left[\begin{array}{cccc}1& 1& & 1\\ u_1& u_2& & u_{12}\\ v_1& v_2& ....& v_{12}\\ u_1{v}_1& u_2{v}_2& ....& u_{12}{v}_{12}\\ {u_1}^2& {u_2}^2& & {u_{12}}^2\\ {v_1}^2& {v_2}^2& & {v_{12}}^2\end{array}\right]$

The point order	1	2	3	4	5	6	7	8	9	10	11	12
													u(pixel)	538.1	626.67	536.94	625.82	537.88	627.1	538.59	627.4	569.88	599.41	598.97	569.74
v(pixel)	330.81	325.28	190.68	192.61	225.62	225.48	296.06	292.15	260.09	259.49	225.48	294.81
													u’(pixel)	550.9	653.71	551.16	653.94	551.22	653.83	551.14	653.87	585.58	620.01	620.11	585.55
v’(pixel)	348.46	347.99	210.82	210.58	244.95	245.01	314.02	314.02	279.49	279.76	244.98	314.12

The correction matrix of trying to achieve is:

$\left[\begin{array}{cccccc}{a}_{00}& a_{10}& a_{01}& a_{11}& a_{20}& a_{02}\\ b_{00}& b_{10}& b_{01}& b_{11}& b_{20}& b_{02}\end{array}\right]=\left[\begin{array}{cccccc}253.137& 0.11401& -0.168791& 3.66461E-5& 0.000887233& 0.00026485\\ 94.3187& -0.131471& 0.666474& 0.000604781& -4.54589E-6& -1.97698E-5\end{array}\right]$

Monocular two-dimensional visual system calibrating implementation process: choose image coordinate and world coordinates thereof after 2 reference point are proofreaied and correct on the scaling board, some P ₁: (u ₁', v ₁')=(454.62,194.04), (x ₁, y ₁)=(280.70,2.41); Point P ₂: (u ₂', v ₂')=(324.29,280.64), (x ₂, y ₂)=(69.89,142.48).According to monocular two-dimensional visual system principle noted earlier, programming realizes the demarcation of camera parameters.

The Kalman Prediction algorithm implementation: model system model, the Moving Workpieces two-dimensional world coordinate that then calculates with above-described scaling method be as the position detection value, simultaneously with the speed that estimates as velocity measurement, form observation vector.So obtained the optimum prediction value of Kalman filter, Fig. 3 is the prognoses system theory diagram.Set up following system model:

$\mathrm{dx}/\mathrm{dt}=\left[\begin{array}{ccc}0& 1& 0\\ 0& 0& 1\\ 0& 0& 0\end{array}\right]x\left(t\right)+\left[\begin{array}{c}0\\ 0\\ 1\end{array}\right]u\left(t\right)+\left[\begin{array}{ccc}1& 0& 0\\ 0& 1& 0\\ 0& 0& 1\end{array}\right]w\left(t\right)$

$y\left(t\right)=\left[\begin{array}{ccc}1& 0& 0\\ 0& 1& 0\end{array}\right]x\left(t\right)+\left[\begin{array}{c}0\\ 0\end{array}\right]u\left(t\right)+v\left(t\right)$

In this model, first equation is system state equation, and x (t) is the position x by the directions X workpiece, speed v _x, acceleration a _xThe state vector that forms, u (t) is the controlled quentity controlled variable of kinematic system.If u (t)=0 o'clock, system's acceleration was 0, is uniform motion, w (t) is system noise, and generally being made as average is zero white Gaussian noise.Second equation is output equation, the output valve of define system, the output valve y of this system (t) is defined as the vector (measured value will be consistent with the output valve type) that is comprised of position and speed, and v (t) is zero white Gaussian noise for measuring noise, also being made as average.

The programming of Kalman Prediction algorithm realizes: gather respectively two two field pictures, and interval 1s, the changes delta x of the location of workpiece is estimated velocity amplitude, as initial velocity v ₀Input Kalman wave filter.According to system model, the observation vector that position, speed form, Kalman filter calculates the optimal estimation value of motion state.Fig. 4 is position prediction value X(solid line) and position detection value X ' (dotted line) between graph of a relation.Such as figure, because the velocity estimation value has certain deviation, cause that certain deviation is arranged between X and the X ', but because the continuous renewal of Kalman Prediction model makes predicted value X approach gradually X ', both errors converge to zero gradually.Fig. 5 is the error between predicted value X and the observed reading X ', and the figure mid point is mixed and disorderly, is owing to there being observation noise, but finds out easily that error amount becomes and zero.

The crawl control of the electronic jaw of SMC LEFH32K2-32-R16N3: write the crawl control program by the programming software of jaw, set action 0 and action 1.Action 0 is crawl, and action 1 is for discharging.Then the I/O mouth by EPSON mechanical arm controller sends coded signal to the SMC controller, realizes the control of jaw.Mechanical arm programming software " Out1,208 " instruction namely sends binary code 11010000, replacement jaw from port one." Out1,144 " instruction namely sends binary code 10010000, write activity 0." Out1,176 " instruction namely sends binary code 10110000, with drive position 1, carries out grasping movement.Similarly, " Out1,145 " write action 1, and " Out1,177 " carry out release movement.

The servocontrol of EPSON SCARA-G6 mechanical arm: PC connects by the controller of ICP/IP protocol and mechanical arm, set the IP address of controller #201 network interface and PC under same subnet, use again the corresponding network interface of " OpenNet#201 " instruction unpack, " Read#201; data1; 12 " reads the movable information that receives and comprises X, Y, V, deg (angle), the motion of " MOVE " instruction control mechanical arm.System does not adopt the mode of real-time follow-up, because mechanical arm can shelter from Moving Workpieces.Assigned address x of default ₀=211(is with reference to the mechanical arm coordinate system), when the x of workpiece coordinate arrives x ₀After, mechanical arm is carried out trajectory planning, and the control mechanical arm is by the expectation orbiting motion, order the jaw grabbing workpiece again, on request workpiece is grabbed to desired location, transmitted signal discharges workpiece again, carry out the crawl of next round, whole servocontrol schematic diagram is seen Fig. 6, and the servocontrol process flow diagram is seen Fig. 7.

Claims (6)

1. workpiece method for sorting based on machine vision technique may further comprise the steps:

1) image processing algorithm of video flowing detects position and the attitude of workpiece the motion in the middle of the video that gathers with this algorithm;

2) calibration algorithm of video camera is converted into the pixel coordinate of Moving Workpieces in camera review with this calibration algorithm the physical coordinates of workpiece in the world coordinate system.

3) the Lens Distortion Correction algorithm of video camera is in order to eliminate the radial distortion of the image of introducing because of wide-angle lens.

4) Kalman Prediction algorithm is predicted in order to the position to Moving Workpieces, obtains the location of workpiece without time lag.5) the type identification algorithm of workpiece, when workpiece from the travelling belt through out-of-date, the camera acquisition workpiece image is identified the workpiece type, is convenient to classification.

6) motion control method of mechanical arm comprises method for planning track, and method for controlling trajectory makes mechanical arm can select optimal path, sorts rapidly workpiece.

2. the image processing algorithm of video flowing according to claim 1 is characterized in that detecting the background subtraction point-score of Moving Workpieces position and the method for detection workpiece attitude, may further comprise the steps:

1) video flowing that gathers is carried out background modeling:

acc(x,y)=α*image(x,y)+(1-α)*acc(x,y)

Wherein image (x, y) is present frame, and acc (x, y) is background model (being initialized as 0), and α is the context update rate, and its scope is 0-1, and system chooses α=0.15.

2) separate the prospect two field picture, detect the location of workpiece:

frimage(x,y)=image(x,y)-acc(x,y)

Wherein frimage (x, y) is the prospect frame.

3) colour picture being carried out gray scale processes.

4) with detecting workpiece vertical direction and the shared ultimate range of horizontal direction, judge that the attitude of workpiece is tending towards vertically or level.Then choose from left to right rim detection if be tending towards vertical attitude; Then choose from top to bottom rim detection if be tending towards horizontal attitude.Detection Grad on selected direction surpasses the point of threshold value, and these points are carried out fitting a straight line, calculates angle.

3. the Lens Distortion Correction algorithm of video camera according to claim 1 is characterized in that the method with linear regression (LR) has simulated the radial distortion matrix of video camera.May further comprise the steps:

1) sets up the Lens Distortion Correction model.

$\left\{\begin{array}{c}{u}^{\&prime;}=a_{00}+a_{10}u+a_{01}v+a_{11}\mathrm{uv}+a_{20}{u}^2+a_{02}{v}^2\\ v^{\&prime;}=b_{00}+b_{10}u+b_{01}v+b_{11}\mathrm{uv}+b_{20}{u}^2+b_{02}{v}^2\end{array}\right.$

In the formula: (u, v) is the image coordinate of reference point, and (u', v') is the image coordinate behind the reference point distortion correction, a _St, b _StBe correction coefficient, s, t=0,1,2.

2) obtain the image coordinate that 12 reference point are proofreaied and correct front and back, ask for the radial distortion matrix.

4. Kalman Prediction algorithm according to claim 1 is characterized in that need not to detect by scrambler the speed of travelling belt, and its prediction may further comprise the steps:

1) estimates workpiece motion s speed.

2) calculate optimum state estimation value according to observation signal and model estimated signal.

5. workpiece kind identification method according to claim 1 is characterized in that can realizing classification than the multiple types workpiece based on the workpiece sorter of LabVIEW visual development module (VDM), and directly the 3D workpiece sample that gathers is carried out the sorter training.May further comprise the steps:

1) sample of the various workpiece of input in the pattern of LabVIEW classify program carries out feature detection to each sample, and the training shapes model, sets up the workpiece sample database.

2) clarification of objective in the area-of-interest (ROI) of realtime graphic is detected, and mate with model in the database, calculate matching value, choose the highest result of matching value as the output of sorter.

6. workpiece automatic sorting method according to claim 1 is characterized in that EPSON SCARA-G6 mechanical arm trajectory planning and track following, makes its continuously grabbing workpiece.May further comprise the steps:

1) according to the Work position information of host computer prediction, mechanical arm is carried out trajectory planning.

2) the control mechanical arm moves according to desired trajectory.

3) adjust the jaw attitude, the Moving Workpieces on the crawl travelling belt.Last as requested dissimilar workpiece the classification puts, and then makes manipulator motion to holding point, waits for the sorting of next round workpiece.

Images