CN110096057A - A kind of Intelligent carrier control system - Google Patents
A kind of Intelligent carrier control system Download PDFInfo
- Publication number
- CN110096057A CN110096057A CN201910286740.9A CN201910286740A CN110096057A CN 110096057 A CN110096057 A CN 110096057A CN 201910286740 A CN201910286740 A CN 201910286740A CN 110096057 A CN110096057 A CN 110096057A
- Authority
- CN
- China
- Prior art keywords
- master control
- control chip
- image
- angle
- axis
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 claims abstract description 53
- 239000000463 material Substances 0.000 claims abstract description 44
- 230000008569 process Effects 0.000 claims abstract description 39
- 230000033001 locomotion Effects 0.000 claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 11
- 238000003708 edge detection Methods 0.000 claims description 11
- 230000001133 acceleration Effects 0.000 claims description 10
- 238000011897 real-time detection Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 230000007935 neutral effect Effects 0.000 claims description 3
- 230000000750 progressive effect Effects 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 2
- 230000011218 segmentation Effects 0.000 claims 1
- 230000000694 effects Effects 0.000 description 6
- 238000000605 extraction Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000011161 development Methods 0.000 description 4
- 238000004088 simulation Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 206010024642 Listless Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000005195 poor health Effects 0.000 description 1
- 235000020004 porter Nutrition 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 102000012498 secondary active transmembrane transporter activity proteins Human genes 0.000 description 1
- 108040003878 secondary active transmembrane transporter activity proteins Proteins 0.000 description 1
- 230000000392 somatic effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0234—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using optical markers or beacons
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0255—Control of position or course in two dimensions specially adapted to land vehicles using acoustic signals, e.g. ultra-sonic singals
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Aviation & Aerospace Engineering (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Electromagnetism (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Acoustics & Sound (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of Intelligent carrier control systems, including power supply module, identification module, six axis motion process components, holder, Master control chip, ultrasonic wave module, PID control circuit, the pressure sensor being located on floor truck gripper, go out the key that sends instructions;The identification module is connect with Master control chip;The six axis motion process component is connect with Master control chip;The identification module is arranged on holder, and the Master control chip is connect with holder;The ultrasonic wave module is connect with Master control chip;The Master control chip passes through the external DC speed-reducing of PID control circuit;The pressure sensor is connect with Master control chip;The key that sends instructions out is connect with Master control chip;Voltage needed for the power supply module is provided to Master control chip, identification module, ultrasonic wave module, pressure sensor.The present invention has image recognition processing ability, can identify material structure, two dimensional code, while can effectively avoid the damage of material in the handling process.
Description
Technical field
The present invention relates to intelligent robot technology fields, more particularly to a kind of Intelligent carrier control system.
Background technique
With the fast development (such as Taobao, spells the more at Jingdone district) of electric business, express delivery is at the modern life indispensable one
Part.In modern delivery industry, courier needs that express delivery is sorted and carried, and sorting work is usually staff's root
Rapid sorting is carried out according to mobile phone tail number, and handling work is staff's manual handling or by some simple porters
Tool.If courier by prolonged work will appear the situations such as in poor health perhaps listless encounter weight express delivery or
Situations such as fragile article express delivery, courier easily causes somatic damage, fragile article express delivery damage or sorting error.
And with the development of science and technology, mobile robot reaches its maturity, intelligent material conveying trolley is as mobile robot
One kind can substitute people and carry material in rugged environment, avoid danger, labour be reduced, before having wide development
Scape.
Currently, floor truck does not have image identification function largely, it is easy to produce mistake in the handling process and carries now
As, and floor truck in the prior art not can avoid the damage of fragile material in the handling process.
Summary of the invention
The present invention makes to solve existing floor truck without image identification function with not can avoid carrying fragile material
The problem of at damage, a kind of Intelligent carrier control system is provided, it, can be to the knot of material with recognition capability
Structure, color, two dimensional code are effectively identified, and can effectively avoid the damage of material.
For realize aforementioned present invention purpose, the technical solution adopted is as follows: further include for identification material structure, color and
The identification module of two dimensional code, for six axis motion process components of real-time detection floor truck posture, for improving identification module
The holder of detection range, Master control chip, for the ultrasonic wave module of ranging and avoidance, for controlling driving DC speed-reducing
PID control circuit, be arranged on the gripper of floor truck pressure sensor, go out to send instructions key;
The output end of the identification module is electrically connected with the input terminal of Master control chip;
The output end of the six axis motion process component is electrically connected with the input terminal of Master control chip, Master control chip it is defeated
Outlet is electrically connected with the input terminal of six axis motion process components, and the Master control chip is monitored and adjusts to the posture of trolley
It is whole;
The identification module is arranged on holder, and the output end of the Master control chip is electrically connected with the input terminal of holder;
The output end of the ultrasonic wave module is electrically connected with the input terminal of Master control chip;The output of the Master control chip
End passes through the external DC speed-reducing of PID control circuit;
The output end of the pressure sensor is electrically connected with the input terminal of Master control chip;
The output end of key that sends instructions out is electrically connected with the input terminal of Master control chip;
Electricity needed for the power supply module is used to provide to Master control chip, identification module, ultrasonic wave module, pressure sensor
Pressure.
Preferably, the identification module is machine vision module openmv;The machine vision module openmv includes
OV7725 camera chip, camera, the OV7725 camera chip are connect with camera, and the camera is by being built in
Machine vision algorithm in OV7725 camera chip, in real time identifies material;The camera glistens equipped with LED
Lamp, machine vision module openmv provide efficient machine vision algorithm, identification that can accurately to material two dimensional code;
Further, described identify including knowing to material two dimensional code, material shapes, color, size to material
Not, it can judge whether express delivery area has material according to the identification to material.
Still further, the image that the machine vision algorithm obtains two dimensional code to camera is handled, it is specific as follows:
S1: binary conversion treatment is carried out to image, formula is as follows:
Wherein, f (x, y) is the gray value of pixel at point (x, y);T is threshold value;
S2: carrying out expansion process to the image of obtained binaryzation, specific as follows:
In formula: A represents original image;B representative structure element, for being expanded to A;Φ represents empty set;
S3: median filtering is carried out to the image after expansion process and carries out noise reduction:
G (x, y)=median { f (x-k, y-l), (k, l ∈ W) }
Wherein, f (x, y) is expressed as original image, g (x, y) is expressed as that treated image, and W is two dimension pattern plate, k be
X-axis value in two dimension pattern plate W, l are the y-axis value in two dimension pattern plate W;
S4: edge detection is carried out to filtered image:
Edge detection is carried out to image by Sobel operator, calculates the gradient of image;
First the vector form of gradient is defined, as follows:
Wherein, GxIndicate the inclined x derivative of each location of pixels;GyIndicate the value of the inclined y derivative of each location of pixels;
It is as follows to image gradient processing:
In formula,For vector field homoemorphism
Sobel operator horizontal direction template:
-1 | 0 | 1 |
2 | 0 | 2 |
-1 | 0 | 1 |
Sobel operator vertical direction template:
0 | 0 | 0 |
1 | 2 | -1 |
Sobel operator is weighted using the gray value of neighborhood in four orientation of pixel, can be at edge according to it
Reach extreme value at point, to realize detection effect.This method not only has good edge detection effect, while having very well
Smoothing effect, accurate edge directional information can be provided for image.
Still further, bar code zone boundary is not very completely, so needing further to revise the boundary, so after edge detection
After be partitioned into a more complete bar code region, the bar code dividing method is as follows:
D1: being split the symbol in bar code using the method that region increases, and corrects bar code border by this;
D2: entire symbol is divided using convex hull algorithm;
D3: n times above step is repeated, the image of a width standard is obtained, wherein N is greater than or equal to 3;
Then image is decoded, the method is as follows:
F1: Grid Sampling is carried out to symbol, the image pixel on each intersection point of grid is sampled, and is determined according to threshold value
It is dark block or light block;
F2: one bitmap of construction indicates dark pixels with binary " 1 ", and " 0 " indicates light pixel, to obtain item
The original binary sequential value of code;
F3: error correction and decoding are carried out to the original binary sequential value for obtaining bar code;
F4: original binary sequential value is converted by data word according to the logic coding rule of bar code.
Preferably, the six axis motion process component uses mpu6050, and the mpu-6050 is at six axis movement of conformability
Component is managed, the mpu6050 includes acceleration transducer, gyroscope;The full lattice sensing range of the angular speed of the mpu6050 be ±
250,±500,±1000,±2000°/sec;The mpu6050 is used for the posture of real-time detection trolley, in detection trolley offset
During angle, detection error is reduced using glide filter, the trolley posture includes pitch angle, yaw angle, roll angle.
Further, the posture of the six axis motion process component detection trolley, specific as follows:
On determining trolley deviation angle, by the four element (q for receiving mpu60500,q1,q2,q3) calculated:
In formula, a is a constant, and i, j, k respectively indicate the unit vector of x, y, z axis;
The direction cosine matrix of Eulerian angles are as follows:
Wherein, ψ is the angle turned about the Z axis, and θ is the angle turned about the X axis, and γ is the angle rotated around Y-axis;
Because using a large amount of triangulo operation using the Eulerian angles differential equation, this brings very big difficulty, Duo Yiyong tetra- to CPU
Element method, calculation amount is small, easily operated, is relatively more suitable for engineering;
So being stated with the direction cosine matrix that Eulerian angles describe with quaternary sketch are as follows:
The collected three-dimensional vector of acceleration transducer is first converted into unit vector by the six axis motion process component, will
Gyroscope collected data gx, gy, gz, acceleration transducer collected data ax, ay, az input six axis motion process groups
Part:
Then four elements are converted into three elements of the third line in direction cosines;By the body of four last elements
Coordinate reference system is scaled neutral unit vector, specific as follows:
Vx=2 (q1q3-q0q2)
Vy=2 (q0q1-q2q3)
In formula, vx, vy, vz respectively indicate body coordinate x, y, z;
The four element differential equations are solved with single order Runge Kutta:
q0=q0+(-q1·gx-q2·gy-q3·gz)·halfT
q1=q1+(q0·gx+q2·gz-q3·gy)·halfT
q2=q2+(q0·gy-q1·gz+q3·gx)·halfT
q3=q3+(q0·gz+q1·gy-q3·gx)·halfT
In formula, T indicates the quaternary number update cycle;
Finally according to the transformational relation of four element Direct cosine matrixes and Eulerian angles, four elements are converted into Eulerian angles:
In formula, ψ is the angle turned about the Z axis, and θ is the angle turned about the X axis, and γ is the angle rotated around Y-axis;
Thus pitch angle, yaw angle, roll angle are obtained;
Pitch=asin (- 2q1q3+2q0q2)·57.3
In formula, pitch indicates pitch angle;Yaw indicates yaw angle, and roll indicates roll angle.
Preferably, the holder is cradle head of two degrees of freedom, and the holder includes two steering engines, and one of steering engine control is left
It turns right dynamic, the control of another steering engine rotates upwardly and downwardly, and makes identification range left and right 180 degree, the upper and lower 180 degree of identification module, improves
Detection range.
Preferably, the pressure sensor is arranged in the gripper of floor truck, when gripper closure, Master control chip inspection
The value of measuring pressure sensor, if pressure value is more than a certain numerical value, Master control chip issues stop signal control gripper and stops closure,
To accomplish to carry out to adapt to crawl material according to material size, damage material is avoided.
Further, the Master control chip uses stm32f103zet6 micro-chip processor, the stm32f103zet6
Micro-chip processor is communicated and is received information by serial ports and identification module, is communicated by I2C and six axis motion process components
Trolley deviation angle information is received, the rotation of holder and the opening and closing of gripper are controlled by PWM, it is straight by PID control circuit control
The speed and progressive position for flowing decelerating motor carry out instruction transmission by I/O port and ultrasonic wave module and receive distance.
Beneficial effects of the present invention are as follows:
1. the present invention by setting machine vision module openmv and machine vision algorithm accurately to material structure, color and
Two dimensional code is effectively identified, and then judges whether there are also materials in material area.
2., using pressure sensor, can accurately detect the dynamics of crawl material on gripper, keep material intact;Together
When trolley it is low in energy consumption, can work on the basis of the power supply power supply of 12V, can be realized express delivery sorting transport energy-saving, automate
The sorting transport work for helping express delivery staff, mitigates the labor intensity of labourer, improves working efficiency.
Detailed description of the invention
Fig. 1 is the present embodiment Intelligent carrier control system architecture figure.
Fig. 2 is the Principle of Process figure that the present embodiment is handled image based on LabVIEW.
Fig. 3 is the handling principle figure of the present embodiment camera calibration.
Fig. 4 is the present embodiment calibration result schematic diagram.
Fig. 5 is the program chart that the present embodiment corresponds to LabVIEW programming language.
Fig. 6 is the present embodiment verifying calibration result schematic diagram.
Fig. 7 is that the present embodiment does not carry out the picture before colour gamut extraction.
Fig. 8 is that the present embodiment carries out the picture after colour gamut extraction.
Fig. 9 is that the present embodiment does not carry out the picture before colour gamut extraction in realistic simulation environment.
Figure 10 is that the present embodiment carries out the picture before colour gamut extraction in realistic simulation environment.
Specific embodiment
The present invention will be described in detail with reference to the accompanying drawings and detailed description.
Embodiment 1
It further include material for identification as shown in Figure 1, a kind of Intelligent carrier control system, including power supply module 107
The identification module 106 of structure, color and two dimensional code, for real-time detection floor truck posture six axis motion process components 104,
For improving the holder 102 of identification module detection range, Master control chip 101, for the ultrasonic wave module of ranging and avoidance
108, for controlling the PID control circuit 103 of driving DC speed-reducing, the pressure sensing being arranged on the gripper of floor truck
Device 109 goes out the key 105 that sends instructions;
The output end of the identification module 106 is electrically connected with the input terminal of Master control chip 101;
The output end of the six axis motion process component 104 is electrically connected with the input terminal of Master control chip 101, the master control
The output end of coremaking piece 101 is electrically connected with the input terminal of six axis motion process components 104, and the Master control chip 101 is to trolley
Posture be monitored and adjust;
The identification module 106 is arranged on holder 102, and the output end of the Master control chip 101 is defeated with holder 102
Enter end electrical connection;
The output end of the ultrasonic wave module 108 is electrically connected with the input terminal of Master control chip 101;The Master control chip
101 output end passes through the external DC speed-reducing of PID control circuit 103;
The output end of the pressure sensor 109 is electrically connected with the input terminal of Master control chip 101;
The output end for sending instructions key 105 out is electrically connected with the input terminal of Master control chip 101, and send instructions key out
105 are used for transmission starting signal to Master control chip 101;
The power supply module 107 is used for Master control chip 101, identification module 106, ultrasonic wave module 108, pressure sensing
Device 109 provides required voltage.
The identification module 106 is machine vision module openmv;The machine vision module openmv includes
OV7725 camera chip, camera, the OV7725 camera chip are connect with camera, and the camera is by being built in
Machine vision algorithm in OV7725 camera chip, in real time identifies material;The camera glistens equipped with LED
The I/O port of lamp, the OV7725 camera chip is electrically connected with the I/O port of Master control chip.
It is described identify including identifying to material two dimensional code, material shapes, color, size to material.
The image that the machine vision algorithm obtains two dimensional code to camera is handled, specific as follows:
S1: binary conversion treatment is carried out to image, formula is as follows:
Wherein, f (x, y) is the gray value of pixel at point (x, y);T is threshold value;
S2: carrying out expansion process to the image of obtained binaryzation, specific as follows:
In formula: A represents original image;B representative structure element, for being expanded to A;Φ represents empty set;
S3: median filtering is carried out to the image after expansion process and carries out noise reduction:
G (x, y)=median { f (x-k, y-l), (k, l ∈ W) }
Wherein, f (x, y) is expressed as original image, g (x, y) is expressed as that treated image, and W is two dimension pattern plate, k be
X-axis value in two dimension pattern plate W, l are the y-axis value in two dimension pattern plate W;
S4: edge detection is carried out to filtered image:
Edge detection is carried out to image by Sobel operator, calculates the gradient of image;
First the vector form of gradient is defined, as follows:
Wherein, GxIndicate the inclined x derivative of each location of pixels;GyIndicate the value of the inclined y derivative of each location of pixels;
It is as follows to image gradient processing:
In formula,For vector field homoemorphism
Sobel operator horizontal direction template:
-1 | 0 | 1 |
2 | 0 | 2 |
-1 | 0 | 1 |
Sobel operator vertical direction template:
0 | 0 | 0 |
1 | 2 | -1 |
Sobel operator is weighted using the gray value of neighborhood in four orientation of pixel, can be at edge according to it
Reach extreme value at point, to realize detection effect.This method not only has good edge detection effect, while having very well
Smoothing effect, accurate edge directional information can be provided for image.
The present embodiment needs further to revise the boundary to the two-dimension code area of image, so after completing Image Edge-Detection
After be partitioned into complete bar code region;The bar code dividing method is as follows:
D1: being split the symbol in bar code using the method that region increases, and corrects bar code border by this;
D2: entire symbol is divided using convex hull algorithm;
D3: n times above step is repeated, the image of a width standard is obtained, wherein N is greater than or equal to 3;
Then image is decoded, the method is as follows:
F1: Grid Sampling is carried out to symbol, the image pixel on each intersection point of grid is sampled, and is determined according to threshold value
It is dark block or light block;
F2: one bitmap of construction indicates dark pixels with binary " 1 ", and " 0 " indicates light pixel, to obtain item
The original binary sequential value of code;
F3: error correction and decoding are carried out to the original binary sequential value for obtaining bar code;
F4: original binary sequential value is converted by data word according to the logic coding rule of bar code.
It is six axis of conformability fortune that six axis motion process components 104 described in the present embodiment, which use mpu6050, the mpu-6050,
Dynamic processing component 106, the mpu6050 includes acceleration transducer, gyroscope;The full lattice sensing of the angular speed of the mpu6050
Range is ± 250, ± 500, ± 1000, ± 2000 °/sec;The mpu6050 is used for the posture of real-time detection trolley, described
Trolley posture includes pitch angle, yaw angle, roll angle;The acceleration transducer, gyroscope are electrically connected with Master control chip respectively
It connects.
Holder 102 described in the present embodiment is cradle head of two degrees of freedom, and the cradle head of two degrees of freedom includes two steering engines, wherein one
A steering engine controls left-right rotation, and the control of another steering engine rotates upwardly and downwardly, make identification module 106 identification range left and right 180 degree,
Upper and lower 180 degree.
Pressure sensor 109 described in the present embodiment is arranged in the gripper of floor truck, when gripper closure, master control coremaking
Piece 101 detects the value of pressure sensor 109, if pressure value is more than a certain numerical value, Master control chip issues stop signal and controls hand
Pawl stops closure.
Master control chip 101 described in the present embodiment uses stm32f103zet6 micro-chip processor, described
Stm32f103zet6 micro-chip processor is communicated and is received information by serial ports and identification module 106, passes through I2C and six axis
The communication of motion process component 104 receives trolley deviation angle information, and the rotation of holder 102 and the opening and closing of gripper are controlled by PWM,
The speed and progressive position that DC speed-reducing is controlled by PID control circuit 103, pass through I/O port and ultrasonic wave module 108
It carries out instruction transmission and receives distance.
The present embodiment working principle is as follows: pressing out the key 105 that sends instructions, Master control chip 101, which receives out, to send instructions
Afterwards, judge whether material area has material by identification module identification 106, and identify that material two-dimensional barcode information determines the position of material
Information, Master control chip 101 carries out ranging and avoidance by ultrasonic wave module 108, and Control PID control circuit 103 drives directly
It flows decelerating motor to advance, while passing through the posture of six axis motion process components, 106 real-time detection trolley, carry out crawl material, lead to
The pressure sensor 109 being arranged on the gripper of floor truck is crossed, detection gripper holds the pressure of material, no more than setting
Value, avoids material from damaging.
The posture of six axis motion process component detection trolleies described in the present embodiment, specific as follows:
On determining trolley deviation angle, by the four element (q for receiving mpu60500,q1,q2,q3) calculated:
In formula, a is a constant, and i, j, k respectively indicate the unit vector of x, y, z axis;
The direction cosine matrix of Eulerian angles are as follows:
Wherein, ψ is the angle turned about the Z axis, and θ is the angle turned about the X axis, and γ is the angle rotated around Y-axis;
Because using a large amount of triangulo operation using the Eulerian angles differential equation, this brings very big difficulty, Duo Yiyong tetra- to CPU
Element method, calculation amount is small, easily operated, is relatively more suitable for engineering.
So being stated with the direction cosine matrix that Eulerian angles describe with quaternary sketch are as follows:
The collected three-dimensional vector of acceleration transducer is first converted into unit vector by the six axis motion process component, will
Gyroscope collected data gx, gy, gz, acceleration transducer collected data ax, ay, az input six axis motion process groups
Part:
Then four elements are converted into three elements of the third line in direction cosines;By the body of four last elements
Coordinate reference system is scaled neutral unit vector, specific as follows:
Vx=2 (q1q3-q0q2)
Vy=2 (q0q1-q2q3)
In formula, vx, vy, vz respectively indicate body coordinate x, y, z;
The four element differential equations are solved with single order Runge Kutta:
q0=q0+(-q1·gx-q2·gy-q3·gz)·halfT
q1=q1+(q0·gx+q2·gz-q3·gy)·halfT
q2=q2+(q0·gy-q1·gz+q3·gx)·halfT
q3=q3+(q0·gz+q1·gy-q3·gx)·halfT
In formula, T indicates the quaternary number update cycle;
Finally according to the transformational relation of four element Direct cosine matrixes and Eulerian angles, four elements are converted into Eulerian angles:
In formula, ψ is the angle turned about the Z axis, and θ is the angle turned about the X axis, and γ is the angle rotated around Y-axis;
Thus pitch angle, yaw angle, roll angle are obtained;
Pitch=asin (- 2q1q3+2q0q2)·57.3
In formula, pitch indicates pitch angle;Yaw indicates yaw angle, and roll indicates roll angle.
The present embodiment is based on machine vision module openmv and carries out visual development, using camera as vision lens, uses
Python language efficiently realizes core machine vision algorithm.
Vision pretreatment: in terms of visual processes: being primarily based on LabVIEW visual aids auxiliary openmv, obtain threshold value;
Then it by image preprocessing, is coordinately transformed, sets world coordinates, while correcting lens distortion, obtain the threshold of color lump identification
Value, so that target express delivery can be found according to the color of express delivery, as shown in Figure 2.
Camera calibration: camera is carried out by calling the Image Calibration in NI Vision Assistant
Calibration, converts world coordinate system for the pixel coordinate system of camera, as shown in Figure 3.
Calibration result, as shown in Figure 4 (side length of each grid is 3cm on scaling board).
The program chart of corresponding LabVIEW programming language is, as shown in Figure 5.
After the completion of calibration, verified using Clamp (Rake) the Lai Jinhang slide calliper rule linear measure longimetry of Vision Assistant
Calibration result, as shown in Figure 6.
As shown in Figure 6, it is known that: length sequences 21.16cm.
This calibration result is in allowable range of error.
After the completion of camera calibration, the coordinate in display can be obtained according to coordinate of the material in picture.
Threshold check: by calling the Threshold checking in NI Vision Assistant come to color lump
Threshold value is verified.As shown in fig. 7, not carrying out the picture before colour gamut extraction.LAB parameter is obtained after comparing by adjusting thresholds
Are as follows: (44,58,60,82,46,69) are brought this parameter into colour gamut and are extracted, obtain the picture after colour gamut is extracted, as shown in Figure 8.Pass through
Threshold check, the threshold value for finding express delivery are occurrences.
Vision color lump is realized:
Color lump identification primary function be with minor function "
Image.find_blobs (thresholds [, invert=False [, roi [, x_stride=2 [, y_
Stride=1 [, area_threshold=10 [, pixels_threshold=10 [, merge=False [, margin=0
[, threshold_cb=None [, merge_cb=None]]]]]]]]]])
The major function of this function is just to look for all blob (by the connection pixel region of threshold testing) in image,
And return to the list object that image.blob describes each blob.And parameter thresholds is in the above LabVIEW processing step
It obtains.
In realistic simulation environment, threshold value is surveyed, result as shown in Figure 9 is obtained and (does not carry out the figure before colour gamut extraction
Piece).As shown in Figure 10, it is extracted to bring parameter into colour gamut, obtains the picture after colour gamut is extracted.In Figure 10, color lump is identified completely,
Test result is good.To help sorting transport trolley accurately to recognize express delivery in chaotic environment.
By the above means, it is able to achieve the color for visually accurately identifying material, size and shape, to accurately sweep
The two-dimensional barcode information on material is retouched, and zone of departure or express delivery rest area are found according to color.
Obviously, the above embodiment of the present invention be only to clearly illustrate example of the present invention, and not be pair
The restriction of embodiments of the present invention.Any modification done within the spirit and principles of the present invention and changes equivalent replacement
Into etc., it should all be included in the scope of protection of the claims of the present invention.
Claims (10)
1. a kind of Intelligent carrier control system, including power supply module, it is characterised in that: further include material knot for identification
Structure, the identification module of color and two dimensional code, for six axis motion process components of real-time detection floor truck posture, for improving
The holder of identification module detection range, Master control chip, for the ultrasonic wave module of ranging and avoidance, for controlling driving direct current
The PID control circuit of decelerating motor, goes out the key that sends instructions at the pressure sensor being arranged on the gripper of floor truck;
The output end of the identification module is electrically connected with the input terminal of Master control chip;
The output end of the six axis motion process component is electrically connected with the input terminal of Master control chip, the Master control chip it is defeated
Outlet is electrically connected with the input terminal of six axis motion process components, and the Master control chip is monitored and adjusts to the posture of trolley
It is whole;
The identification module is arranged on holder, and the output end of the Master control chip is electrically connected with the input terminal of holder;
The output end of the ultrasonic wave module is electrically connected with the input terminal of Master control chip;The output end of the Master control chip is logical
Cross the external DC speed-reducing of PID control circuit;
The output end of the pressure sensor is electrically connected with the input terminal of Master control chip;
The output end of key that sends instructions out is electrically connected with the input terminal of Master control chip;
Voltage needed for the power supply module is used to provide to Master control chip, identification module, ultrasonic wave module, pressure sensor.
2. Intelligent carrier control system according to claim 1, it is characterised in that: the identification module is machine
Vision module openmv;The machine vision module openmv includes OV7725 camera chip, camera, and the OV7725 takes the photograph
It is connect with camera as head chip, the camera passes through the machine vision algorithm that is built in OV7725 camera chip, reality
When material is identified;The camera is equipped with LED flash.
3. Intelligent carrier control system according to claim 2, it is characterised in that: described to carry out identification packet to material
It includes and material two dimensional code, material shapes, color, size is identified.
4. Intelligent carrier control system according to claim 2, it is characterised in that: the machine vision algorithm is to taking the photograph
As head obtain two dimensional code image handled, it is specific as follows:
S1: binary conversion treatment is carried out to image, formula is as follows:
Wherein, f (x, y) is the gray value of pixel at point (x, y);T is threshold value;
S2: carrying out expansion process to the image of obtained binaryzation, specific as follows:
In formula: A represents original image;B representative structure element, for being expanded to A;Φ represents empty set;
S3: median filtering is carried out to the image after expansion process and carries out noise reduction:
G (x, y)=median { f (x-k, y-l), (k, l ∈ W) }
Wherein, f (x, y) is expressed as original image, g (x, y) is expressed as that treated image, and W is two dimension pattern plate, and k is in two dimension
X-axis value in template W, l are the y-axis value in two dimension pattern plate W;
S4: edge detection is carried out to filtered image:
Edge detection is carried out to image by Sobel operator, calculates the gradient of image;
First the vector form of gradient is defined, as follows:
Wherein, GxIndicate the inclined x derivative of each location of pixels;GyIndicate the value of the inclined y derivative of each location of pixels;
It is as follows to image gradient processing:
In formula, ▽ f is vector field homoemorphism
5. Intelligent carrier control system according to claim 4, it is characterised in that: after completing Image Edge-Detection,
It needs further to revise the boundary to the two-dimension code area of image, is then partitioned into complete bar code region;The bar code segmentation side
Method is as follows:
D1: being split the symbol in bar code using the method that region increases, and corrects bar code border by this;
D2: entire symbol is divided using convex hull algorithm;
D3: n times above step is repeated, the image of a width standard is obtained, wherein N is greater than or equal to 3;
Then image is decoded, the method is as follows:
F1: carrying out Grid Sampling to symbol, sample to the image pixel on each intersection point of grid, and is deep according to threshold value determination
Color lump or light block;
F2: one bitmap of construction indicates dark pixels with binary " 1 ", and " 0 " indicates light pixel, to obtain bar code
Original binary sequential value;
F3: error correction and decoding are carried out to the original binary sequential value for obtaining bar code;
F4: original binary sequential value is converted by data word according to the logic coding rule of bar code.
6. Intelligent carrier control system according to claim 1, it is characterised in that: the six axis motion process component
Using mpu6050, the mpu-6050 is six axis motion process component of conformability, the mpu6050 include acceleration transducer,
Gyroscope;The full lattice sensing range of the angular speed of the mpu6050 is ± 250, ± 500, ± 1000, ± 2000 °/sec;It is described
Mpu6050 is used for the posture of real-time detection trolley, and the trolley posture includes pitch angle, yaw angle, roll angle.
7. Intelligent carrier control system according to claim 6, it is characterised in that: the six axis motion process component
The posture of trolley is detected, specific as follows:
On determining trolley deviation angle, by the four element (q for receiving mpu60500,q1,q2,q3) calculated:
In formula, a is a constant, and i, j, k respectively indicate the unit vector of x, y, z axis;
The direction cosine matrix of Eulerian angles are as follows:
Wherein, ψ is the angle turned about the Z axis, and θ is the angle turned about the X axis, and γ is the angle rotated around Y-axis;
It is stated using the direction cosine matrix that Eulerian angles describe with quaternary sketch are as follows:
The collected three-dimensional vector of acceleration transducer is first converted into unit vector by the six axis motion process component, by gyro
Instrument collected data gx, gy, gz, acceleration transducer collected data ax, ay, az input six axis motion process components:
Then four elements are converted into three elements of the third line in direction cosines;By the body coordinate of four last elements
Referential is scaled neutral unit vector, specific as follows:
Vx=2 (q1q3-q0q2)
Vy=2 (q0q1-q2q3)
In formula, vx, vy, vz respectively indicate body coordinate x, y, z;
The four element differential equations are solved with single order Runge Kutta:
q0=q0+(-q1·gx-q2·gy-q3·gz)·halfT
q1=q1+(q0·gx+q2·gz-q3·gy)·halfT
q2=q2+(q0·gy-q1·gz+q3·gx)·halfT
q3=q3+(q0·gz+q1·gy-q3·gx)·halfT
In formula, T indicates the quaternary number update cycle;
Finally according to the transformational relation of four element Direct cosine matrixes and Eulerian angles, four elements are converted into Eulerian angles:
In formula, ψ is the angle turned about the Z axis, and θ is the angle turned about the X axis, and γ is the angle rotated around Y-axis;
Thus pitch angle, yaw angle, roll angle are obtained;
Pitch=asin (- 2q1q3+2q0q2)·57.3
In formula, pitch indicates pitch angle;Yaw indicates yaw angle, and roll indicates roll angle.
8. Intelligent carrier control system according to claim 1, it is characterised in that: the holder is two degrees of freedom cloud
Platform, the holder include two steering engines, and one of steering engine controls left-right rotation, and the control of another steering engine rotates upwardly and downwardly, is arranged
The identification range of identification module is left and right 180 degree, upper and lower 180 degree.
9. Intelligent carrier control system according to claim 1, it is characterised in that: the pressure sensor setting exists
In the gripper of floor truck, when gripper closure, Master control chip detects the value of pressure sensor, if pressure value is more than a certain number
Value, Master control chip issue stop signal control gripper and stop closure.
10. according to the described in any item Intelligent carrier control systems of claim 2~9, it is characterised in that: the main control
Chip uses stm32f103zet6 micro-chip processor, and the stm32f103zet6 micro-chip processor passes through serial ports and identification module
Information is communicated and received, trolley deviation angle information is received by I2C and the communication of six axis motion process components, passes through PWM
The rotation of holder and the opening and closing of gripper are controlled, by the speed and progressive position of PID control circuit control DC speed-reducing, are led to
It crosses I/O port and ultrasonic wave module carries out instruction transmission and receives distance.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910286740.9A CN110096057A (en) | 2019-04-10 | 2019-04-10 | A kind of Intelligent carrier control system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910286740.9A CN110096057A (en) | 2019-04-10 | 2019-04-10 | A kind of Intelligent carrier control system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110096057A true CN110096057A (en) | 2019-08-06 |
Family
ID=67444629
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910286740.9A Pending CN110096057A (en) | 2019-04-10 | 2019-04-10 | A kind of Intelligent carrier control system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110096057A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111452046A (en) * | 2020-03-31 | 2020-07-28 | 佛山科学技术学院 | Virtual reality-based explosive-handling robot system, control method and storage medium |
CN114185284A (en) * | 2021-10-20 | 2022-03-15 | 福建江夏学院 | Internet of things reconnaissance system based on STM32 and control method thereof |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080249663A1 (en) * | 2005-09-27 | 2008-10-09 | Honda Motor Co., Ltd. | Robot control information generator and robot |
CN205855355U (en) * | 2016-08-16 | 2017-01-04 | 国网山东省电力公司滨州市滨城区供电公司 | Goods provides automatic transporting device |
CN106383514A (en) * | 2015-07-29 | 2017-02-08 | 湖北汽车工业学院 | Remote control detection vehicle |
CN206178473U (en) * | 2016-10-18 | 2017-05-17 | 张锦迪 | Control system of intelligence materials handling dolly |
CN108268825A (en) * | 2016-12-31 | 2018-07-10 | 广州映博智能科技有限公司 | Three-dimensional face tracking and expression recognition system based on mobile holder |
CN108297084A (en) * | 2018-03-16 | 2018-07-20 | 五邑大学 | A kind of intelligent conveyor type mechanical arm system based on image recognition |
CN108834576A (en) * | 2018-06-07 | 2018-11-20 | 华南农业大学 | A kind of citrus picking robot and its implementation based on binocular vision |
CN208276902U (en) * | 2018-06-11 | 2018-12-25 | 深圳华制智能制造技术有限公司 | A kind of Multi-sensor Fusion mobile robot |
-
2019
- 2019-04-10 CN CN201910286740.9A patent/CN110096057A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080249663A1 (en) * | 2005-09-27 | 2008-10-09 | Honda Motor Co., Ltd. | Robot control information generator and robot |
CN106383514A (en) * | 2015-07-29 | 2017-02-08 | 湖北汽车工业学院 | Remote control detection vehicle |
CN205855355U (en) * | 2016-08-16 | 2017-01-04 | 国网山东省电力公司滨州市滨城区供电公司 | Goods provides automatic transporting device |
CN206178473U (en) * | 2016-10-18 | 2017-05-17 | 张锦迪 | Control system of intelligence materials handling dolly |
CN108268825A (en) * | 2016-12-31 | 2018-07-10 | 广州映博智能科技有限公司 | Three-dimensional face tracking and expression recognition system based on mobile holder |
CN108297084A (en) * | 2018-03-16 | 2018-07-20 | 五邑大学 | A kind of intelligent conveyor type mechanical arm system based on image recognition |
CN108834576A (en) * | 2018-06-07 | 2018-11-20 | 华南农业大学 | A kind of citrus picking robot and its implementation based on binocular vision |
CN208276902U (en) * | 2018-06-11 | 2018-12-25 | 深圳华制智能制造技术有限公司 | A kind of Multi-sensor Fusion mobile robot |
Non-Patent Citations (2)
Title |
---|
曹旭东: "基于ROS 与四元数互补滤波的IMU 姿态解算研究", 《工业控制计算机》 * |
谢俊鑫: "基于互联网及二维码识别技术的公路小型桥梁技术状况评定系统研究", 《中国优秀博硕士学位论文全文数据库(硕士) 工程科技Ⅱ辑》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111452046A (en) * | 2020-03-31 | 2020-07-28 | 佛山科学技术学院 | Virtual reality-based explosive-handling robot system, control method and storage medium |
CN114185284A (en) * | 2021-10-20 | 2022-03-15 | 福建江夏学院 | Internet of things reconnaissance system based on STM32 and control method thereof |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10928204B2 (en) | Industrial vehicle with feature-based localization and navigation | |
CN106737665B (en) | Based on binocular vision and the matched mechanical arm control system of SIFT feature and implementation method | |
CN111507976B (en) | Defect detection method and system based on multi-angle imaging | |
Azad et al. | Stereo-based 6d object localization for grasping with humanoid robot systems | |
CN103747667B (en) | A kind of vision-based detection for the automatic mounted box of Notebook Battery and control system | |
CN108010074A (en) | A kind of workpiece inspection method and system based on machine vision | |
CN115609591B (en) | Visual positioning method and system based on 2D Marker and compound robot | |
CN109506628A (en) | Object distance measuring method under a kind of truck environment based on deep learning | |
CN110096057A (en) | A kind of Intelligent carrier control system | |
CN105631893A (en) | Method and device for detecting whether capacitor is correctly mounted through photographing | |
CN110553650B (en) | Mobile robot repositioning method based on small sample learning | |
CN114049624B (en) | Ship cabin intelligent detection method and system based on machine vision | |
CN111582123A (en) | AGV positioning method based on beacon identification and visual SLAM | |
CN110866949A (en) | Center point positioning method and device, electronic equipment and storage medium | |
CN107300382A (en) | A kind of monocular visual positioning method for underwater robot | |
US10960550B2 (en) | Identification code reading apparatus and machine learning device | |
CN112926503A (en) | Automatic captured data set generation method based on rectangle fitting | |
CN108009574A (en) | A kind of rail clip detection method | |
CN109460757A (en) | Seal location recognition method and device | |
CN112215308A (en) | Single-order detection method and device for hoisted object, electronic equipment and storage medium | |
Truong et al. | New lane detection algorithm for autonomous vehicles using computer vision | |
CN109079777B (en) | Manipulator hand-eye coordination operation system | |
CN113269234A (en) | Connecting piece assembly detection method and system based on target detection | |
CN115984806B (en) | Dynamic detection system for road marking damage | |
Jiang et al. | Mobile robot gas source localization via top-down visual attention mechanism and shape analysis |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190806 |